CN102867005A - Retrieving device, retrieving method and vehicle-mounted navigation apparatus - Google Patents
Retrieving device, retrieving method and vehicle-mounted navigation apparatus Download PDFInfo
- Publication number
- CN102867005A CN102867005A CN2011101881686A CN201110188168A CN102867005A CN 102867005 A CN102867005 A CN 102867005A CN 2011101881686 A CN2011101881686 A CN 2011101881686A CN 201110188168 A CN201110188168 A CN 201110188168A CN 102867005 A CN102867005 A CN 102867005A
- Authority
- CN
- China
- Prior art keywords
- mentioned
- template
- search terms
- data
- retrieval
- 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.)
- Pending
Links
Images
Abstract
The invention discloses a retrieving device, a retrieving method and a vehicle-mounted navigation apparatus applying the retrieving device. A retrieving result corresponding to regional information can be displayed preferentially in the retrieving result according to the regional information represented by a sound signal of a user. The retrieving device comprises an input part for inputting the sound signal, a command storage part for storing a plurality of sound retrieval commands, a retrieval item storage part for storing a plurality of retrieval item data, a command judgment part for sound recognition and a data extraction part for extracting the retrieval item data corresponding to the judged sound retrieval command; the plurality of sound retrieval commands are composed of a standard template and a plurality of regional templates; the retrieval item data include the regional information; the command judgment part analyzes the frequency of the sound signal, selects corresponding template and carries out sound recognition, and the data extraction part preferentially displays the retrieval item data including the regional information which is the same as the region represented by the selected template.
Description
Technical field
The present invention relates to indexing unit, the search method of retrieving based on user's voice signal and the on-vehicle navigation apparatus of having used this indexing unit, relating in particular to can be according to indexing unit, search method and the on-vehicle navigation apparatus of the represented regional information preferential demonstration in result for retrieval of user's the voice signal result for retrieval corresponding with this regional information.
Background technology
In recent years, along with the development of voice recognition technology, realized the control based on voice signal in the increasing electronic equipment.For example, in some on-vehicle navigation apparatuses, set the functions such as path of navigation, music playing, broadcast listening and interconnection network and not only can realize by operation control panel, can also realize by user's voice signal.
For example, in the situation that the user retrieves facility by voice signal, when the user sends the voice signal in " restaurant " and so on, as shown in Figure 11, can show restaurant's facilities such as " outside the river river Xing Hai shop ", " restaurant, Dalian ", " restaurant, nine divisions of China in remote antiquity ", " Shanghai-Hangzhou restaurant ", " seafood restaurant ", " Guangdong dishes dining room, the peninsula " at display screen, the user can operate one of them restaurant easily like this, for example some restaurants is set as the destination.
In the situation that the user comes music playing by voice signal, when the user sent the voice signal of " music " and so on, this on-vehicle navigation apparatus can be play the predefined song of user automatically.Also can be as shown in figure 12, send after the voice signal of " music " and so on the user, the user shows the song tabulation comprise the music such as " Chinese songs 1 ", " Chinese songs 2 ", " Chinese songs 3 ", " English song 1 ", " English song 2 ", " English song 3 ", " Jealousy 1 " at display screen, so that can select to wish the song play easily.
In the situation that the user comes interconnection network by voice signal, when the user sent the voice signal of " interconnection network " and so on, this on-vehicle navigation apparatus started browser and shows the webpage of acquiescence at display screen.Next, if the user has sent again the voice signal of concrete web site name, then vehicle-mounted this website that will certainly be dynamically connected on display screen perhaps shows the list of websites relevant with this web site name.For example, in the situation that the user has sent " Alpine website " this voice signal, demonstrate the list of websites of shown in Figure 13 comprising " Alpine China website ", " Alpine Japan website ", " Alpine U.S. website " etc. at display screen.
In addition, in some on-vehicle navigation apparatuses, not only have function of carrying out various operations by voice signal as described above, also realized the identification to the dialect input.In such on-vehicle navigation apparatus, can according to frequency, semantic analysis, the model of rhythm formation and the occurrence frequency of particular phoneme harmony simple or compound vowel of a Chinese syllable etc. of sound, effectively identify the kind of dialect.Further, can compare voice signal and the identification dictionary of pre-prepd dialect or the similarity of dialect template inputted, thereby identify exactly the sound retrieval order corresponding with voice signal.
In technical scheme in the past, although possessed the function of identification dialect or other languages, no matter use which kind of dialect or language, the result for retrieval that obtains all is identical.For example, for " restaurant " of mandarin and " restaurant " these two voice commands of Sichuan dialect, their result for retrieval is duplicate.In this case, wish to search the restaurant of Sichuan style if say the user of Sichuan dialect, then must carry out more detailed operation.
Summary of the invention
The present invention makes in view of the above problems, its purpose is the on-vehicle navigation apparatus that a kind of indexing unit, search method is provided and used this indexing unit, and this indexing unit, search method and the on-vehicle navigation apparatus of having used this indexing unit can show the result for retrieval corresponding with this regional information according to the represented regional information of user's voice signal is preferential in result for retrieval.
The invention provides a kind of indexing unit, it is characterized in that, possess: input part, be used for input audio signal, demanded storage section is used for a plurality of sound retrieval orders that storage is made of predefined word; The search terms storage part is used for the storage multiple search terms data corresponding with each tut retrieval command difference; Command determination section carries out voice recognition to the voice signal from above-mentioned input part input, judges the tut retrieval command of inputting; And data extraction unit, the corresponding search terms data of sound retrieval order of judging from above-mentioned multiple search terms extracting data and mentioned order judging part, and be presented on the display part, in above-mentioned indexing unit, above-mentioned a plurality of sound retrieval order is made of standard form and region template, and above-mentioned search terms data comprise respectively regional information, the mentioned order judging part is analyzed at least from the frequency of the voice signal of above-mentioned input part input, from above-mentioned standard form and region template, select the template corresponding with this voice signal, and carry out voice recognition and process, above-mentioned data extraction unit is the preferential search terms data that comprise the identical regional information in the represented region of the template selected with the mentioned order judging part that show on above-mentioned display part.
In above-mentioned indexing unit, comprise in the preferred above-mentioned search terms data in residence data, facility name data, melody name data, artist name data, the telephone number data more than 2.
In above-mentioned indexing unit, preferred above-mentioned region template comprises at least a in the template of dialect of different regions of template, other countries of standard speech of template, other countries of the dialect of deifferent regions.China.
In above-mentioned indexing unit, preferably also storing the some templates of expression in the mentioned order storage part is the default logo of acquiescence template.
In above-mentioned indexing unit, preferred mentioned order judging part is not being selected in the situation of the template corresponding with this voice signal from above-mentioned standard form and region template, utilizes the acquiescence template to carry out voice recognition and processes.
The present invention also provides a kind of search method, this search method is used in indexing unit, this indexing unit possesses demanded storage section and search terms storage part, this demanded storage section is used for a plurality of sound retrieval orders that storage is made of predefined word, this search terms storage part is used for the storage multiple search terms data corresponding with each tut retrieval command difference, this search method is characterised in that, comprise: input step, input audio signal, the command determination step, the voice signal of inputting is carried out voice recognition, according to a plurality of sound retrieval orders in the mentioned order storage part, judge the sound retrieval order corresponding with above-mentioned input signal; And data extraction step, in the multiple search terms data from above-mentioned search terms storage part, extract the search terms data corresponding with the tut retrieval command, and be presented on the display part, above-mentioned a plurality of sound retrieval order is divided into standard form and region template, and above-mentioned search terms data comprise respectively regional information, in the mentioned order determining step, at least analyze the frequency by the voice signal of above-mentioned input step input, from above-mentioned standard form and region template, select the template corresponding with this voice signal, and carry out voice recognition and process, in above-mentioned data extraction step, the preferential search terms data that comprise the regional information identical with the represented region of the template of selecting that show on above-mentioned display part.
The present invention also provides a kind of on-vehicle navigation apparatus, it is characterized in that, comprises above-mentioned indexing unit.
The invention effect
Indexing unit of the present invention, search method and the on-vehicle navigation apparatus of having used this indexing unit can show the result for retrieval corresponding with this regional information according to the represented regional information of user's voice signal is preferential in result for retrieval, thereby further screening that the user may carry out this result for retrieval or the operation of ordering have been saved, obtain to save user's running time, improved the effect of the operability of device.Especially for just for the user of steering vehicle, can reduce the user confirms on-vehicle navigation apparatus with eyes number of times, can guidance path be set more easily, safely or carry out relevant multimedia operation.
Description of drawings
Fig. 1 is the structural drawing of the indexing unit of expression the first embodiment.
Fig. 2 is the schematic diagram that expression is stored in the template kind in the demanded storage section of indexing unit.
Fig. 3 is the schematic diagram that expression is stored in the search terms data in the search terms storage part of indexing unit.
Fig. 4 is the process flow diagram of indexing unit when retrieving of expression the first embodiment.
Fig. 5 is the figure of the result for retrieval of the embodiment 1 in expression the first embodiment.
Fig. 6 is the figure of the result for retrieval of the embodiment 2 in expression the first embodiment.
Fig. 7 is the figure of the result for retrieval of the embodiment 3 in expression the first embodiment.
Fig. 8 is the schematic diagram that expression is stored in the sound retrieval order in the demanded storage section of indexing unit of the second embodiment.
Fig. 9 is the structural drawing of the indexing unit of expression the second embodiment.
Figure 10 is the structural drawing of the on-vehicle navigation apparatus of expression the 3rd embodiment.
Figure 11 is the figure of result for retrieval of the facility name of expression prior art.
Figure 12 is the figure of result for retrieval of the music track of expression prior art.
Figure 13 is the figure of result for retrieval of the website of expression prior art.
Embodiment
The first embodiment
Below, with reference to Fig. 1 the structure of the indexing unit of the first embodiment of the present invention is described.
As shown in Figure 1, the indexing unit 10 of the first embodiment possesses input part 11, demanded storage section 12, search terms storage part 13, command determination section 14, data extraction unit 15 and display part 16.Command determination section 14 in Fig. 1 and data extraction unit 15 can be that separate microprocessor consists of, and also can be formed in the inside of not shown 1 control part (CPU).
Input part 11 is used for input audio signal.For example, receive voice signal from the user by Mike, and the voice signal that receives is sent to command determination section 13.
Demanded storage section 12 is used for a plurality of sound retrieval orders that storage is made of predefined word.Above-mentioned a plurality of sound retrieval order constitutes respectively the sound retrieval order of standard form and the sound retrieval order of a plurality of regions template.About standard form and region template, as shown in Figure 2, standard form is the template of standard speech of various countries (such as Japan, the U.S.), and the region template refers to the template of the dialect of the Chinese zones of different such as Sichuan, Guangdong and other countries different regions (such as Japanese Kansai Broadband Trial Network).And the sound retrieval order refers to the order language for speech retrieval, if this order language is sent with the form of voice by the user, can retrieve the result corresponding with it after being identified.Such as: be used for searching facility sound retrieval order " restaurant " etc., be used for playing media sound retrieval order " music " etc., be used for interconnection network, the sound retrieval order " AA company's site " that browses web sites etc.Specifically for example, for " restaurant " this sound retrieval order, store " restaurant (restaurant of mandarin) " of standard form, also have Sichuan template " restaurant (restaurants of Sichuan words) " etc.In addition, each template shown in Fig. 2 only is an example, also can only comprise one or more in above-mentioned each region template in the demanded storage section 12 of indexing unit 10.
In addition, each template that demanded storage section 12 stores also can customize according to user's custom or set, when for example the other countries beyond China used above-mentioned indexing unit, then Chinese standard form and other regional dialect templates of China were not essential.
Search terms storage part 13 is used for the storage multiple search terms data corresponding with each sound retrieval order difference.As shown in Figure 3, the situation that comprises residence data, facility name data, melody name data, artist name data, telephone number data, network related data etc. in the search terms data, but the present invention not only is defined in this, comprises getting final product more than 2 in the above-mentioned search terms data in search terms storage part 13.For example, with the corresponding search terms data of sound retrieval order " restaurant " be exactly " dining room, Guangdong, the peninsula " that belong to the restaurant, " outside the river river Xing Hai shop ", " restaurant, Dalian " etc. under the above-mentioned facility name data, the search terms data corresponding with sound retrieval order " music " just are " Chinese songs 1 ", " Jealousy 2 " in the above-mentioned melody name data etc.The Alpine website " the related data such as " Alpine English website ", " Alpine Japanese web ", " Alpine Chinese website " of network related data in such sound retrieval order and the multiple search terms data is corresponding.
Contain respectively regional information in each search terms data, for example, the regional information of facility name data is the information of the address of this facility of expression, the regional information of melody name is the affiliated regional information of the languages of this melody of expression and/or the information that represents this melody author, deduction person's region, the regional information of telephone number is the information of this corresponding region of telephone number of expression, etc.In addition, for special facility name, regional information can also comprise the regional information of answering with the distinctive Attribute Relative of this facility, for example, can also comprise the information of the territorial scope of the style of cooking that represents this restaurant in the regional information in restaurant.
In addition, voice signal for input, command determination section 14 can also carry out the analysis etc. of semantic analysis, rhythm component analysis and/or sound mother's the frequency of occurrences, identification comprises the kind of the voice signal of dialect more effectively, and the template that the voice signal similar degree of further selecting and inputting is high is carried out voice recognition and processed.
The search terms data that the sound retrieval order that data extraction unit 15 is judged from multiple search terms extracting data and command determination section 14 is corresponding, and be presented on the display part 16.And data extraction unit 15 is the preferential search terms data that comprise the regional information identical with the represented region of command determination section 14 selected templates that show on this display part 16.Wherein, this display part 16 can be the included display part of indexing unit 10, also can be other display part of being made of liquid crystal display etc. of being connected with indexing unit 10.
Below, with reference to Fig. 4, the motion flow of indexing unit 10 is elaborated.
At first, in step S1, the user is by input part 11 input audio signals.This voice signal can be the facility name for searching facility or destination, also can be song name, the channel name for music playing or broadcast listening, also can be web site name for interconnection network etc.
In step S2, command determination section 14 analyzes from the frequency of the voice signal of input part 11 inputs, and judges in the standard form stored in demanded storage section 12 and a plurality of regions template whether have the template corresponding with the voice signal of input.
In step S2, be judged as (step S2: "No"), be back to step S1, wait for that the user re-enters voice signal in the situation that does not have the template corresponding with the voice signal of input.
Be judged as (step S2: "Yes") in the situation that has the template corresponding with the voice signal of input, command determination section 14 utilizes the template of selecting that the voice signal of inputting is carried out voice recognition and processes, thereby identifies the sound retrieval order (step S3) corresponding with this voice signal.
Then, in step S4, data extraction unit 15 is utilized the sound retrieval order of being judged by command determination section, according to the regional information that comprises in the tut retrieval command of judging among the step S3, extracts the search terms data that comprise above-mentioned regional information from search terms storage part 13.
Then, in step S5, data extraction unit 15 is preferential on display part 16 to show that processing finishes by the search terms data of the identical regional information in the represented region of the template that comprises with select of step S4 extraction.
Embodiment 1
Below,, as example and with reference to Fig. 5 each action of carrying out among Fig. 4 is described take the situation of user's searching facility.
At first, in step S1, for example the user is by input part 11 usefulness Guangdong dialect input voice commands " restaurant ".
In step S2, command determination section 14 analyzes from the frequency of the voice signal " restaurant " of input part 11 inputs, and according to analysis result, the Guangdong dialect template of judging storage in demanded storage section 12 is the template corresponding with the voice signal of input.
Be judged as (step S2: "Yes") in the situation that has the Guangdong dialect template corresponding with the voice signal of input, command determination section 14 utilizes Guangdong dialect template that the voice signal " restaurant " of inputting is carried out voice recognition and processes, thereby identifies the sound retrieval order " restaurant " (step S3) corresponding with this voice signal.
Then, in step S4, data extraction unit 15 is utilized the sound retrieval order " restaurant " of being judged by command determination section, extract the search terms data corresponding with tut retrieval command " restaurant " from search terms storage part 13, the search terms data of extraction are such as comprising the facilities such as " outside the river river Xing Hai shop ", " restaurant, Dalian ", " restaurant, nine divisions of China in remote antiquity ", " Shanghai-Hangzhou restaurant ", " seafood restaurant ", " Guangdong dishes dining room, the peninsula ".
Then, in step S5, data extraction unit 15 is the preferential search terms data " Guangdong dishes dining room, the peninsula " that comprise the regional information identical with the represented region " Guangdong " of Guangdong dialect template that show on display part 16.As shown in Figure 5, owing to the region that regional information and the Guangdong dialect template of search terms data " Guangdong dishes dining room, the peninsula " are represented is identical, therefore be displayed on the position of the first row.
Embodiment 2
Below,, as example and with reference to Fig. 6 each action of carrying out among Fig. 4 is described take the situation of user's music playing.
At first, in step S1, the user has inputted voice signal " music " by input part 11 usefulness Japanese standard speech.
In step S2, command determination section 14 analyzes from the frequency of the voice signal " music " of input part 11 inputs, and according to analysis result, the Japanese standard speech template of judging storage in demanded storage section 12 is the template corresponding with the voice signal of input.
Be judged as (step S2: "Yes") in the situation that has the Japanese standard speech template corresponding with the voice signal of input, command determination section 14 utilizes Japanese standard speech template that the voice signal " music " of inputting is carried out voice recognition and processes, thereby identifies the sound retrieval order " music " (step S3) corresponding with this voice signal.
Then, in step S4, data extraction unit 15 is utilized the sound retrieval order " music " of being judged by command determination section, extract the search terms data corresponding with tut retrieval command " music " from search terms storage part 13, the search terms data of extraction are such as comprising " Chinese songs 1 ", " Chinese songs 2 ", " Chinese songs 3 ", " English song 1 ", " English song 2 ", " English song 3 ", " Jealousy 1 " etc.
Then, in step S5, data extraction unit 15 is the preferential search terms data " Jealousy 1 " that comprise the regional information identical with the represented region " Japan " of Japanese standard speech template that show on display part 16.As shown in Figure 6, owing to the region that regional information and the Japanese standard speech template of search terms data " Jealousy 1 " are represented is identical, therefore be displayed on the position of the first row.
Embodiment 3
Below,, as example and with reference to Fig. 7 each action of carrying out among Fig. 4 is described take the situation of user's interconnection network.
At first, in step S1, the user has inputted voice signal " Alpine website " by input part 11 usefulness Japanese standard speech.
In step S2, command determination section 14 analyzes from the frequency of the voice signal " Alpine website " of input part 11 inputs, and according to analysis result, the Japanese standard speech template of judging storage in demanded storage section 12 is the template corresponding with the voice signal of input.
Be judged as (step S2: "Yes") in the situation that has the Japanese standard speech template corresponding with the voice signal of input, command determination section 14 utilizes Japanese standard speech template that the voice signal " Alpine website " of inputting is carried out voice recognition and processes, thereby identifies the sound retrieval order corresponding with this voice signal " Alpine website " (step S3).
Then, in step S4, data extraction unit 15 is utilized the sound retrieval order " Alpine website " of being judged by command determination section, extract the search terms data corresponding with tut retrieval command " Alpine website " from search terms storage part 13, the search terms data of extraction are such as comprising the websites such as " Alpine China website ", " Alpine Japan website ", " Alpine U.S. website ".
Then, in step S5, data extraction unit 15 is the preferential search terms data " Alpine Japan website " that comprise the regional information identical with the represented region " Japan " of Japanese standard speech template that show on display part 16.The represented region of the regional information of " Alpine Japan website " and Japanese standard speech template is identical because the search terms data, therefore the webpage that shows " Alpine Japan website " at display part 16, perhaps as shown in Figure 7, in the list of websites that retrieves, " Alpine Japan website " is presented at the position of the first row.
Indexing unit according to the first embodiment, retrieve at the voice signal according to the user in the situation of a plurality of result for retrieval, can be according to the preferential demonstration of the shown regional information of user's the voice signal result for retrieval corresponding with this regional information, compare with existing indexing unit, improved operability and the convenience of indexing unit.
The second embodiment
The formation block diagram of the indexing unit 10 of the formation block diagram of the indexing unit 10 of the second embodiment of the present invention and the first embodiment shown in Figure 1 is basic identical, but in the demanded storage section 12 of the indexing unit 10 of the second embodiment, not only stored a plurality of sound retrieval orders that consisted of by standard form and a plurality of regions template, also stored represent a certain template be the acquiescence template default logo.The initial value of this default logo can be specified by manufacturing firm when dispatching from the factory, and is perhaps in use set by the user.It is the situation of standard speech template that Fig. 8 shows acquiescence template current in this demanded storage section 12.
Below, with reference to Fig. 9, the motion flow of indexing unit 10 is elaborated.
At first, in step S11, the user is by input part 11 input audio signals.This voice signal can be the facility name for searching facility or destination, also can be song name, the channel name for music playing or broadcast listening, also can be web site name for interconnection network etc.
In step S12, command determination section 14 analyzes from the frequency of the voice signal of input part 11 inputs, and judges in the standard form stored in demanded storage section 12 and a plurality of regions template whether have the template corresponding with the voice signal of input.
Be judged as (step S12: "Yes") in the situation that has the template corresponding with the voice signal of input, command determination section 14 utilizes the template corresponding with the voice signal of input that the voice signal of inputting is carried out voice recognition and processes, thereby identifies the sound retrieval order (step S13) corresponding with this voice signal.
Then, in step S14, data extraction unit 15 is utilized the sound retrieval order of being judged by command determination section, extracts the search terms data corresponding with the tut retrieval command of judging from search terms storage part 13.
Then, in step 15, data extraction unit 15 is the preferential search terms data that comprise the regional information identical with the represented region of the template of selecting that show on display part 16, and processing finishes.
On the other hand, in step S12, be judged as (step S12: "No") in the situation that does not have the template corresponding with the voice signal of input, command determination section 14 utilizes the acquiescence template that has been set up default logo that the voice signal of inputting is carried out voice recognition and processes, thereby identifies the sound retrieval order (step S16) corresponding with this voice signal.
Then, in step S17, data extraction unit 15 is utilized the sound retrieval order of being judged by command determination section 14, extracts the search terms data corresponding with the tut retrieval command of judging from search terms storage part 13.
Then, in step 18, data extraction unit 15 can preferentially show the search terms data that comprise the identical regional information in the region represented with giving tacit consent to template on display part 16, also can directly show by the data extraction unit 15 search terms data corresponding with the tut retrieval command that extract at display part, then processing finishes.
According to the indexing unit of the second embodiment, in demanded storage section 12 for a certain template stores by default logo manufacturing firm's appointment or that set by the user.Therefore, even in demanded storage section 12, do not exist in the situation of the template corresponding with this voice signal, also can utilize the acquiescence template to identify, compare with the situation that random selection template is identified or do not identified, can increase the probability of correct identification, thereby improve the convenience of indexing unit.
In addition, in demanded storage section 12, do not exist in the situation of the template corresponding with this voice signal, can directly show by the data extraction unit 15 search terms data corresponding with the tut retrieval command that utilizes the acquiescence template to identify that extract at display part 16.Thus, omit the processing that the search terms data are resequenced, in the more situation of the search terms data that retrieve, can alleviate the load of processing, significantly shortened the time of processing simultaneously.
The 3rd embodiment
The 3rd embodiment of the present invention is a kind of on-vehicle navigation apparatus, as shown in figure 10, on-vehicle navigation apparatus 100 possesses input part 11 ', demanded storage section 12 ', search terms storage part 13 ', command determination section 14 ', data extraction unit 15 ', display part 16 ', control part 17, antenna 18, gps receiver 19, operating portion 20 and map storage part 21.Because formation and input part 11, demanded storage section 12, search terms storage part 13, command determination section 14 and the data extraction unit 15 in function and the first and second embodiments of the parts such as input part 11 ', demanded storage section 12 ', search terms storage part 13 ', command determination section 14 ', data extraction unit 15 ' are basic identical, in the explanation of this omission about this each several part.But command determination section 14 ', data extraction unit 15 ' are the inside that is formed in a control part 17 in the present embodiment.For this control part 17, will be described in detail in the back.
Operating portion 20 is made of the button with difference in functionality, knob, switch etc., is used for accepting the user to the various operations of on-vehicle navigation apparatus 100, and will sends to control part 17 with the instruction of user's operational correspondence.
Store the map datum that comprises various facilities, place, road information etc. in the map storage part 21.
Display part 16 ' is used for showing the various information that provide to the user, comprises map, operation interface, video etc.Display part 16 ' generally is made of liquid crystal display.In addition, have at the display part 16 ' of on-vehicle navigation apparatus 100 in the situation of function of touch panel, display part 16 ' is also held concurrently as the part of operating portion 20.
According to said structure, on-vehicle navigation apparatus 100 not only can be carried out the retrieval process in the first and second embodiments, and can continue to carry out the navigation processing capacity based on the result who retrieves.
For example, in the situation that the user inputs voice command " restaurant ", the retrieval process shown in on-vehicle navigation apparatus 100 execution graphs 4 (the first embodiment) or Fig. 9 (the second embodiment) by input part 11 ' with the Guangdong dialect.Suppose by above-mentioned retrieval process, as shown in Figure 5, on display part 16 ', preferentially shown the search terms data " Guangdong dishes dining room, the peninsula " that comprise the regional information identical with the represented region " Guangdong " of Guangdong dialect template as result for retrieval.
Then, if the user has selected this " Guangdong dishes dining room, the peninsula " by the operating portion display part of touch screen function (or have), then the control part 17 of on-vehicle navigation apparatus 100 should " Guangdong dishes dining room, the peninsula " be made as the destination, the current location of the map datum in the map-based storage part 21 and the vehicle obtained by gps receiver 19, the optimal path in this " Guangdong dishes dining room, the peninsula " is gone in calculating, then carries out the path and shows and Route guiding.
In addition, possess at on-vehicle navigation apparatus 100 in the situation of function of broadcast listening, audio plays and video, clearly on-vehicle navigation apparatus 100 can also continue to carry out the functions such as broadcasting is listened to, video playback based on the result who retrieves, and omits its detailed explanation at this.
Other embodiments
The particular content of putting down in writing in the above-mentioned embodiment is not be used to limiting scope of the present invention, in the situation that do not break away from technical conceive of the present invention, the present invention can make various changes.
In above-mentioned the first and second embodiments, the result that data extraction unit 15 will retrieve has been presented on the display part, but the result of retrieval also can not be presented on the display part, also can be used as intermediate data storage among indexing unit 10 or be stored in external equipment that indexing unit links to each other in, the result who retrieves can also be sent to other equipment and carry out other follow-up processing.
In the respective embodiments described above, disclosing command determination section 14 analyzes from the frequency of the voice signal of input part 11 inputs, select the situation of the template corresponding with this voice signal in standard form from order storage part 12 and a plurality of regions template, but the present invention not only is defined in this.Can not select the template corresponding with the voice signal of inputting by command determination section 14 yet, but specify some templates by the user, perhaps utilize user's the essential informations such as birthplace automatically to determine some templates, and then utilize this template to carry out voice recognition.Such formation can alleviate the burden of command determination section 14, accelerates retrieval rate.
In addition, in the respective embodiments described above, the function of command determination section 14 and data extraction unit 15 can be carried out corresponding program by processor and finish, and also can realize by the one or more specific integrated circuit with corresponding function.In the situation that command determination section and data extraction unit realize by specific integrated circuit, then the command determination section 14 ' in the 3rd embodiment and data extraction unit 15 ' are not comprised in the control part 17, but carry out corresponding function under the control of control part 17.
In addition, in the step S12 of the second embodiment, directly move to step S14 being judged as in the situation about not existing with the template corresponding to voice signal of input, but the present invention also not only is defined in this, also can be judged as in the situation that does not have the template corresponding with the voice signal of input, as the first embodiment, return the input that step S11 accepts voice signal again, be judged as in the situation that does not have the template corresponding with the voice signal of input at continuously certain number of times, move to again step S14.By like this, in the situation that the user allows again input audio signal of user, thereby avoided using unusual voice signal to carry out the situation that voice recognition is processed because of the emergency situations signal of can normally not sounding.
Claims (7)
1. indexing unit is characterized in that possessing:
Input part is used for input audio signal,
Demanded storage section is used for a plurality of sound retrieval orders that storage is made of predefined word;
The search terms storage part is used for the storage multiple search terms data corresponding with each tut retrieval command difference;
Command determination section carries out voice recognition to the voice signal from above-mentioned input part input, judges the tut retrieval command of inputting; And
The data extraction unit, the corresponding search terms data of sound retrieval order of judging from above-mentioned multiple search terms extracting data and mentioned order judging part, and be presented on the display part,
In above-mentioned indexing unit,
Above-mentioned a plurality of sound retrieval order is divided into standard form and region template, and above-mentioned search terms data comprise respectively regional information,
The mentioned order judging part is analyzed at least from the frequency of the voice signal of above-mentioned input part input, selects the template corresponding with this voice signal from above-mentioned standard form and region template, and carries out voice recognition and process,
Above-mentioned data extraction unit is the preferential search terms data that comprise the identical regional information in the represented region of the template selected with the mentioned order judging part that show on above-mentioned display part.
2. indexing unit according to claim 1 is characterized in that,
Comprise in the above-mentioned search terms data in residence data, facility name data, melody name data, artist name data, the telephone number data more than 2.
3. indexing unit according to claim 1 is characterized in that,
Above-mentioned region template comprises at least a in the template of dialect of different regions of template, other countries of standard speech of template, other countries of the dialect of deifferent regions.China.
4. indexing unit according to claim 1 is characterized in that,
Also storing the some templates of expression in the mentioned order storage part is the default logo of acquiescence template.
5. indexing unit according to claim 1 is characterized in that,
The mentioned order judging part is not being selected in the situation of the template corresponding with this voice signal from above-mentioned standard form and region template, utilizes the acquiescence template to carry out voice recognition and processes.
6. search method, this search method is used in indexing unit, this indexing unit possesses demanded storage section and search terms storage part, this demanded storage section is used for a plurality of sound retrieval orders that storage is made of predefined word, this search terms storage part is used for the storage multiple search terms data corresponding with each tut retrieval command difference, this search method is characterised in that
Comprise:
Input step, input audio signal,
The command determination step is carried out voice recognition to the voice signal of inputting, and according to a plurality of sound retrieval orders in the mentioned order storage part, judges the sound retrieval order corresponding with above-mentioned input signal; And
The data extraction step in the multiple search terms data from above-mentioned search terms storage part, extracts the search terms data corresponding with the tut retrieval command, and is presented on the display part,
Above-mentioned a plurality of sound retrieval order is divided into standard form and region template, and above-mentioned search terms data comprise respectively regional information,
In the mentioned order determining step, analyze at least the frequency by the voice signal of above-mentioned input step input, from above-mentioned standard form and region template, select the template corresponding with this voice signal, and carry out voice recognition and process,
In above-mentioned data extraction step, the preferential search terms data that comprise the regional information identical with the represented region of the template of selecting that show on above-mentioned display part.
7. an on-vehicle navigation apparatus is characterized in that, comprises the indexing unit described in the claim 1～5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101881686A CN102867005A (en) | 2011-07-06 | 2011-07-06 | Retrieving device, retrieving method and vehicle-mounted navigation apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2011101881686A CN102867005A (en) | 2011-07-06 | 2011-07-06 | Retrieving device, retrieving method and vehicle-mounted navigation apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102867005A true CN102867005A (en) | 2013-01-09 |
Family
ID=47445880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011101881686A Pending CN102867005A (en) | 2011-07-06 | 2011-07-06 | Retrieving device, retrieving method and vehicle-mounted navigation apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102867005A (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103943109A (en) * | 2014-04-28 | 2014-07-23 | 深圳如果技术有限公司 | Method and device for converting voice to characters |
| CN105874405A (en) * | 2013-12-11 | 2016-08-17 | Lg电子株式会社 | Smart home appliances, operating method of thereof, and voice recognition system using the smart home appliances |
| CN105989841A (en) * | 2015-02-17 | 2016-10-05 | 上海汽车集团股份有限公司 | Vehicle-mounted speech control method and device |
| CN106985669A (en) * | 2015-12-27 | 2017-07-28 | 昶洧新能源汽车发展有限公司 | Information of vehicles panel interface |
| CN108664602A (en) * | 2018-05-09 | 2018-10-16 | 北京五八信息技术有限公司 | Search processing method, device, electronic equipment and the storage medium of application program |
| CN110162605A (en) * | 2018-02-15 | 2019-08-23 | 阿尔派株式会社 | Search result provides device and search result providing method |
| CN110310631A (en) * | 2019-06-28 | 2019-10-08 | 北京百度网讯科技有限公司 | Audio recognition method, device, server and storage medium |
| CN110781657A (en) * | 2019-10-14 | 2020-02-11 | 百度在线网络技术（北京）有限公司 | Management method, device and equipment for navigation broadcasting |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924526A (en) * | 2006-09-27 | 2007-03-07 | 江苏新科数字技术有限公司 | Method and device for electronic map keywords search for satellite navigation |
| CN101242562A (en) * | 2007-07-25 | 2008-08-13 | 中国移动通信集团福建有限公司 | Music voice searching device |
| CN101415259A (en) * | 2007-10-18 | 2009-04-22 | 三星电子株式会社 | System and method for searching information of embedded equipment based on double-language voice enquiry |
| KR20090112829A (en) * | 2008-04-25 | 2009-10-29 | 엔에이치엔(주) | System and method for searching local information based on at least one of initial, medial and final sounds of hangul |
| JP2010277388A (en) * | 2009-05-29 | 2010-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Method, system and program for providing information |
| WO2011068170A1 (en) * | 2009-12-04 | 2011-06-09 | ソニー株式会社 | Search device, search method, and program |
-
2011
- 2011-07-06 CN CN2011101881686A patent/CN102867005A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1924526A (en) * | 2006-09-27 | 2007-03-07 | 江苏新科数字技术有限公司 | Method and device for electronic map keywords search for satellite navigation |
| CN101242562A (en) * | 2007-07-25 | 2008-08-13 | 中国移动通信集团福建有限公司 | Music voice searching device |
| CN101415259A (en) * | 2007-10-18 | 2009-04-22 | 三星电子株式会社 | System and method for searching information of embedded equipment based on double-language voice enquiry |
| KR20090112829A (en) * | 2008-04-25 | 2009-10-29 | 엔에이치엔(주) | System and method for searching local information based on at least one of initial, medial and final sounds of hangul |
| JP2010277388A (en) * | 2009-05-29 | 2010-12-09 | Nippon Telegr & Teleph Corp <Ntt> | Method, system and program for providing information |
| WO2011068170A1 (en) * | 2009-12-04 | 2011-06-09 | ソニー株式会社 | Search device, search method, and program |
Non-Patent Citations (2)
| Title |
|---|
| 汪健: ""车载导航系统语音控制功能实现研究"", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑 》 * |
| 陈卫民: ""语音技术引领车载导航新时代"", 《安徽科技》 * |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105874405A (en) * | 2013-12-11 | 2016-08-17 | Lg电子株式会社 | Smart home appliances, operating method of thereof, and voice recognition system using the smart home appliances |
| US10269344B2 (en) | 2013-12-11 | 2019-04-23 | Lg Electronics Inc. | Smart home appliances, operating method of thereof, and voice recognition system using the smart home appliances |
| CN103943109A (en) * | 2014-04-28 | 2014-07-23 | 深圳如果技术有限公司 | Method and device for converting voice to characters |
| CN105989841A (en) * | 2015-02-17 | 2016-10-05 | 上海汽车集团股份有限公司 | Vehicle-mounted speech control method and device |
| CN105989841B (en) * | 2015-02-17 | 2019-12-27 | 上海汽车集团股份有限公司 | Vehicle-mounted voice control method and device |
| CN106985669A (en) * | 2015-12-27 | 2017-07-28 | 昶洧新能源汽车发展有限公司 | Information of vehicles panel interface |
| CN110162605A (en) * | 2018-02-15 | 2019-08-23 | 阿尔派株式会社 | Search result provides device and search result providing method |
| CN108664602A (en) * | 2018-05-09 | 2018-10-16 | 北京五八信息技术有限公司 | Search processing method, device, electronic equipment and the storage medium of application program |
| CN110310631A (en) * | 2019-06-28 | 2019-10-08 | 北京百度网讯科技有限公司 | Audio recognition method, device, server and storage medium |
| CN110781657A (en) * | 2019-10-14 | 2020-02-11 | 百度在线网络技术（北京）有限公司 | Management method, device and equipment for navigation broadcasting |
| US11906320B2 (en) | 2019-10-14 | 2024-02-20 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method for managing navigation broadcast, and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102867005A (en) | Retrieving device, retrieving method and vehicle-mounted navigation apparatus | |
| KR101844516B1 (en) | Method and device for analyzing content | |
| JP5526396B2 (en) | Information search apparatus, information search system, and information search method | |
| US9188456B2 (en) | System and method of fixing mistakes by going back in an electronic device | |
| EP3125134B1 (en) | Speech retrieval device, speech retrieval method, and display device | |
| CN102549652B (en) | Information retrieving apparatus | |
| US7310602B2 (en) | Navigation apparatus | |
| US20140365215A1 (en) | Method for providing service based on multimodal input and electronic device thereof | |
| US9123327B2 (en) | Voice recognition apparatus for recognizing a command portion and a data portion of a voice input | |
| JP2010072507A (en) | Speech recognition search system and speech recognition search method | |
| JP4466379B2 (en) | In-vehicle speech recognition device | |
| US20050171685A1 (en) | Navigation apparatus, navigation system, and navigation method | |
| JP2014106927A (en) | Information processing system | |
| CN106910503A (en) | Method, device and intelligent terminal for intelligent terminal display user's manipulation instruction | |
| TW201506905A (en) | Apparatus and method for selecting a control object by voice recognition | |
| KR20160044859A (en) | Speech recognition apparatus, vehicle having the same and speech recongition method | |
| JP2009042968A (en) | Information selection system, information selection method, and program for information selection | |
| JP5986468B2 (en) | Display control apparatus, display system, and display control method | |
| JP2011065526A (en) | Operating system and operating method | |
| JP5341548B2 (en) | Voice recognition device | |
| JP2007271277A (en) | Navigation system, method and program | |
| JP2011232668A (en) | Navigation device with voice recognition function and detection result presentation method thereof | |
| JP4682199B2 (en) | Voice recognition apparatus, information processing apparatus, voice recognition method, voice recognition program, and recording medium | |
| JP3624698B2 (en) | Voice recognition device, navigation system and vending system using the device | |
| JP2017182251A (en) | Analyzer |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130109 |