CN103218199A - Phonetic input method with identification code input function - Google Patents
Phonetic input method with identification code input function Download PDFInfo
- Publication number
- CN103218199A CN103218199A CN2013100592461A CN201310059246A CN103218199A CN 103218199 A CN103218199 A CN 103218199A CN 2013100592461 A CN2013100592461 A CN 2013100592461A CN 201310059246 A CN201310059246 A CN 201310059246A CN 103218199 A CN103218199 A CN 103218199A
- Authority
- CN
- China
- Prior art keywords
- input
- auxilliary
- identification code
- primary
- stroke
- 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
Landscapes
- Character Discrimination (AREA)
Abstract
The invention discloses a phonetic input method with an identification code input function, specific to the problem of low identification rate existing in the conventional phonetic input method. The input method is characterized in that input methods such as a phonetic input method and the like are taken as main input ways (main input for short), an auxiliary input way (auxiliary input for short) is realized by simplifying on the basis of another input method (such as wubi, stroke and the like), the main input and the auxiliary input are implemented simultaneously during inputting, and a certain time difference exists between the main input and the auxiliary input. After inputting, a system is used for identifying the voice of the main input; if necessary, the identification code of the auxiliary input is identified, and identification results of the main input are screened through the identification code; and if necessary, after the screening result is processed, a final processed result is displayed on a screen.
Description
Technical field
The present invention relates to input method field, be specifically related to a kind of mixing voice input method.
Background technology
Literal input is as the interactive mode of equipment such as we and computer, mobile phone, and the speed of input speed has influenced the height of efficient such as we handle official business.The character of keyboard and mobile telephone virtual keyboard is an english character, and this input for non-English has caused certain obstruction.Input method development so far, Chinese has developed input methods such as phonetic, spelling, five by the keyboard input, and associating input function is arranged, and by the phonitic entry method of audio frequency input and the hand-writing input method of recognizing by person's handwriting.But all there is deficiency in above several input method, phonetic and all-phonetic input method are because a sound multiword situation of Chinese, need a plurality of candidate Chinese characters to be selected behind the input Pinyin character, the phonetic input of phrase and whole sentence is owing to the difference of speech habits also needs candidate is selected again; Though five and region code input accuracy is high but need mass memory work, the skilled people who uses is also few, and five inputs for whole sentence are supportive not high; Handwriting input is slow, and each one hand-written custom is different, and is also not high for the recognition correct rate of handwritten word; Phonetic entry speed is fast, but still has the not high situation of recognition correct rate.Just popularizing along with smart mobile phone, how just can be implemented on the smart mobile phone of incorporeity keyboard support and import fast, the typewriting input speed of dummy keyboard is obviously fast not as good as the speed of physical keyboard, and handwriting input still exists the problem that speed is slow, discrimination is not high, and phonetic entry also locks into discrimination.And the mixing input method of present stage will not be optimized between the various input methods, but the various combinations of input character are enumerated, and the user must select prepare word, and input efficiency does not promote.
Summary of the invention
At above-mentioned defective, the invention provides a kind of phonitic entry method and other input methods of tape identification sign indicating number input based on same principle based on Chinese.In the accuracy rate of guaranteeing to promote greatly on the basis of input speed identification.And this input method is to promote on the basis of existing voice, input method such as hand-written, after the user only need remember simple input rule, do not need to learn in addition, both is familiar with and grasps this input method, promotes the speed of input.The process of phonetic entry identification generally as shown in Figure 1, can be summed up as sampling, pre-service, feature extraction, identification and aftertreatment link substantially, basic procedure all is after feature extraction, compares by algorithm at identification link and sound bank and obtains recognition result.This input method is in the identification link or add the process of recognition result being screened by identification code afterwards, exports preferred plan and alternatives again.
The present invention is achieved by the following technical solutions: the phonitic entry method of tape identification sign indicating number input be by with input methods such as phonitic entry methods as primary input mode (abbreviation primary input), to simplify the back based on another kind of input method (as five, stroke etc.) as auxiliary input mode (be called for short to assist and import), primary input and auxilliary input are carried out simultaneously when importing, and it is poor to allow certain hour between primary input and the auxilliary input.After input finishes, system discerns the voice of primary input, as need necessity the identification code of auxilliary input is discerned, and the recognition result of primary input is screened by identification code, after as need necessity The selection result being handled, final process result is shown to screen.
Description of drawings
Fig. 1 is the basic procedure synoptic diagram of speech recognition
Fig. 2 is the structural representation of an embodiment of the present invention
Fig. 3 is the structural representation of an embodiment of the present invention
Fig. 4 is the structural representation of an embodiment of the present invention
Fig. 5 is the structural representation of an embodiment of the present invention
Embodiment
The present invention can implement by following several embodiments:
Embodiment 1, with reference to Fig. 2, this embodiment is to be primary input with the Chinese speech input mode, analysis and processing method for the primary input input information is identical with the analysis and processing method that uses the phonetic entry mode to import separately in the link except that the aftertreatment link, and difference is to have added the step of recognition result being screened by auxilliary input identification code in the aftertreatment link; In Chinese stroke handwriting input mode is auxilliary input, because auxilliary input is only used as identification code, and do not take out separately as the foundation of judging input information, so when input, do not need each pen of a word is all carried out handwriting input, and only the first stroke of each word of input information handwriting input successively need be got final product (for improving accuracy rate, can require to import the preceding N pen of each word, wherein N is the natural number greater than 0.), the input content of auxilliary input is a little, horizontal stroke, perpendicular, cast aside, press down, cross break, perpendicular folding is cast aside folding, the cross break crotch, it is several that perpendicular folding colludes etc., the handwritten input information of auxilliary input discerned only need be identified each independent stroke (if what require is N pen before the input, then needing respectively to discern N stroke), identification than the handwritten Chinese character input is easy, the accuracy rate height.
When carrying out the primary input phonetic entry, auxilliary input is imported synchronously, beginning point input time of primary input and auxilliary input allows the mistiming, and end point input time of primary input and auxilliary input allows the mistiming, if but the efficient of time point oversize meeting influence interval time input.During input, can be to handle the interval with a word, perhaps be to handle at interval with the speech, serves as to handle at interval with single word perhaps, and processing is spaced apart the user and imports primary information shows this input information to system process.The handwritten stroke input of auxilliary input can be from left to right or from right to left or from top to bottom or from top to bottom also to allow the mode of line feed input to import in handwriting area, distance before and after system is judged between the input is distinguished each identification code, or allow in handwriting area any position to import and system to time interval of front and back input or do not frame out and wait sign or action to distinguish each identification code, also can given a plurality of hand-written frames allow the user import multiple mode such as each identification code successively and distinguish the identification code that front and back are imported.
After primary input and auxilliary input were all finished, system discerned the primary input voice messaging, the handwriting input of auxilliary input is discerned, and the recognition result of primary input is screened at the recognition result of aftertreatment link by auxilliary input.Result after will screening at last is shown to screen.
With input " examination swimsuit " is that example illustrates that this scheme is as follows: in the time of by primary input input " examination swimsuit " voice messaging, by auxilliary first stroke of writing these several words on touch-screen successively of importing, be followed successively by " point, point, point ".Voice to primary input carry out processes such as feature extraction and identification, and the stroke input of auxilliary input is discerned, and recognition result is " point, point, a point ".In the absence of auxilliary input, the possibility of result of identification and output is as follows: " optimal result is a dress on probation; candidate result is followed successively by formula swimsuit, examination swimsuit, is suitable for shape ... ", also need to want the user that above candidate result is selected, and by the link after the speech recognition is being screened voice identification result with the identification code that auxilliary input identifies, have only " examination swimsuit " option to meet the situation of " point, point, point ", then " examination swimsuit " provided as optimal result, all the other results that meet identification code provide as alternative result.When recognition result being screened, can take following two kinds of schemes as required: only allow to meet the recognition result of identification code as optimal result and candidate result with identification code; The recognition result that does not meet identification code cannot be as optimal result, but can be used as candidate result.
Because user's hand-written custom is different, such as " going into " word, has the people to write left-falling stroke earlier, also has the people to write right-falling stroke earlier, when this type of word was screened, when can be set to identification code for left-falling stroke or right-falling stroke, " going into " word was all eligible, and other analogues are example herewith.Owing to error can occur during for the input information identification of auxilliary input, press down when too short such as input, can be identified as a little or press down, all eligible during then the first sum of screening of being depicted as a little or pressing down, other analogues are herewith routine.
Embodiment 2, with reference to Fig. 3, this embodiment is similar with embodiment 1, unspecified part please refer to embodiment 1.With the Chinese speech input mode is primary input; Be chosen as auxilliary input with given Chinese stroke, auxilliary input comprises following mode but is not limited to following mode: the Chinese stroke is corresponded on the part key position on the keyboard, allow the user to import successively, as each numerical key or corresponding other keys such as corresponding 1,2,3,4,5,6 respectively such as point, horizontal, vertical, left-falling stroke, right-falling stroke, cross break by button; The Chinese stroke is corresponded on the part key position on the dummy keyboard, allow the user to select by touch screen; With the Chinese stroke as the virtual key layout on screen, allow the user to click or mouse clicks or mode such as mouse-over is selected by touch screen.For the convenience of the user, can be incorporated on a key position or the virtual key position (abbreviation key) by stroke a plurality of shapes are similar or that type is identical, for example cross break and cross break hook are incorporated on the key, or cross break and perpendicular folding be incorporated on the key, maybe will put and right-falling stroke is incorporated on the key, or with horizontal left-falling stroke with horizontal to be incorporated into a key first-class.N pen before also can requiring the user to import.
When carrying out the primary input phonetic entry, auxilliary input is selected input synchronously or is keyed in, and beginning point input time of primary input and auxilliary input allows the mistiming, and end point input time of primary input and auxilliary input allows the mistiming.
After primary input and auxilliary input were all finished, system discerned the primary input voice messaging.Recognition result to primary input screens with the auxilliary identification code of importing.Result after will screening at last is shown to screen.
It is as follows to illustrate this scheme: in the time of by primary input input " examination swimsuit " voice messaging, and by the key position (such as 1,1,1) at auxilliary input key entry " point, point, point " place, or the virtual key of " point " mapping on the taps screen etc.
Not auxilliary input, the possibility of result of identification and output is as follows: " optimal result is a dress on probation; candidate result is followed successively by formula swimsuit, examination swimsuit, is suitable for shape ... ", also need the user that above candidate result is selected, and by the identification code of the aftertreatment link after identification with auxilliary input recognition result is screened, have only " examination swimsuit " option to meet the situation of " point, point, point ", then " examination swimsuit " provided as optimal result, all the other results that meet identification code provide as alternative result.When recognition result being screened, can take following two kinds of schemes as required: only allow to meet the recognition result of identification code as optimal result and candidate result with identification code; The recognition result that does not meet identification code cannot be as optimal result, but can be used as candidate result.
Because user's hand-written custom is different, such as " going into " word, has the people to write left-falling stroke earlier, also has the people to write right-falling stroke earlier, when this type of word was screened, when can be set to identification code for left-falling stroke or right-falling stroke, " going into " word was all eligible.Other analogues are example herewith.
Embodiment 3, with reference to Fig. 3, this embodiment is similar with embodiment 1, unspecified part please refer to embodiment 1.With the Chinese speech input mode is primary input; With given Chinese font structure choice is auxilliary input, auxilliary input comprises following mode but is not limited to following mode: Chinese font structure is corresponded on the part key position on the keyboard, allow the user to select successively, as each numerical key or corresponding other keys such as difference such as single character, left and right sides structure, up-down structure, left, center, right structure, upper, middle and lower structure, external and internal compositions corresponding 1,2,3,4,5,6 by button; Chinese font structure is corresponded on the part key position on the dummy keyboard, allow the user to select by touch screen; With the font structure as the virtual key layout on screen, allow the user to click or mouse clicks or mode such as mouse-over is selected by touch screen.For the convenience of the user, a plurality of similar font structures can be incorporated on a key position or the virtual key position (abbreviation key), for example left and right sides structure and left, center, right structure be incorporated on the key, or it is first-class that single character and external and internal compositions are incorporated into a key.
When carrying out the primary input phonetic entry, auxilliary input is imported synchronously, and beginning point input time of primary input and auxilliary input allows the mistiming, and end point input time of primary input and auxilliary input allows the mistiming.After primary input and auxilliary input were all finished, system discerned the primary input voice messaging.Recognition result to primary input screens with the auxilliary identification code of importing.Result after will screening at last is shown to screen.
It is as follows to illustrate this scheme: in the time of by primary input input " examination swimsuit " voice messaging, by the key position (such as 2,2,3) at auxilliary input key entry " left and right sides structure, left and right sides structure, up-down structure " place, or the virtual key of each font structure mapping on the taps screen etc.
Not auxilliary input, the possibility of result of identification and output is as follows: " optimal result is a dress on probation; candidate result is followed successively by formula swimsuit, examination swimsuit, is suitable for shape ... ", also need the user that above candidate result is selected, and by the identification code of the aftertreatment link after identification with auxilliary input recognition result is screened, have only " examination swimsuit " option to meet the situation of " left and right sides structure, left and right sides structure, left and right sides structure ", then " examination swimsuit " provided as optimal result, all the other results that meet identification code provide as alternative result.When recognition result being screened, can take following two kinds of schemes as required: only allow to meet the recognition result of identification code as optimal result and candidate result with identification code; The recognition result that does not meet identification code cannot be as optimal result, but can be used as candidate result.
Embodiment 4, with reference to Fig. 3, this embodiment is similar with embodiment 1, unspecified part please refer to embodiment 1.With the Chinese speech input mode is primary input; With input methods such as given Chinese radical, radical or five is auxilliary input, uses input methods such as radical, radical or five in layout on the keyboard or the layout on dummy keyboard.
When carrying out the primary input phonetic entry, auxilliary input is imported synchronously, and beginning point input time of primary input and auxilliary input allows the mistiming, and end point input time of primary input and auxilliary input allows the mistiming.After primary input and auxilliary input were all finished, system discerned the primary input voice messaging.Recognition result to primary input screens with the auxilliary identification code of importing.Result after will screening at last is shown to screen.
It is as follows to illustrate this scheme: in the time of by primary input input " examination swimsuit " voice messaging, first key (can be the top n key, N be greater than zero integer) of keying in input methods such as the radical, radical of these three word correspondences or five by auxilliary input is as identification code.The primary input recognition result may be as follows: " dress on probation, formula swimsuit, examination swimsuit, suitable shape ... ", with the identification code of auxilliary input recognition result is screened, the result is exported.When recognition result being screened, can take following two kinds of schemes as required: only allow to meet the recognition result of identification code as optimal result and candidate result with identification code; The recognition result that does not meet identification code cannot be as optimal result, but can be used as candidate result.
Embodiment 5, this embodiment are to be primary input with the Chinese hand-writing input mode; With the Chinese speech input mode is auxilliary input.When carrying out the primary input handwriting input, auxilliary input voice synchronous is imported, beginning point input time of primary input and auxilliary input allows the mistiming, end point input time of primary input and auxilliary input allows the mistiming, if but the efficient of time point oversize meeting influence interval time input.During input, can be to handle the interval with a word, perhaps be to handle at interval with the speech, serves as to handle at interval with single word perhaps, and processing is spaced apart the user and imports primary information shows this input information to system process.After primary input and auxilliary input were all finished, system discerned the primary input hand-written information, the voice messaging of auxilliary input is discerned, and the recognition result that auxilliary input crossed in the pronunciation of the recognition result of primary input is compared screening.And The selection result provided.
Embodiment 6, with reference to Fig. 4, this embodiment is to be primary input with the Chinese speech input mode; In Chinese stroke handwriting input mode is auxilliary input, because auxilliary input is only used as identification code, and do not take out separately as the foundation of judging input information, so when input, do not need each pen of a word is all carried out handwriting input, and only the first stroke of each word of input information handwriting input successively need be got final product (for improving accuracy rate, can require to import the preceding N pen of each word, wherein N is the natural number greater than 0.), the input content of auxilliary input is a little, horizontal stroke, perpendicular, cast aside, press down, cross break, perpendicular folding is cast aside folding, the cross break crotch, it is several that perpendicular folding colludes etc., the handwritten input information of auxilliary input discerned only need be identified each independent stroke (if what require is N pen before the input, then needing respectively to discern N stroke), identification than the handwritten Chinese character input is easy, the accuracy rate height.
It is as follows to illustrate this scheme: in the time of by primary input input " the use mixing input method is applicable to touch panel device " voice messaging, on touch-screen, write first stroke of these several words successively by auxilliary input, be followed successively by and " cast aside; cast aside; point; cast aside; horizontal stroke; press down, the point, cast aside, cast aside, horizontal, cast aside, horizontal, cross break, the point, cast aside "; primary input and auxilliary input are finished the back system primary input voice messaging are discerned; process is following but be not limited to following order: a; the stroke to auxilliary input is analyzed, and judges to be followed successively by " left-falling stroke, cast aside, the point, cast aside, horizontal, press down, the point, cast aside, cast aside, horizontal, cast aside, horizontal, cross break, the point, cast aside "; B after the voice messaging of primary input analyzed, judges that input information is the pinyin combinations of " shi yong hun he shu ru fa shi yong yu chu mo ping she bei "; C, search alternative word, as the alternative word of " shi " for " city, be, the time, make, scholar, formula, thing, ten, begin, show, suitable " etc. a plurality of phonetically similar words, and can be by the scope that alternative word is further dwindled in the judgement of tone, in view of the reason of various places dialect can be included in alternative word scope such as " si " close pronunciation; D screens alternative word by the information of auxilliary input method input, and the first stroke is the reservation following " making " of left-falling stroke etc. when writing, and can will keep " beginning " according to the writing style difference of different people in this step; E, information for the input of primary input method is carried out c successively, the d step, screen alternative word, as example, remaining alternative word be followed successively by " make, begin ", " with, hire ", " mixed, muddy, palace gate ", " with, what, close, box, standing grain ", " fail, state, comb, express ", " going into ", " method ", " suitable, family name, decorations ", " with, hire ", " in, the fine jade ", " locate, touch, Chu ", " touch, jasmine ", " screen ", " establish, society, relate to ", " fully, times, barium "; F, speech custom, collocation custom and dictionary just organized in remaining alternative word compare judgement, " use mixing input method to be applicable to touch panel device " final optimum arranging scheme and output to screen, if alternative arranging scheme is arranged, arranging scheme is arranged according to customs such as group speech, collocation and is outputed to screen with alternative.
When recognition result being screened, can take following two kinds of schemes as required: only allow to meet the recognition result of identification code as optimal result and candidate result with identification code; The recognition result that does not meet identification code cannot be as optimal result, but can be used as candidate result.Because user's hand-written custom is different, such as " going into " word, has the people to write left-falling stroke earlier, also has the people to write right-falling stroke earlier, when this type of word was screened, when can be set to identification code for left-falling stroke or right-falling stroke, " going into " word was all eligible, and other analogues are example herewith.Owing to error can occur during for the input information identification of auxilliary input, press down when too short such as input, can be identified as a little or press down, all eligible during then the first sum of screening of being depicted as a little or pressing down, other analogues are herewith routine.
Embodiment 7, with reference to Fig. 5, this embodiment is to be primary input with the Chinese speech input mode; Candidate's Chinese stroke being chosen as auxilliary input, the use-pattern of auxilliary input is by stroke and the mapping of keyboard portion key or the mode of showing the virtual key that comprises stroke information on screen are carried out, and is identical with the auxilliary embodiment of importing in the embodiment 2.
It is as follows to illustrate this scheme: in the time of by primary input input " the use mixing input method is applicable to touch panel device " voice messaging, key in or select the key of each word first stroke correspondence or virtual key etc. by auxilliary input, be followed successively by and " cast aside; cast aside; point; cast aside; horizontal stroke; press down, the point, cast aside, cast aside, horizontal, cast aside, horizontal, cross break, the point, cast aside "; primary input and auxilliary input are finished the back system primary input voice messaging are discerned; process is following but be not limited to following order: a; after the voice messaging of primary input was analyzed, the judgement input information was the combination of " shi yong hun he shu ru fa shi yong yu chu mo ping she bei "; B, search alternative word, as the alternative word of " shi " for " city, be, the time, make, scholar, formula, thing, ten, begin, show, suitable " etc. a plurality of phonetically similar words, and can be by the scope that alternative word is further dwindled in the judgement of tone, in view of the reason of various places dialect can be included in alternative word scope such as " si " close pronunciation; C screens alternative word by the information of auxilliary input method input, and the first stroke is the reservation following " making " of left-falling stroke etc. when writing, and can will keep " beginning " according to the writing style difference of different people in this step; D, information for the input of primary input method is carried out b successively, the c step, screen alternative word, as example, remaining alternative word be followed successively by " make, begin ", " with, hire ", " mixed, muddy, palace gate ", " with, what, close, box, standing grain ", " fail, state, comb, express ", " going into ", " method ", " suitable, family name, decorations ", " with, hire ", " in, the fine jade ", " locate, touch, Chu ", " touch, jasmine ", " screen ", " establish, society, relate to ", " fully, times, barium "; E, speech custom, collocation custom and dictionary just organized in remaining alternative word compare judgement, " use mixing input method to be applicable to touch panel device " final optimum arranging scheme and output to screen, if alternative arranging scheme is arranged, arranging scheme is arranged according to customs such as group speech, collocation and is outputed to screen with alternative.
Embodiment 8, with reference to Fig. 5, this embodiment is to be primary input with the Chinese speech input mode; Candidate's Chinese font structure is chosen as auxilliary input, the use-pattern of auxilliary input is by font structure and the mapping of keyboard portion key or the mode of showing the virtual key that comprises the font structure on screen are carried out, identical with the embodiment of auxilliary input in the embodiment 3, auxilliary input input mode no longer illustrates.
It is as follows to illustrate this scheme: in the time of by primary input input " the use mixing input method is applicable to touch panel device " voice messaging, key in or select the key or the virtual key of each word font structure mapping by auxilliary input, be followed successively by " about; independent body; about; upper, middle and lower (up and down); about; independent body, about, semi-surrounding, independent body, independent body, about, about, semi-surrounding, about, up and down "; primary input and auxilliary input are finished the back system primary input voice messaging is discerned; process is following but be not limited to following order: a; after the voice messaging of primary input was analyzed, the judgement input information was the combination of " shi yong hun he shu ru fa shi yong yu chu mo ping she bei "; B, search alternative word, as the alternative word of " shi " for " city, be, the time, make, scholar, formula, thing, ten, begin, show, suitable " etc. a plurality of phonetically similar words, and can be by the scope that alternative word is further dwindled in the judgement of tone, in view of the reason of various places dialect can be included in alternative word scope such as " si " close pronunciation; C screens alternative word by the information of auxilliary input method input, is that the reservation of left and right sides structure is following " make, time, beginning " etc.; D carries out b successively for the information of primary input method input, and the c step is screened alternative word; E, speech custom, collocation custom and dictionary just organized in remaining alternative word compare judgement, " use mixing input method to be applicable to touch panel device " final optimum arranging scheme and output to screen, if alternative arranging scheme is arranged, arranging scheme is arranged according to customs such as group speech, collocation and is outputed to screen with alternative.
When above each scheme is implemented, following explanation is arranged:
A, used sound bank, hand-written storehouse etc. can be preserved on the internet or on the employed equipment of user when discerning;
B, user's dictionary etc. can possess the user and import word habit statistical function;
C can have association function during output, imports the word custom by user's dictionary in conjunction with the user and provides candidate word;
D, the flow process of various Chinese speech input methods is roughly the same or variant slightly, the naming method of each flow process may be different, but preceding 5 kinds of embodiments are after the voice messaging of primary input is discerned processing, again it is screened by identification code, the sound bank of these several schemes is huger, can take with sound bank be put on the network discern by Network Transmission input voice or phonetic feature after, return the mode that the user uses equipment again, therefore when identifying information being screened by the indications of auxilliary input, can The selection result be returned the user at the enterprising row filter of network and use equipment, perhaps recognition result screens after returning user's use equipment again;
E, the embodiment of embodiment 6,7,8 is slightly different with the recognition method of existing voice input method, embodiment 6,7,8 can be that unit discerns screening with regard to the pronunciation of single word to the input voice messaging, collocation compares identification by dictionary between the word that meets screening conditions after the screening under again to each pronunciation, export optimum arranging scheme and alternative arranging scheme, needed sound bank is littler than preceding 5 embodiments, be more convenient for sound bank is placed on the subscriber equipment and discern, also can as preceding 5 embodiments, discern by network;
F, only enforcement partly describes to Chinese in embodiment of the present invention, though and need carry out identification simultaneously during the input phonetic entry of English letter and arabic numeral, because character quantity is few, the input stroke is simple, can draw with interior 3 mostly and finish or realize to connect a mode, can direct hand-written English alphabet and arabic numeral during the identification code of inputting English letter and arabic numeral when implementing, or on physical keyboard, directly key in, or on dummy keyboard, list its regional mode separately and operate, when screening by identification code, directly the English alphabet and the arabic numeral of identification code representative are exported as the ingredient of optimal case or optimal case, do not carried out the detailed description of its embodiment at this;
G, if the user is using mobile device to carry out primary input and can't assist when importing because of some situation, system then can discern input information by the input method of primary input separately, and do not screen by the auxilliary identification code of importing, in this case the discrimination of input is compared under the situation of assisting the input input and can be reduced.
Claims (10)
1. the phonitic entry method of tape identification sign indicating number input is characterized in that, with the Chinese speech input method as the primary input mode, with the non-voice input mode as auxilliary input mode, two kinds of mixing input methods that input mode is carried out jointly.
2. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 1 is characterized in that, discerns at the voice to primary input, screens by the recognition result of the auxilliary identification code of importing to primary input.
3. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 2 is characterized in that the result who does not meet screening conditions can keep.
4. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 2 is characterized in that auxilliary input can be imported for stroke.
5. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 3 is characterized in that auxilliary input can be imported for stroke.
6. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 5 is characterized in that auxilliary input can be the stroke handwriting input, and the stroke information after the input information of auxilliary input is discerned is as identification code.
7. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 4 is characterized in that auxilliary input can be the mode that given stroke corresponding virtual key is selected.
8. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 2 is characterized in that auxilliary input can be the Chinese character pattern structure.
9. the phonitic entry method of a kind of tape identification sign indicating number input according to claim 8 is characterized in that auxilliary input can be the mode that given Chinese character pattern structure corresponding virtual key is selected.
10. the phonitic entry method of tape identification sign indicating number input, it is characterized in that, with handwriting input as the primary input mode,, the primary input recognition result is screened as auxilliary input mode in the phonetic entry mode by comparing with the auxilliary voice of importing to the pronunciation of the information after the primary input identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100592461A CN103218199A (en) | 2013-02-26 | 2013-02-26 | Phonetic input method with identification code input function |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2013100592461A CN103218199A (en) | 2013-02-26 | 2013-02-26 | Phonetic input method with identification code input function |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103218199A true CN103218199A (en) | 2013-07-24 |
Family
ID=48816042
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2013100592461A Pending CN103218199A (en) | 2013-02-26 | 2013-02-26 | Phonetic input method with identification code input function |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103218199A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014187418A1 (en) * | 2013-09-29 | 2014-11-27 | 中兴通讯股份有限公司 | Online interactive processing method, device and server |
| CN106294306A (en) * | 2015-05-14 | 2017-01-04 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1549244A (en) * | 2003-05-22 | 2004-11-24 | 宏�股份有限公司 | Identificating method for integrated speech and hand writing inputting |
| CN101082836A (en) * | 2007-06-29 | 2007-12-05 | 华中科技大学 | Chinese characters input system integrating voice input and hand-written input function |
| CN101221469A (en) * | 2007-11-23 | 2008-07-16 | 成都理工大学 | Stroke input method of mobile keyboard |
| CN101315666A (en) * | 2008-07-11 | 2008-12-03 | 中国科学院软件研究所 | Multi-channel hand-written Chinese error correction method based on voice |
| CN101488044A (en) * | 2009-02-18 | 2009-07-22 | 陈拙夫 | Voice and single-pen mixed computer Chinese character input method |
| US20120014603A1 (en) * | 2006-07-06 | 2012-01-19 | Senapps, Llc. | Recognition method and system |
| CN102937834A (en) * | 2012-11-26 | 2013-02-20 | 上海量明科技发展有限公司 | Mixed input method, client and system |
-
2013
- 2013-02-26 CN CN2013100592461A patent/CN103218199A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1549244A (en) * | 2003-05-22 | 2004-11-24 | 宏�股份有限公司 | Identificating method for integrated speech and hand writing inputting |
| US20120014603A1 (en) * | 2006-07-06 | 2012-01-19 | Senapps, Llc. | Recognition method and system |
| CN101082836A (en) * | 2007-06-29 | 2007-12-05 | 华中科技大学 | Chinese characters input system integrating voice input and hand-written input function |
| CN101221469A (en) * | 2007-11-23 | 2008-07-16 | 成都理工大学 | Stroke input method of mobile keyboard |
| CN101315666A (en) * | 2008-07-11 | 2008-12-03 | 中国科学院软件研究所 | Multi-channel hand-written Chinese error correction method based on voice |
| CN101488044A (en) * | 2009-02-18 | 2009-07-22 | 陈拙夫 | Voice and single-pen mixed computer Chinese character input method |
| CN102937834A (en) * | 2012-11-26 | 2013-02-20 | 上海量明科技发展有限公司 | Mixed input method, client and system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2014187418A1 (en) * | 2013-09-29 | 2014-11-27 | 中兴通讯股份有限公司 | Online interactive processing method, device and server |
| CN104519040A (en) * | 2013-09-29 | 2015-04-15 | 中兴通讯股份有限公司 | Method, device and server for processing online interaction |
| CN106294306A (en) * | 2015-05-14 | 2017-01-04 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
| CN106294306B (en) * | 2015-05-14 | 2019-04-26 | 联想(北京)有限公司 | A kind of information processing method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US8994660B2 (en) | Text correction processing | |
| KR100704093B1 (en) | Component-based, adaptive stroke-order system | |
| CN101334704B (en) | Multichannel Chinese input method facing to mobile equipment | |
| CN102467319B (en) | Handwriting Chinese character input method and system | |
| CN104464720A (en) | Apparatus and method for selecting a control object by voice recognition | |
| CN102629158A (en) | Character input method and device on basis of touch screen system | |
| US7669122B2 (en) | Using input of rhyming characters for computer text entry of Chinese characters | |
| US20120086638A1 (en) | Multi-area handwriting input system and method thereof | |
| CN102937837A (en) | Method for inputting words on the basis of incomplete recognition quickly | |
| CN102272827A (en) | Method and apparatus utilizing voice input to resolve ambiguous manually entered text input | |
| CN1237435C (en) | Chinese Character graphic form input device and method | |
| CN103218199A (en) | Phonetic input method with identification code input function | |
| TW201512969A (en) | Method of increasing handwriting input efficiency | |
| US20110285635A1 (en) | Sign language keyboard and sign language searching apparatus using the same | |
| CN106095126A (en) | The generation method of dummy keyboard and the method and system of input Sanskrit | |
| CN102289299A (en) | Chinese character Pinyin input method using English letter keys for selecting characters | |
| KR101355377B1 (en) | Korean syllable input method by continuous dragging on screen keyboard | |
| KR20090077086A (en) | Apparatus and method for inputting alphabet characters from keypad | |
| CN104345898A (en) | Spelling clicking and sliding input method, input device and electronic equipment | |
| KR100625357B1 (en) | Alphabet input apparatus in a keypad and method thereof | |
| CN106873950A (en) | A kind of reminding method and device based on calendar application | |
| KR101275365B1 (en) | Apparatus and method for inputting alphabet characters from keypad | |
| CN102467245B (en) | Method for inputting Chinese characters by using character and word splitting interactive entrance | |
| KR20110008660A (en) | Korean syllable input method by continuous drag on screen keyboard Part 2 | |
| KR20210027300A (en) | Korean syllable characters input method and device on screen keyboard |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130724 |
|
| WD01 | Invention patent application deemed withdrawn after publication |