CN101604233B - Method for using voice virtual keyboard for interactive control - Google Patents
Method for using voice virtual keyboard for interactive control Download PDFInfo
- Publication number
- CN101604233B CN101604233B CN2009101477144A CN200910147714A CN101604233B CN 101604233 B CN101604233 B CN 101604233B CN 2009101477144 A CN2009101477144 A CN 2009101477144A CN 200910147714 A CN200910147714 A CN 200910147714A CN 101604233 B CN101604233 B CN 101604233B
- Authority
- CN
- China
- Prior art keywords
- user
- virtual keyboard
- data
- voice
- search
- 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.)
- Expired - Fee Related
Links
Images
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a method for using voice virtual keyboard for interactive control, which realizes interactive control through a mode of provision of a plurality of related results for user's selection, therefore a computer system does not needed to perform one-off accurate analysis at high speed, so the requirement of hardware and software configurations of the computer system is reduced, the cost of the system is reduced, and the voice virtual keyboard is easy to popularize.
Description
The present invention is that application number is 200410039109.2, applies for that artificial Liu Xinbin, the applying date are on 02 06th, 2004 the dividing an application of patent of invention.
Technical field
The invention belongs to input of computer media information and control field, be specifically related to a kind of using method that is used for the voice virtual keyboard of mutual control.
Background technology
Along with the continuous development of computer technology, phonetic entry technology and treatment technology thereof have been widely applied to aspect of social life.But because phonetic entry has very many uncertainties and complicacy, present computer system also is difficult to satisfy the requirement to the accuracy of phonological detection, in particular for control in real time, the computing ability is not very powerful computer system, therefore phonetic entry is used for the field that speech conversion and preservation, transmission etc. do not need to resolve the voice implication more, voice are used for the human-computer interactive control field comparatively speaking, and the accuracy that its voice are resolved is present subject matter.The solution of prior art mainly is by repeatedly learning user's the feature of posting a letter for each syllable, the accuracy of coming the raising system that user's voice is resolved.But this method exists three problems to be difficult to solve: the firstth, need prior learning before using, be that the user needs repeatedly to read aloud repeatedly whole received pronunciation tables, supply with computer system and resolve and make up user's pronunciation data storehouse, even need gather the pronunciation character of user under conditions such as different environment, health status, could make up more complete database, this has increased the difficulty that the user uses undoubtedly greatly, make the simplest this control mode become very complicated, limited voice-operated universal use widely; The secondth, the software of requirement computer system will have very strong intelligent, even can both accurately be resolved in user's pronunciation, under the condition of identification, can also accurately differentiate the phrase or the statement of the many meanings of unisonance by the contact of front and back literary composition, thereby not only require computer system to have very powerful data processing and arithmetic capability, the support of very intelligentized software also will be arranged; The 3rd is owing to preceding 2 points, and the existing voice input can't use the numerous and complicated public situation of accent still at proprietary user.If again these requirements are joined together, unless functions of use is powerful, complex structure, the high dedicated system of cost, just might realize voice control, and for the control system of cheapness, almost can't realize at present.
Summary of the invention
At problems of the prior art, the invention provides a kind of using method that computer system is required low voice virtual keyboard, it is in the system of control core that described using method is applied in the computing machine, in described system, made up corresponding voice virtual keyboard with specific user, and include corresponding speech database with same user, and with control purpose or the relevant target database of object; This using method includes following steps:
A. start the interactive voice control function,
B. the user reads aloud and Be Controlled object or the relevant keyword of purpose;
C. described system analysis user's pronunciation, then with the pairing speech database of user in search, relatively, obtain keyword with this user corresponding data code of pronouncing;
D. be that target is searched for described target database with described data code;
E. judge whether the result that obtains being consistent: if search has obtained relevant data, continue execution in step F, if search does not obtain related data, then redirect execution in step I;
F. utilize the key element database that is comprised in the voice virtual keyboard to be sign, export Search Results according to certain rule or order, and with the key element that voice mode prompting user utilizes voice virtual keyboard to comprise, use phonetic order to confirm or select described output result;
G. the constantly various sound inputs of accurate Analysis outside are that the pronunciation director data of the user in the key element database is compared with analysis result and user instruction dictionary, judge whether the user confirms or select; If the judgement user confirms or selects, then continues execution in step H; If the user does not confirm to select then redirect execution in step I;
H. judge that the user confirms or whether the result that selects is the final goal data: if the user confirms or the result that selects is not the final goal data, then further ferret out database, obtain more Search Results near the final goal data, repeating step E, F output then, the confession user reaffirms or selects; If the user confirms or the result of selection is the final objective data, other parts that just target data outputed to system are carried out next step operation, and finish the operation of this mutual control;
I. according to the setting of control service program, perhaps point out the user to operate again, perhaps reset operation entry and carry out other operation, perhaps stop the operation of this mutual control.
Further, the key element described in the step G is an English alphabet.
Further, described English alphabet is the single syllable English alphabet.
Further, the key element described in the step G is numerical key and function key.
Further, described numerical key is " 0-9 ", and described function key is "Yes" and "No".
Further, when the Search Results quantity described in the step F is one, confirms or deny exporting the result by described function key.
Further, in step F, also include following steps: add the word of the aid illustration relevant and described word and described Search Results are combined together output with described Search Results.
Further, in step C, the Accurate Analysis user's of elder generation pronunciation during described system analysis user's pronunciation; In the step e, if search does not obtain related data, the fuzzy again pronunciation of resolving the user of then described system, then with the pairing speech database of user in search, relatively, obtain keyword with this user corresponding data code of pronouncing; With described data code is that target is searched for described target database; Judge whether the result that obtains being consistent:, then continue execution in step F if search has obtained relevant data; If search does not obtain related data, then redirect execution in step I.
This using method that is used for the interactive voice dummy keyboard of the present invention realizes mutual control by the mode of " providing one group of correlated results selects for the user ", therefore no longer require the computer system high-speed cruising to carry out the accurate parsing of one-time-reach-place, this has reduced cost, the penetration and promotion easily that the requirement of computer system software and hardware configuration has been reduced system on the one hand; Also only need the user to read aloud twice Received Pronunciation table on the other hand, just can realize the fuzzy identification of user speech implication basically; Simultaneously since the quantity of the instruction that comprises in the virtual speech keyboard seldom and pronunciation simple, even system requirements is repeatedly gathered the instruction pronunciation of user under different situations, also be easy to finish, therefore the preliminary work amount such as read aloud before the user uses significantly reduces, and has alleviated the time and intensity of user's preliminary work to greatest extent.
Description of drawings
Fig. 1 is the general work process flow diagram that is used for controlling alternately the using method of voice virtual keyboard.
Embodiment
The invention will be further described below in conjunction with specification drawings and specific embodiments.
Fig. 1 is a kind of general work process flow diagram that is used for controlling alternately the using method of voice virtual keyboard of the present invention, this using method is exactly to provide the means selecting or confirm the output result for the user, and the output result here, be from database, to retrieve the result who obtains, using method is described below set by step according to the keyword of user's input.After human-computer interaction function started, system entered " monitoring " step 101, waited for that the user imports keyword.After system receives the user's voice order, the step 102 of accurate Analysis user's voice order at first, the result that will resolve compares with the user speech of preservation in " the user voice data storehouse " 103 then, obtain with the user speech keyword in the pronunciation corresponding command code, re-use this command code at last as target, ferret out database 104 retrieves and the corresponding word of user's pronunciation.Then, enter determining step 105, judge whether to obtain result for retrieval:, just jump to step 108 if obtained corresponding target data, and, select a plurality of results' outputs or confirm single result's output for the user by exporting behind the upward suitable aid illustration voice of step 109 interpolation.If the single target data of output are just pointed out the user to use function key in " voice virtual keyboard " to confirm or are denied exporting the result; If a plurality of target datas, the key element that then uses numerical key in " voice virtual keyboard " etc. can embody a definite sequence adds; Export front as a result at each, select for the user.The effect of this aid illustration word early is to allow the user be more readily understood the content of output.For example in auto-navigation system, can add and go up words such as " would you please to confirm place that you think whether ", " would you please from following target, select you to think destination ".If do not retrieve objective result, then enter step 106, fuzzy once more keyword of resolving user's input, adopt the method identical then with step 102, searching database 103 once more, obtain fuzzy search target database 104 behind the corresponding command code, obtain the corresponding target data of keyword with user's input.But this step requires system will possess certain intelligence, not only can retrieve and the corresponding word of user's pronunciation, also should be when can not find complete corresponding target data, can constitute meaning, export synthetic with the more corresponding scattered syllable intelligence of user's pronunciation with the immediate a plurality of target datas of the keyword of user's input.Enter step 107 subsequently, judge, whether corresponding target data output is arranged through after the top processing.If target data output is arranged then as before, after output step 108 is added upward suitable aid illustration, key element in the use " virtual speech keyboard " is exported each target data by the mode of voice and is selected for the user according to each target data of certain sequential calibration.If after handling like this, still do not obtain alternative target data, illustrate that then the voice keyword that the user imports has problem, then redirect execution in step 117, setting according to system, perhaps point out the user to operate again, perhaps reset operation entry, perhaps stop this service, perhaps carry out other operations.
After step 108 export target data, system enters determining step 110, judges whether to detect the sound instruction that obtains the user.If do not detect the sound input within a certain period of time, both can return step 108, continue prompting user selection or affirmation, also can other suitable operations be set by step 117; If detected the sound input, then pass through the sound of sound analyzing step 111 accurate Analysis input, then analysis result is compared with " user instruction dictionary " database 112 that constitutes voice virtual keyboard, the sound of judging input by determining step 113 whether with this dictionary in certain key element be complementary: if do not match, both can not respond the information of input within a certain period of time, wait for that the user re-enters sound instruction, to prevent that other external disturbance from producing maloperation (not drawing among this part figure), also can copy top mode to jump to step 108 or 117, operate accordingly.These two determining steps 110 and 113 negative output port operation pointed, the operation that provides among the figure or do not provide all is one of various possible selections, the operation of its setting should be that principle is set to be user-friendly to native system, should not be limited to above-mentioned various possibilities.If obtained the data of coupling, then execution in step 114, judge further whether target data user-selected or that confirm is the final goal data that finally can be performed.Certainly, this step is not the step that obviously will set, because can note down target data is classified in target database, can whether be the target data that finally can be performed by system identification clearly just, put forward with a clear and definite step at this, purpose is the workflow of wishing the system that can be illustrated more clearly in.For example in auto-navigation system, the user has said " three (four) loops " this place name, because some is close in the pronunciation of " three " and " four ", so system is through after the fuzzy search, the prompting user selects " 1. three loops " and " the 2. Fourth Ring road " to wait for that the user determines, the user has selected " Fourth Ring road " by the instruction speech " 2 " of dummy keyboard, but the Fourth Ring road is difficult to as a definite place name, because the region that comprises is too wide, so should store according to the classification of " intermediate data " in target database, system just is easy in advance judge that the data of being exported all are " intermediate objective data " but not can use electronic chart like this, " the final goal data " that modes such as GPS positioning system are carried out.If the result who judges is " final goal data ", system then by step 116, exports this data to other topworkies, finishes preset task for system; If judge it is not " final goal data ", then by step 115, the method for copying the front is the ferret out database once more, and the result that search is obtained export once more by step 210 then, selects or affirmation for the user.If the result of retrieval still is the intermediate objective data for the second time, then repeat said process by step 215 once more, up to obtaining the final objective data.As top for example shown in, the possibility of result of search is for the second time: " 1. northeast three; 2. West 3rd Ring Road ... 4. North 3rd Ring Road ", after the user determines to be " 4 ", may also to export " 1. East Road, North 3rd Ring Road once more; 2. North Third Ring Middle Road; 3. West Road, North 3rd Ring Road " select for the user.Certainly, here " the intermediate objective data " and the classification of " final goal data " neither be absolute, such as can in system and database, setting the target of subject matters such as certain landmark building on " North 3rd Ring Road " road or crossing as navigation, if starting point is distant apart from the North 3rd Ring Road, just can point out the user whether no longer further to retrieve, perhaps subsequently in the liftoff retrieval once more of the Lu Shangzai low coverage of advancing.If like this, in process flow diagram shown in Figure 1, just can insert the link that user interferes, interrupt search and confirm that the intermediate objective data are as executable target.
Be meant in the man-machine interaction process at " phonetic order " of the present invention, the user only use comprised in " voice virtual keyboard ", a limited number of certain words are selected or confirm the information that computing machine is exported, data volume is relatively very little, behind the system analysis by with " user instruction dictionary " in data of record come confirmation, and require accuracy very high relatively.
Method of the present invention is not limited to the embodiment described in the embodiment, and those skilled in the art's technical scheme according to the present invention draws other embodiment, belongs to technological innovation scope of the present invention equally.
Claims (8)
1. one kind is used for the using method of the voice virtual keyboard of control alternately, be applied in the computing machine is in the system of control core, in described system, made up corresponding voice virtual keyboard with specific user, and include corresponding speech database with same user, and with control purpose or the relevant target database of object, this using method includes following steps:
A. start the interactive voice control function,
B. the user reads aloud and Be Controlled object or the relevant keyword of purpose;
C. described system analysis user's pronunciation, then with the pairing speech database of user in search, relatively, obtain keyword with this user corresponding data code of pronouncing;
D. be that target is searched for described target database with described data code;
E. judge whether the result that obtains being consistent: if search has obtained relevant data, continue execution in step F, if search does not obtain related data, then redirect execution in step I;
F. utilize the key element database that is comprised in the voice virtual keyboard to be sign, export Search Results according to certain rule or order, and with the key element that voice mode prompting user utilizes voice virtual keyboard to comprise, use phonetic order to confirm or select described output result;
G. the constantly various sound inputs of accurate Analysis outside are that the pronunciation director data of the user in the key element database is compared with analysis result and user instruction dictionary, judge whether the user confirms or select; If the judgement user confirms or selects, then continues execution in step H; If the user does not confirm to select then redirect execution in step I;
H. judge that the user confirms or whether the result that selects is the final goal data: if the user confirms or the result that selects is not the final goal data, then further ferret out database, obtain more Search Results near the final goal data, repeating step E, F output then, the confession user reaffirms or selects; If the user confirms or the result of selection is the final objective data, other parts that just target data outputed to system are carried out next step operation, and finish the operation of this mutual control;
I. according to the setting of control service program, perhaps point out the user to operate again, perhaps reset operation entry and carry out other operation, perhaps stop the operation of this mutual control.
2. a kind of using method that is used for the voice virtual keyboard of mutual control according to claim 1, it is characterized in that: the key element described in the step G is an English alphabet.
3. a kind of using method that is used for the voice virtual keyboard of mutual control according to claim 2, it is characterized in that: described English alphabet is the single syllable English alphabet.
4. a kind of using method that is used for the voice virtual keyboard of mutual control according to claim 1, it is characterized in that: the key element described in the step G is numerical key and function key.
5. a kind of using method that is used for the voice virtual keyboard of mutual control according to claim 4 is characterized in that: described numerical key is " 0-9 ", and described function key is "Yes" and "No".
6. a kind of using method that is used for the voice virtual keyboard of mutual control according to claim 5 is characterized in that: when the Search Results quantity described in the step F is one, confirms or deny exporting the result by described function key.
7. according to the described a kind of using method that is used for the voice virtual keyboard of mutual control of one of claim 1 to 6, it is characterized in that, in step F, also include following steps: add the word of the aid illustration relevant and described word and described Search Results are combined together output with described Search Results.
8. a kind of using method that is used for the voice virtual keyboard of mutual control according to claim 1 is characterized in that, in step C, and the Accurate Analysis user's of elder generation pronunciation during described system analysis user's pronunciation; In the step e, if search does not obtain related data, the fuzzy again pronunciation of resolving the user of then described system, then with the pairing speech database of user in search, relatively, obtain keyword with this user corresponding data code of pronouncing; With described data code is that target is searched for described target database; Judge whether the result that obtains being consistent:, then continue execution in step F if search has obtained relevant data; If search does not obtain related data, then redirect execution in step I.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009101477144A CN101604233B (en) | 2004-02-06 | 2004-02-06 | Method for using voice virtual keyboard for interactive control |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009101477144A CN101604233B (en) | 2004-02-06 | 2004-02-06 | Method for using voice virtual keyboard for interactive control |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200410039109 Division CN1629934B (en) | 2004-02-06 | 2004-02-06 | Building method of user instruction library for virtual speech keyboard |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101604233A CN101604233A (en) | 2009-12-16 |
| CN101604233B true CN101604233B (en) | 2011-08-10 |
Family
ID=41469976
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009101477144A Expired - Fee Related CN101604233B (en) | 2004-02-06 | 2004-02-06 | Method for using voice virtual keyboard for interactive control |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101604233B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104424944B (en) * | 2013-08-19 | 2018-01-23 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| KR102197143B1 (en) * | 2013-11-26 | 2020-12-31 | 현대모비스 주식회사 | System for command operation using speech recognition and method thereof |
| CN105956047A (en) * | 2016-04-26 | 2016-09-21 | 北京橙鑫数据科技有限公司 | Search method and device |
| CN107390888A (en) * | 2017-08-15 | 2017-11-24 | 深圳诺欧博智能科技有限公司 | Finger-impu system and method |
| CN108845797A (en) * | 2018-06-28 | 2018-11-20 | 深圳市乾乾编程科技有限公司 | A kind of speech recognition type programmed method, device and computer equipment |
| CN114678012A (en) * | 2022-02-18 | 2022-06-28 | 青岛海尔科技有限公司 | Voice interaction data processing method and device, storage medium and electronic device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1221142A (en) * | 1998-08-15 | 1999-06-30 | 郑友总 | Double-frequency sound-shape coding method and its keyboard |
| CN1245316A (en) * | 1998-06-24 | 2000-02-23 | 微软公司 | Method for converting one keyboard mode text to another keyboard mode text |
| US6240168B1 (en) * | 1998-10-29 | 2001-05-29 | Picazo Communications | Method and apparatus for controlling a computer to implement telephone functions with a displayed telephone of variable size |
| CN2447894Y (en) * | 2000-11-02 | 2001-09-12 | 陈振文 | Sound control identificating device |
-
2004
- 2004-02-06 CN CN2009101477144A patent/CN101604233B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1245316A (en) * | 1998-06-24 | 2000-02-23 | 微软公司 | Method for converting one keyboard mode text to another keyboard mode text |
| CN1221142A (en) * | 1998-08-15 | 1999-06-30 | 郑友总 | Double-frequency sound-shape coding method and its keyboard |
| US6240168B1 (en) * | 1998-10-29 | 2001-05-29 | Picazo Communications | Method and apparatus for controlling a computer to implement telephone functions with a displayed telephone of variable size |
| CN2447894Y (en) * | 2000-11-02 | 2001-09-12 | 陈振文 | Sound control identificating device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101604233A (en) | 2009-12-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9489432B2 (en) | System and method for using speech for data searching during presentations | |
| US7630901B2 (en) | Multimodal input method | |
| KR20040102071A (en) | Integrated development tool for building a natural language understanding application | |
| JPH0433069B2 (en) | ||
| CN106251863B (en) | A kind of instruction type speech control system and control method based on smart machine | |
| WO2008144638A2 (en) | Systems and methods of a structured grammar for a speech recognition command system | |
| WO2020018525A1 (en) | Method, system, and computer program product for an intelligent industrial assistant | |
| CN104484057B (en) | The offer method and apparatus of result are provided | |
| CN101604233B (en) | Method for using voice virtual keyboard for interactive control | |
| CN108062214A (en) | The methods of exhibiting and device of a kind of search interface | |
| CN1629934A (en) | Building and using method of virtual speech keyboard for interactive control | |
| CN108062213A (en) | A kind of methods of exhibiting and device at quick search interface | |
| JP2009140287A (en) | Retrieval result display device | |
| CN108090112A (en) | The exchange method and device of a kind of search interface | |
| JP2004145732A (en) | Voice identification support chinese character input system and method | |
| US20200257734A1 (en) | Method, System, and Computer Program Product for Developing Dialogue Templates for an Intelligent Industrial Assistant | |
| JP2002156996A (en) | Voice recognition device, recognition result correcting method, and recording medium | |
| KR101553395B1 (en) | Method, system and recording medium for controlling keyboard and file distribution system | |
| CN107450742A (en) | A kind of information processing method, device and terminal | |
| JPH0668137A (en) | Operation command object information generating system and operation command object recognition system | |
| JPS61262924A (en) | Electronic file device | |
| JPH04290158A (en) | Document creation device | |
| JPH0528129A (en) | Word processor | |
| CN113779027A (en) | Dialect homophonic vocabulary automatic generation system | |
| JP5344649B2 (en) | Character string conversion apparatus, character string conversion method, program, and recording medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| DD01 | Delivery of document by public notice |
Addressee: Liu Xinbin Document name: Notification to Pay the Fees |
|
| DD01 | Delivery of document by public notice | ||
| DD01 | Delivery of document by public notice |
Addressee: Liu Xinbin Document name: Notification of Termination of Patent Right |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20110810 Termination date: 20160206 |