CN102193736A - Input method and system supporting multimode automatic switching - Google Patents
Input method and system supporting multimode automatic switching Download PDFInfo
- Publication number
- CN102193736A CN102193736A CN201110101100XA CN201110101100A CN102193736A CN 102193736 A CN102193736 A CN 102193736A CN 201110101100X A CN201110101100X A CN 201110101100XA CN 201110101100 A CN201110101100 A CN 201110101100A CN 102193736 A CN102193736 A CN 102193736A
- Authority
- CN
- China
- Prior art keywords
- input
- user
- keyboard
- frame
- handwriting
- 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.)
- Granted
Links
Images
Landscapes
- Character Discrimination (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention relates to an input method supporting multimode automatic switching. The method comprises the following steps of: analyzing an input mode of a user according to first stroke information input by the user, and if input is handwriting input, entering a handwriting input mode, tracking and identifying handwriting input in real time and completing input of a single character; if the input is keyboard input, entering a keyboard input mode, feeding back a user key pressing event and recording the input track of the user, performing secondary analysis on subsequent input of the user, and if the subsequent input is handwriting input according to the secondary analysis, clearing the historical marks of the keyboard input and entering the handwriting input mode; and if the subsequent input is keyboard input according to the secondary analysis, keeping the keyboard input mode. The invention further provides an input system supporting multimode automatic switching. Particularly specific to the problem of probable wrong judgment caused by the input of short strokes, all inputs which are determined as key trigger events are further determined and restored, so that wrong judgment is avoided to the maximum extent.
Description
Technical field
The present invention relates to information typing field, particularly a kind of input method and input system of supporting that multi-mode automaticallyes switch.
Background technology
Along with the swift and violent development of infotech, the acceleration of the 3G industry fusion and the arrival in 3G mobile communication epoch, new intelligent human-machine interaction is used and is maked rapid progress.Wherein, handwriting input and keyboard input have just obtained more and more users' approval as two kinds of common interactive modes.The handwriting input mode is meant on touch-screen hand-written, and by the recognition system of inside the writing of importing is converted into ASCII character, and shows with the standard letter form.The dummy keyboard input mode is that dummy keyboard is set on terminal, imports by the selection of style of writing.Because button is more, reduced on the ordinary electronic equipment on the dummy keyboard because the layout of 9 keys need repeat repeatedly the defective that button is finished a letter input.
In general, when Chinese character was imported, owing to meet the input demand of user's efficient natural more, the user often tended to finish the character input in hand-written mode.When English word was imported, perhaps when the user was not familiar with font and need imports with phonetic, it is convenient more that the keyboard input then seems.For the better response user's request, most on the market at present smart machine all provides hand-written simultaneously and keyboard entry method is selected for the user.
The matter of utmost importance that multimodal input system need solve is to judge that correctly the user imports handwriting input or keyboard triggers input, so that take correct operation response.Under traditional multimodal input system, handwriting input and keyboard input are individualisms, need to set respectively to use.The user at first needs by the manually selected single-mode of default function key before input character, or with the keyboard input or with handwriting input.
Fig. 1 illustrates the system with multiple different input modes.Fig. 1 a provides the keyboard inputting interface after the switching.The user finishes the input of character in the clicking trigger mode on dummy keyboard.Fig. 1 b has provided module and has switched synoptic diagram.By the function switch key in the diagram lower right corner, the user can select only pattern in a plurality of options that eject.Fig. 1 c is a handwriting input mode, and the user can be at default zone (writing frame or the full frame) written character of writing.
Under this traditional mode, the user as when using different input pattern, repeat continuous manual setting input pattern in the input process of finishing a string literal.Cause the reduction of whole input efficiency on the one hand easily, owing to need artificial execution pattern to switch, user's the sense of continuity of writing also reduces greatly on the other hand.Therefore, input pattern can not automatically be switched according to user's intention in this system, uses inconvenience, and bigger limitation is arranged.
In order to give full play to the convenience of the collaborative input of multiple input pattern, press for a kind of input pattern intelligence automatic switchover algorithm of efficient natural, to be supported on the terminal system with dummy keyboard and hand-write input function the switching of keyboard input and handwriting input when realizing input automatically.
The user can only be with the single-mode input character under the traditional mode in order to overcome, the problem that still needs manual intervention when between different input patterns, switching, proposed at present information input from touch screen is carried out the method that automatic distinguishing is handled, it is differentiated automatically is key information or hand-written information, and takes corresponding control module to be handled.Under such input pattern, the user no longer needs to consider the mode switch problem, but simply in the input field with the free smooth character input of finishing of the mode of any custom.
When input character by different way, the signal that touch-screen captures often shows different characteristics.The user triggers button in the click mode when importing with keyboard, thereby on touch-screen the residence time shorter, person's handwriting displacement is also shorter, on the contrary if import with ways of writing, longer duration of contact with touch-screen, the person's handwriting displacement that collects is also longer.Patent CN100561414C open source information shows, can do automatic distinguishing to input pattern by the first stroke of a Chinese character characteristic of analysis user input.
When the user falls the first stroke, system promptly analyzes distance and the time of first sampled point of the first stroke of a Chinese character to N sampled point, start to write a little to the average velocity between this sampled point according to first distance and the Time Calculation first of starting to write a little this sampled point, if this average velocity surpasses the judgement speed of default, simultaneously first start to write the distance of this sampled point greater than the judging distance of default, substantially can assert that then the user is with the ways of writing input, otherwise then may be to trigger the button input.
Fig. 2 illustrates the input process flow diagram that present support multi-mode automaticallyes switch, and concrete operation steps is as follows:
Step S101, system initialization, the initialization system parameter: judging distance S0, judge speed V0 and sampling number NO.
Step S102, judge that whether the position of starting to write of the first stroke is positioned at function button zone on the screen, if change step S104 over to, otherwise changes step S103 over to;
Step S103, judge whether to enter hand-written state with other algorithms;
Step S104, obtain first start to write N sampled point apart from S and time t;
Step S105, according to first start to write N sampled point calculate average velocity v apart from S and time t;
Step S106, judge that first starts to write a little and whether start to write average velocity v between some these 2 positions of N surpasses the judgement speed V0 of system intialization, judge that simultaneously distance between this two positions is whether greater than the judging distance S0 of default, if the judgement speed V0 that average velocity V surpass to set and apart from S during greater than the judging distance S0 that sets, change step S107 over to, otherwise change step S108 over to;
Step S107, control function button area enter hand-written state, and follow the tracks of and gather follow-up person's handwriting;
Step S108, judge that whether sampling number N surpasses the sampling number N0 of default,, change step S104 after sampling number adds 1 over to as sampling number N during less than the sampling number N0 of default; Otherwise change step S109 over to;
Step S109, drive system enter button and trigger state, follow the tracks of the alphabet key that the user triggers.
Under the support of this system, the user no longer needs to consider the switching between different mode, but simply directly imports in the mode of custom separately according to different needs.This method is obtaining certain achievement on the input problem continuously, but still there are many problems in actual applications, particularly in the simple stroke input, when admission control, the system that is to say does not collect the enough state of starting to write sampled points, the average velocity and the distance that calculate by such scheme tend to less than the threshold value that sets in advance, and trigger state and will write the state erroneous judgement for button, cause follow-up input error.
Summary of the invention
Purpose of the present invention provides a kind of input method of supporting that multi-mode automaticallyes switch, what this method existed when importing at short and small stroke may judge problem by accident, further affirmation reparation is done in all inputs of confirming as the button trigger event, maximum possible avoid judging by accident mistake.
The present invention is a kind of to support the input method that multi-mode automaticallyes switch, and comprising: according to the first sum of information analysis user's of user's input input pattern, if handwriting input enters handwriting input mode, the input of single character is finished in real-time follow-up identification handwriting input; If keyboard input enters the keyboard input pattern, the input trajectory of feedback user key-press event and recording user, and the follow-up input of user carried out secondary analysis, and be handwriting input as secondary analysis, remove the historical rudiment of keyboard input, enter handwriting input mode; As secondary analysis is the keyboard input, keeps the keyboard input pattern.
Preferably, according to the first sum of information analysis user's of user input input pattern be: relatively the actual samples point sequence is apart from S and judging distance St, the actual samples point sequence apart from S greater than turn-off from St, be judged as handwriting input; The actual samples point sequence apart from S less than turn-off from St, be judged as keyboard input.
Preferably, the input pattern according to the first sum of information analysis user of user input is specially:
Step 1, sample frame sequence number i=1 is set;
Step 2, calculate from the 1st frame to current i frame in the sampled point sequence apart from S;
If whether step 3, judging distance S be judged as handwriting input, otherwise change step 4 greater than judging distance St;
Whether the sample frame time of step 4, judgement accumulative total is greater than a judgement time T1, or the first sum of end of input, if be judged as the keyboard input, otherwise changes step 5 over to;
Step 5, sampling frame number i=i+1 is set, changes the sampling point information that step 2 is investigated next time frame over to.
Preferably, the secondary analysis method is specially:
Step 6, sample frame sequence number i=1 is set;
Step 7, calculate from the 1st frame to current i frame in the sampled point sequence apart from S;
If whether step 8, judging distance S be judged as handwriting input, otherwise change step 9 greater than judging distance St;
Whether the sample frame time of step 9, judgement accumulative total is greater than secondary judgement time T2, or the first sum of end of input, if be judged as the keyboard input, otherwise changes step 10 over to;
Step 10, sampling frame number i=i+1 is set, changes the sampling point information that step 7 is investigated next time frame over to.
Preferably, also comprise adjustment judging distance St: as above a character is handwriting input, dwindles the value of judging distance St; As above a character is the keyboard input, strengthens the value of judging distance St.
The present invention also provides a kind of input method of supporting that multi-mode automaticallyes switch, and what this system existed during at short and small stroke input may judge problem by accident, and further affirmation reparation is done in all inputs of confirming as the button trigger event, maximum possible avoid judging by accident mistake.
A kind of input system of supporting that multi-mode automaticallyes switch of the present invention, comprise judge module and secondary judge module first: judge module first, be used for input pattern according to the first sum of information analysis user of user's input, if handwriting input, enter handwriting input mode, the input of single character is finished in real-time follow-up identification handwriting input; If the keyboard input enters the keyboard input pattern, the input trajectory of feedback user key-press event and recording user; The secondary judge module is used for when judge module is judged as the keyboard input pattern first secondary analysis being carried out in the follow-up input of user, is handwriting input as secondary analysis, removes the historical rudiment of keyboard input, enters handwriting input mode; As secondary analysis is the keyboard input, keeps the keyboard input pattern.
Preferably, judge module comprises sampled point sequence distance calculation submodule, relatively judges that submodule, a judgement time submodule and the frame number of sampling are provided with module first:
The sampling frame number is provided with module, is used to be provided with sample frame sequence number i=1;
Sampled point sequence distance calculation submodule, be used for calculating from the 1st frame to current i frame in the sampled point sequence apart from S;
Relatively judge submodule, whether be used for judging distance S,, otherwise start the judgement time submodule one time if be judged as handwriting input greater than judging distance St;
A judgement time submodule, whether the sample frame time that is used to judge accumulative total is greater than a judgement time T1, or the first sum of end of input, if be judged as the keyboard input, otherwise start the sampling frame number module is set; The sampling frame number is provided with module adjustment sampling frame number i=i+1.
Preferably, the secondary judge module comprises sampled point sequence distance calculation submodule, relatively judges that submodule, secondary judgement time submodule and sampling frame number are provided with module:
The sampling frame number is provided with module, is used to be provided with sample frame sequence number i=1;
Sampled point sequence distance calculation submodule, be used for calculating from the 1st frame to current i frame in the sampled point sequence apart from S;
Relatively judge submodule, whether be used for judging distance S,, otherwise start secondary judgement time submodule if be judged as handwriting input greater than judging distance St;
Secondary judgement time submodule, whether the sample frame time that is used to judge accumulative total is greater than secondary judgement time T2, or the first sum of end of input, if be judged as the keyboard input, otherwise start the sampling frame number module is set; The sampling frame number is provided with module adjustment sampling frame number i=i+1.
Preferably, comprise also and adjust the judging distance module that be used to adjust judging distance St, as above a character is handwriting input, dwindles the value of judging distance St; As above a character is the keyboard input, strengthens the value of judging distance St.
Preferably, described keyboard inputting interface and pen interface are a unified interface.
Compared with prior art, the present invention has the following advantages:
The present invention is by analyzing the characteristic of input first stroke of a Chinese character data, come the intention of predictive user input according to its displacement size in the time of determining, what exist when importing at short and small stroke especially may judge problem by accident, further affirmation reparation is done in all inputs of confirming as the button trigger event, maximum possible avoid judging by accident mistake.
Description of drawings
Fig. 1 a is the keyboard inputting interface figure after switching;
Fig. 1 b is that module is switched synoptic diagram;
Fig. 1 c is the handwriting input mode synoptic diagram;
Fig. 2 supports the input process flow diagram that multi-mode automaticallyes switch at present;
Fig. 3 a imports synoptic diagram for the present invention with the spelling input method button;
Fig. 3 b is a handwriting input synoptic diagram of the present invention;
Fig. 4 supports the input method process flow diagram that multi-mode automaticallyes switch for the present invention;
Fig. 5 is the first sum of information analysis process flow diagram of user of the present invention;
Fig. 6 is a secondary analysis process flow diagram flow chart of the present invention;
Fig. 7 supports the input system synoptic diagram that multi-mode automaticallyes switch for the present invention;
Fig. 8 is the present invention's judge module synoptic diagram first;
Fig. 9 is a secondary judge module synoptic diagram of the present invention;
Figure 10 supports another embodiment synoptic diagram of input system that multi-mode automaticallyes switch for the present invention.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.
Problem at the such scheme existence, by analyzing the characteristic of input first stroke of a Chinese character data, come the intention of predictive user input according to its displacement size in the time of determining, what exist when importing at short and small stroke especially may judge problem by accident, further affirmation reparation is done in all inputs of confirming as the button trigger event, maximum possible avoid judging by accident mistake.
Fig. 3 illustrates a kind of keyboard and writes surface chart.Keyboard area is the user input area, accepts the input of user with key mode or ways of writing.Fig. 3 a has showed the process with spelling input method button input " news " word.Fig. 3 b has showed that then handwriting input " writes " process of word.As seen from Figure 3, these two inputting interfaces are identical, and the user finishes keyboard input and handwriting input on a unified interface.And unlike in traditional multi-mode input system, need behind selected certain the single input pattern in function setting district, import in single mode.This input method can be applied in the program that needs text editing arbitrarily." addressee " on touch-screen top and " short message " frame are used for accepting to show identification character and support corresponding editing operation.Be the character candidates district between text editing district and the input field, the association's character that produces when identification candidate when being used to show handwriting input or keyboard input.
System of the present invention will be at three kinds of different conditions, and promptly vacant attitude is switched between button attitude and handwriting input attitude mutually.Vacant attitude refers to that system is in the blank waiting status of button and hand-written mode switch; Button attitude control system is accepted the keyboard input, and the immediate feedback user triggers button and carries out subsequent treatment; Hand-written attitude control system is accepted user handwriting input, instant playback handwriting trace.Under the button input pattern, the user finishes the complete input of single behind selected certain word from the word candidates tabulation, and system turns back to vacant state subsequently.Similarly, under write mode after the user confirms recognition result system return vacant state.Finish the input of complete character or word because of the user adopts single input pattern usually, the present invention only judges user's input pattern by the data characteristic of analyzing in the character first stroke of a Chinese character or the first stroke of a Chinese character finite time.
Fig. 4 illustrates the input method that the present invention supports that multi-mode automaticallyes switch, and concrete steps are as follows.
Step S401, system initialization also are provided with systematic parameter, and systematic parameter comprises judgement time T1 one time, secondary judgement time T2, and judging distance St;
Step S402, gather the touch screen information of user's input, chronologically touch screen information is recorded as the two-dimensional coordinate point sequence (x, y), x wherein, y is respectively the horizontal ordinate and the ordinate of sampled point;
Step S403, according to the possible input pattern of the first sum of information analysis user of user input; In general, when keyboard is imported in the unit interval on the touch-screen person's handwriting displacement shorter, and under write mode, the person's handwriting displacement that collects in the unit interval is often longer.By accumulation displacement S in judgement time T1 frame relatively and the relation of judging distance St, switch different input patterns, when the actual samples point sequence apart from S during greater than St, judge currently to be input as handwriting input, otherwise then may import for keyboard;
Step S404, judge whether to be handwriting input, if change step S405 over to otherwise change step S406 over to;
Step S405, system enter hand-written state: the current input person's handwriting of instant playback user, and start rear end handwriting recognition engine real-time follow-up identification handwriting input, change the input that step S4011 finishes the single character over to;
Step S406, control system enter button and trigger state, the input trajectory of immediate feedback user key-press incident and recording user;
Step S407, the user is judged that at secondary the follow-up input of T2 in the time carry out secondary analysis, to revise possible pattern misjudgment;
Step S408, judge whether the result of secondary analysis is hand-written pattern,, otherwise change step S410 over to if change step S409 over to;
S409, the historical rudiment of removing the keyboard input and keyboard input associated internal memory change S405 over to and enter hand-written pattern;
S410, maintenance keyboard input pattern are followed the tracks of the follow-up key-press event of user;
S411, the input of end single.
The first-selected word of recognition result is sent to the text editing district under handwriting input mode, and a plurality of recognition result shows affirmation for you to choose simultaneously in candidate regions.Under the button pattern, the interior continual renovation of candidate regions is associated character and behind the selected character of user, is sent it to and finish this time input in the text editing district.
Wherein, the refinement flow process of step S403 as shown in Figure 5.
Step S501, according to the possible input pattern of the first sum of information analysis user of user input; System initialization is provided with the sample frame sequence number i=1 of investigation;
Step S502, calculate from the 1st frame to current i frame in the sampled point sequence always apart from S;
Step S503, judge this apart from S whether greater than the judging distance St of systematic parameter, if change step S504 over to, otherwise change step S505 over to;
Step S504, control system enter hand-written state: the interior and current input person's handwriting of user of instant playback buffer memory, and start rear end handwriting recognition engine real-time follow-up identification handwriting input;
Step S505, judge whether current investigation finishes, whether the sample frame time of judging accumulative total greater than judgement time T1 or the first sum of end of input, if change step S507 over to, otherwise change step S506 over to;
Step S506, the sampling frame number i=i+1 of investigation is set, changes the sampling point information that step S502 investigates next time frame over to;
Step S507, control system enter button and trigger state, the input trajectory of immediate feedback user key-press incident and recording user.
Systematic parameter judging distance St, the setting of a judgement time T1 has important effect to the raising of system performance.Distance threshold is provided with excessive, then easily short and small stroke input erroneous judgement is key-press event, otherwise then thinks the button input by mistake handwriting input.In general, the setting of these systematic parameters depends on the size of display screen sampling rate, the speed of hardware processor and the framework of system software etc.The present invention takes all factors into consideration user's writing experience and actual effect, is that T1 is 200-300ms with a judgement time, is preferably 250ms; St is the 15-25 pixel, is preferably 20 pixels.
Legacy system substantially all is based on once judgement to the first sum of analysis to the judgement of input pattern, often no longer considers pattern correction problem after determining that it is the keyboard input.But this method based on distance analysis is subjected to various noise jamming in actual applications easily, be that short and small stroke is write in the judgement to the first stroke particularly, the first sum of stroke as words such as " ", " words ", stroke itself is not very long just, then often causes system's erroneous judgement to be button operation if also have the part sampled point to lose.In order in time to revise input pattern so that accept follow-up handwriting input, the notion of secondary correction has been proposed at the erroneous judgement problem of short and small stroke among the present invention, after being judged as the keyboard input, continue the follow-up stroke signal characteristic of trace analysis and carry out the secondary judgement, in order to reduce single stroke risk, shown in step S407 among Fig. 4.
Referring to Fig. 6, secondary analysis process of the present invention is shown, concrete steps are as follows.
Step S601, according to the possible input pattern of the first sum of information analysis user of user input; System initialization is provided with the sample frame sequence number i=1 of investigation;
Step S602, calculate from the 1st frame to current i frame in the sampled point sequence always apart from S;
Step S603, judge this apart from S whether greater than the judging distance St of systematic parameter, if change step S604 over to, otherwise change step S605 over to;
Step S604, control system enter hand-written state: the interior and current input person's handwriting of user of instant playback buffer memory, and start rear end handwriting recognition engine real-time follow-up identification handwriting input;
Step S605, judge whether current investigation finishes, if whether the sample frame time of judging accumulative total change step S607, otherwise changes step S606 greater than secondary judgement time T2;
Step S606, the sampling frame number i=i+1 of investigation is set, changes the sampling point information that step S602 investigates next time frame over to;
Step S607, control system enter button and trigger state, the input trajectory of immediate feedback user key-press incident and recording user.
Secondary of the present invention is judged the flow process basically identical of operational scheme and the first sum of judgement, and just the Rule of judgment to the flow process end of run is modified to: whether the sample frame time of judging current investigation is greater than secondary judgement time T2.For the stability of assurance system operation, secondary judgement time T2 often is set to a bigger value, and span is 700-900ms, is preferably 800ms.Like this if system be keyboard input and accumulative total the investigation time less than secondary judgement time T2 then system will continue to judge.Write input if the button input that the secondary judgement will once be judged is modified to, then system at first removes the historical rudiment of key-press event and starts hand-written pattern, the historical person's handwriting that is stored in buffer zone is presented at writes in the district.
Because user's writing style is not quite similar, and the user constantly adapts to input mode, and unified systematic parameter of solidifying obviously can not well be met consumers' demand.Therefore the present invention continues to optimize system configuration to improve system performance by following the tracks of study user input.
In general, user's input has certain continuity, if finish the current character input with handwriting mode, also will continue to finish next character input with handwriting mode on the then very big probability.Under this hypothesis, the user is hand-written finish a character after, the distance parameter St of system then can be adjusted into a less distance threshold accordingly improving response speed, on the contrary if with character of keyboard input, then for response stability then distance threshold be set to a bigger value.Concrete formula is as follows:
S wherein
tThe judging distance parameter of system when (n) being the n time input, and S
1And S
2Be respectively two threshold values of systemic presupposition, satisfy S
1=0.5S
2The present invention defines S
1=20 picture elements.Need to prove when system initialization does not have historical input information, set S
t(1)=S
2
Based on the input method that above-mentioned support multi-mode automaticallyes switch, the present invention also provides a kind of input system of supporting that multi-mode automaticallyes switch.Referring to Fig. 7, comprise judge module 71 and secondary judge module 72 first.Judge module 71 is used for the input pattern according to the first sum of information analysis user of user's input first, if handwriting input enters handwriting input mode, the input of single character is finished in real-time follow-up identification handwriting input; If the keyboard input enters the keyboard input pattern, the input trajectory of feedback user key-press event and recording user.
Referring to Fig. 8, judge module 71 comprises sampled point sequence distance calculation submodule 711, relatively judges that submodule 712, judgement time submodule 713 and sampling frame number are provided with module 714 first.
The sampling frame number is provided with module 714 sample frame sequence number i=1 is set, the sampled point sequence was apart from S in sampled point sequence distance calculation submodule 711 calculated from the 1st frame to current i frame, judge that relatively whether submodule 712 judging distance S are greater than judging distance St, if be judged as handwriting input, otherwise start judgement time submodule 713 one time; A judgement time submodule 713 judges that whether the sample frame time of accumulative total is greater than a judgement time T1, or the first sum of end of input, if be judged as the keyboard input, otherwise start the sampling frame number module 714 is set, the sampling frame number is provided with module 714 and adjusts sampling frame number i=i+1.
Referring to Fig. 9, secondary judge module 72 comprises sampled point sequence distance calculation submodule 721, relatively judges that submodule 722, secondary judgement time submodule 723 and sampling frame number are provided with module 724.
The sampling frame number is provided with module 724 sample frame sequence number i=1 is set, the sampled point sequence was apart from S in sampled point sequence distance calculation submodule 721 calculated from the 1st frame to current i frame, judge that relatively whether submodule 722 judging distance S are greater than judging distance St, if be judged as handwriting input, otherwise start secondary judgement time submodule 723; If whether the sample frame time that secondary judgement time submodule 723 is judged accumulative total be judged as keyboard input, otherwise start sampling frame number is provided with module 724 greater than secondary judgement time T2, and the sampling frame number is provided with module 724 and adjusts sampling frame number i=i+1.
Referring to Figure 10, another embodiment of input system that the present invention supports that multi-mode automaticallyes switch is shown, comprise judge module 71, secondary judge module 72 and adjustment judging distance module 73 first.
Adjust judging distance module 73 and adjust judging distance St, as above a character is handwriting input, dwindles the value of judging distance St; As above a character is the keyboard input, strengthens the value of judging distance St.
The present invention carries out secondary analysis to the input that is judged as key-press event, helps to revise the erroneous judgement mistake of short and small stroke etc., improves the accuracy that input pattern is judged.And the systematic parameter that the present invention need be provided with only is distance parameter St, thereby system architecture is comparatively simple, and robustness is also better.The system of helping that is provided with of adaptive updates systematic parameter of the present invention constantly adapts to user's input habit, improves performance.
The present invention also can be used for supporting the input of hand-written and common 9 lattice keyboards, and hand-written in a word and keyboard input coexistence gets final product.
The above only is a preferred implementation of the present invention, does not constitute the qualification to protection domain of the present invention.Any any modification of being done within the spirit and principles in the present invention, be equal to and replace and improvement etc., all should be included within the claim protection domain of the present invention.
Claims (10)
1. an input method of supporting that multi-mode automaticallyes switch is characterized in that, comprising:
According to the first sum of information analysis user's of user input input pattern, if handwriting input enters handwriting input mode, the input of single character is finished in real-time follow-up identification handwriting input;
If keyboard input enters the keyboard input pattern, the input trajectory of feedback user key-press event and recording user, and the follow-up input of user carried out secondary analysis, and be handwriting input as secondary analysis, remove the historical rudiment of keyboard input, enter handwriting input mode; As secondary analysis is the keyboard input, keeps the keyboard input pattern.
2. the method for claim 1 is characterized in that, according to the first sum of information analysis user's of user input input pattern is:
Relatively the actual samples point sequence is apart from S and judging distance St, the actual samples point sequence apart from S greater than turn-off from St, be judged as handwriting input; The actual samples point sequence apart from S less than turn-off from St, be judged as keyboard input.
3. method as claimed in claim 2 is characterized in that, is specially according to the first sum of information analysis user's of user input input pattern:
Step 1, sample frame sequence number i=1 is set;
Step 2, calculate from the 1st frame to current i frame in the sampled point sequence apart from S;
If whether step 3, judging distance S be judged as handwriting input, otherwise change step 4 greater than judging distance St;
Whether the sample frame time of step 4, judgement accumulative total is greater than a judgement time T1, or the first sum of end of input, if be judged as the keyboard input, otherwise changes step 5 over to;
Step 5, sampling frame number i=i+1 is set, changes the sampling point information that step 2 is investigated next time frame over to.
4. the method for claim 1 is characterized in that, the secondary analysis method is specially:
Step 6, sample frame sequence number i=1 is set;
Step 7, calculate from the 1st frame to current i frame in the sampled point sequence apart from S;
If whether step 8, judging distance S be judged as handwriting input, otherwise change step 9 greater than judging distance St;
Whether the sample frame time of step 9, judgement accumulative total is greater than secondary judgement time T2, or the first sum of end of input, if be judged as the keyboard input, otherwise changes step 10 over to;
Step 10, sampling frame number i=i+1 is set, changes the sampling point information that step 7 is investigated next time frame over to.
5. as each described method of claim 1-4, it is characterized in that also comprise and adjust judging distance St: as above a character is handwriting input, dwindles the value of judging distance St; As above a character is the keyboard input, strengthens the value of judging distance St.
6. an input system of supporting that multi-mode automaticallyes switch is characterized in that, comprises judge module and secondary judge module first:
Judge module is used for the input pattern according to the first sum of information analysis user of user's input first, if handwriting input enters handwriting input mode, the input of single character is finished in real-time follow-up identification handwriting input; If the keyboard input enters the keyboard input pattern, the input trajectory of feedback user key-press event and recording user.
The secondary judge module is used for when judge module is judged as the keyboard input pattern first secondary analysis being carried out in the follow-up input of user, is handwriting input as secondary analysis, removes the historical rudiment of keyboard input, enters handwriting input mode; As secondary analysis is the keyboard input, keeps the keyboard input pattern.
7. system as claimed in claim 6 is characterized in that, judge module comprises sampled point sequence distance calculation submodule, relatively judges that submodule, a judgement time submodule and the frame number of sampling are provided with module first:
The sampling frame number is provided with module, is used to be provided with sample frame sequence number i=1;
Sampled point sequence distance calculation submodule, be used for calculating from the 1st frame to current i frame in the sampled point sequence apart from S;
Relatively judge submodule, whether be used for judging distance S,, otherwise start the judgement time submodule one time if be judged as handwriting input greater than judging distance St;
A judgement time submodule, whether the sample frame time that is used to judge accumulative total is greater than a judgement time T1, or the first sum of end of input, if be judged as the keyboard input, otherwise start the sampling frame number module is set; The sampling frame number is provided with module adjustment sampling frame number i=i+1.
8. system as claimed in claim 6 is characterized in that, the secondary judge module comprises sampled point sequence distance calculation submodule, relatively judges that submodule, secondary judgement time submodule and sampling frame number are provided with module:
The sampling frame number is provided with module, is used to be provided with sample frame sequence number i=1;
Sampled point sequence distance calculation submodule, be used for calculating from the 1st frame to current i frame in the sampled point sequence apart from S;
Relatively judge submodule, whether be used for judging distance S,, otherwise start secondary judgement time submodule if be judged as handwriting input greater than judging distance St;
Secondary judgement time submodule, whether the sample frame time that is used to judge accumulative total is greater than secondary judgement time T2, or the first sum of end of input, if be judged as the keyboard input, otherwise start the sampling frame number module is set; The sampling frame number is provided with module adjustment sampling frame number i=i+1.
9. as claim 6,7 or 8 described systems, it is characterized in that also comprise and adjust the judging distance module, be used to adjust judging distance St, as above a character is handwriting input, dwindles the value of judging distance St; As above a character is the keyboard input, strengthens the value of judging distance St.
10. as claim 6,7 or 8 described systems, it is characterized in that described keyboard inputting interface and pen interface are a unified interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110101100XA CN102193736B (en) | 2011-04-21 | 2011-04-21 | Input method and system supporting multimode automatic switching |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110101100XA CN102193736B (en) | 2011-04-21 | 2011-04-21 | Input method and system supporting multimode automatic switching |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102193736A true CN102193736A (en) | 2011-09-21 |
| CN102193736B CN102193736B (en) | 2013-06-26 |
Family
ID=44601880
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110101100XA Active CN102193736B (en) | 2011-04-21 | 2011-04-21 | Input method and system supporting multimode automatic switching |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102193736B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419645A (en) * | 2011-10-28 | 2012-04-18 | 汉王科技股份有限公司 | Method and device for inputting Chinese characters in combined mode and palm terminal |
| CN102609133A (en) * | 2012-01-13 | 2012-07-25 | 浙江优诺肯科技有限公司 | Touchpad, touch input method and touch input system integrating track input and key input |
| CN102778999A (en) * | 2012-04-16 | 2012-11-14 | 中兴通讯股份有限公司 | Mobile terminal and full screen handwriting processing method thereof |
| CN103106024A (en) * | 2011-11-15 | 2013-05-15 | 三星电子株式会社 | Text input method in touch screen terminal and apparatus therefor |
| CN103558943A (en) * | 2013-11-08 | 2014-02-05 | 安徽科大讯飞信息科技股份有限公司 | Method and system for realizing multi-mode synchronous input |
| CN104423867A (en) * | 2013-09-03 | 2015-03-18 | 深圳市世纪光速信息技术有限公司 | Character input method and character input device |
| CN104679224A (en) * | 2013-11-30 | 2015-06-03 | 富泰华工业（深圳）有限公司 | Input device and input management system |
| CN104793727A (en) * | 2014-01-21 | 2015-07-22 | 安徽科大讯飞信息科技股份有限公司 | Method and system for achieving individual multi-mode input |
| CN106484181A (en) * | 2016-09-20 | 2017-03-08 | 青岛海信电器股份有限公司 | The touch-responsive method and device of infrared touch panel |
| WO2017144171A1 (en) * | 2016-02-23 | 2017-08-31 | Myscript | System and method for multiple input management |
| CN104076945B (en) * | 2014-07-10 | 2017-10-10 | 广州三星通信技术研究有限公司 | Apparatus and method for showing input keyboard in the terminal |
| CN107256124A (en) * | 2017-04-21 | 2017-10-17 | 青岛海信电器股份有限公司 | A kind of electronic whiteboard touch control method and device |
| CN108182000A (en) * | 2017-12-25 | 2018-06-19 | 科大讯飞股份有限公司 | Input through keyboard detection method and device, storage medium, electronic equipment |
| CN109213412A (en) * | 2017-07-03 | 2019-01-15 | 北京搜狗科技发展有限公司 | Input method, device and machine readable media |
| CN111124222A (en) * | 2019-12-03 | 2020-05-08 | 科大讯飞股份有限公司 | Input switching method and device, electronic equipment and storage medium |
| CN112633243A (en) * | 2020-12-31 | 2021-04-09 | 安徽鸿程光电有限公司 | Information identification method, device, equipment and computer storage medium |
| US11461507B2 (en) * | 2018-10-30 | 2022-10-04 | Third Block Gear | Systems and methods for secure peripherals |
| WO2023030377A1 (en) * | 2021-08-31 | 2023-03-09 | 华为技术有限公司 | Writing/drawing content display method and related device |
| WO2023124141A1 (en) * | 2021-12-27 | 2023-07-06 | 荣耀终端有限公司 | Input method calling method and related device |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050102620A1 (en) * | 2003-11-10 | 2005-05-12 | Microsoft Corporation | Boxed and lined input panel |
| CN1991700A (en) * | 2005-12-28 | 2007-07-04 | 中兴通讯股份有限公司 | Mobile terminal having keyboard and hand-write synergic input function |
| CN101183284A (en) * | 2007-11-26 | 2008-05-21 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal hand-written inputting method, device and mobile terminal |
-
2011
- 2011-04-21 CN CN201110101100XA patent/CN102193736B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050102620A1 (en) * | 2003-11-10 | 2005-05-12 | Microsoft Corporation | Boxed and lined input panel |
| CN1991700A (en) * | 2005-12-28 | 2007-07-04 | 中兴通讯股份有限公司 | Mobile terminal having keyboard and hand-write synergic input function |
| CN101183284A (en) * | 2007-11-26 | 2008-05-21 | 宇龙计算机通信科技(深圳)有限公司 | Mobile terminal hand-written inputting method, device and mobile terminal |
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102419645A (en) * | 2011-10-28 | 2012-04-18 | 汉王科技股份有限公司 | Method and device for inputting Chinese characters in combined mode and palm terminal |
| US9569091B2 (en) | 2011-11-15 | 2017-02-14 | Samsung Electronics Co., Ltd | Text input method in touch screen terminal and apparatus therefor |
| CN103106024A (en) * | 2011-11-15 | 2013-05-15 | 三星电子株式会社 | Text input method in touch screen terminal and apparatus therefor |
| US11042291B2 (en) | 2011-11-15 | 2021-06-22 | Samsung Electronics Co., Ltd. | Text input method in touch screen terminal and apparatus therefor |
| US10459626B2 (en) | 2011-11-15 | 2019-10-29 | Samsung Electronics Co., Ltd. | Text input method in touch screen terminal and apparatus therefor |
| US9921744B2 (en) | 2011-11-15 | 2018-03-20 | Samsung Electronics Co., Ltd. | Text input method in touch screen terminal and apparatus therefor |
| CN102609133A (en) * | 2012-01-13 | 2012-07-25 | 浙江优诺肯科技有限公司 | Touchpad, touch input method and touch input system integrating track input and key input |
| CN102778999A (en) * | 2012-04-16 | 2012-11-14 | 中兴通讯股份有限公司 | Mobile terminal and full screen handwriting processing method thereof |
| CN104423867A (en) * | 2013-09-03 | 2015-03-18 | 深圳市世纪光速信息技术有限公司 | Character input method and character input device |
| CN103558943B (en) * | 2013-11-08 | 2016-08-17 | 科大讯飞股份有限公司 | Realize the method and system of multi-modal synchronization input |
| CN103558943A (en) * | 2013-11-08 | 2014-02-05 | 安徽科大讯飞信息科技股份有限公司 | Method and system for realizing multi-mode synchronous input |
| CN104679224B (en) * | 2013-11-30 | 2018-03-20 | 富泰华工业（深圳）有限公司 | Input equipment and input management system |
| CN104679224A (en) * | 2013-11-30 | 2015-06-03 | 富泰华工业（深圳）有限公司 | Input device and input management system |
| CN104793727A (en) * | 2014-01-21 | 2015-07-22 | 安徽科大讯飞信息科技股份有限公司 | Method and system for achieving individual multi-mode input |
| CN104793727B (en) * | 2014-01-21 | 2017-08-25 | 科大讯飞股份有限公司 | Realize the method and system of personalized multi-mode input |
| CN104076945B (en) * | 2014-07-10 | 2017-10-10 | 广州三星通信技术研究有限公司 | Apparatus and method for showing input keyboard in the terminal |
| CN108700996B (en) * | 2016-02-23 | 2021-08-31 | 迈思慧公司 | System and method for multiple input management |
| CN108700996A (en) * | 2016-02-23 | 2018-10-23 | 迈思慧公司 | System and method for multi input management |
| KR20180115699A (en) * | 2016-02-23 | 2018-10-23 | 마이스크립트 | System and method for multi-input management |
| KR102402397B1 (en) | 2016-02-23 | 2022-05-25 | 마이스크립트 | Systems and Methods for Multi-Input Management |
| JP2019512765A (en) * | 2016-02-23 | 2019-05-16 | マイスクリプト | System and method for multiple input management |
| WO2017144171A1 (en) * | 2016-02-23 | 2017-08-31 | Myscript | System and method for multiple input management |
| CN106484181A (en) * | 2016-09-20 | 2017-03-08 | 青岛海信电器股份有限公司 | The touch-responsive method and device of infrared touch panel |
| CN107256124B (en) * | 2017-04-21 | 2023-01-10 | 海信视像科技股份有限公司 | Electronic whiteboard touch control method and device |
| CN107256124A (en) * | 2017-04-21 | 2017-10-17 | 青岛海信电器股份有限公司 | A kind of electronic whiteboard touch control method and device |
| CN109213412A (en) * | 2017-07-03 | 2019-01-15 | 北京搜狗科技发展有限公司 | Input method, device and machine readable media |
| CN108182000A (en) * | 2017-12-25 | 2018-06-19 | 科大讯飞股份有限公司 | Input through keyboard detection method and device, storage medium, electronic equipment |
| US11461507B2 (en) * | 2018-10-30 | 2022-10-04 | Third Block Gear | Systems and methods for secure peripherals |
| CN111124222B (en) * | 2019-12-03 | 2022-02-01 | 科大讯飞股份有限公司 | Input switching method and device, electronic equipment and storage medium |
| CN111124222A (en) * | 2019-12-03 | 2020-05-08 | 科大讯飞股份有限公司 | Input switching method and device, electronic equipment and storage medium |
| CN112633243A (en) * | 2020-12-31 | 2021-04-09 | 安徽鸿程光电有限公司 | Information identification method, device, equipment and computer storage medium |
| CN112633243B (en) * | 2020-12-31 | 2023-01-03 | 安徽鸿程光电有限公司 | Information identification method, device, equipment and computer storage medium |
| WO2023030377A1 (en) * | 2021-08-31 | 2023-03-09 | 华为技术有限公司 | Writing/drawing content display method and related device |
| WO2023124141A1 (en) * | 2021-12-27 | 2023-07-06 | 荣耀终端有限公司 | Input method calling method and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102193736B (en) | 2013-06-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102193736B (en) | Input method and system supporting multimode automatic switching | |
| US20210406578A1 (en) | Handwriting-based predictive population of partial virtual keyboards | |
| US9323456B2 (en) | Multi-character continuous handwriting input method | |
| US10373009B2 (en) | Character recognition and character input apparatus using touch screen and method thereof | |
| CN109614845B (en) | Managing real-time handwriting recognition | |
| EP2570901A1 (en) | Method and mobile terminal for automatically recognizing gesture | |
| US8713464B2 (en) | System and method for text input with a multi-touch screen | |
| US20120110518A1 (en) | Translation of directional input to gesture | |
| CN1777858A (en) | Unambiguous text input method for touch screens and reduced keyboard systems | |
| CN102184074B (en) | Keyboard, automatic hand input switching method and device and mobile terminal | |
| CN101581992A (en) | Touch screen device and input method thereof | |
| CN100561414C (en) | A kind of portable terminal hand-written inputting method, device and portable terminal | |
| US9170734B2 (en) | Multiple-input handwriting recognition system and measure thereof | |
| WO2004097722A1 (en) | Hand-written character input device and hand-written character input processing method | |
| CN103299254A (en) | Method, apparatus, and computer program product for overlapped handwriting | |
| EP1513053A2 (en) | Apparatus and method for character recognition | |
| CN103294175A (en) | Electronic device and method for electronic device to automatically switch input modes | |
| CN102455887A (en) | Input display apparatus and input display method | |
| CN103150111A (en) | Symbol inputting method, device and terminal | |
| CN103150114B (en) | A kind of convenient input method for touch screen | |
| CN102109960A (en) | Fast Chinese-character pinyin input method based on touch sensing device as well as system for realizing same | |
| CN104898855B (en) | Based on text input system and method with rocking bar equipment | |
| CN100432901C (en) | Mobile terminal having keyboard and hand-write synergic input function | |
| CN105095924A (en) | Handwriting recognition method and device | |
| CN110858291A (en) | Character segmentation method and device |
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 | ||
| C56 | Change in the name or address of the patentee |
Owner name: IFLYTEK CO., LTD. Free format text: FORMER NAME: ANHUI USTC IFLYTEK CO., LTD. |
|
| CP03 | Change of name, title or address |
Address after: Wangjiang Road high tech Development Zone Hefei city Anhui province 230088 No. 666 Patentee after: Iflytek Co., Ltd. Address before: 230088 No. 616, Mount Huangshan Road, hi tech Development Zone, Anhui, Hefei Patentee before: Anhui USTC iFLYTEK Co., Ltd. |