CN103019397B - A kind of line of text input method of multilingual mixing and device - Google Patents
A kind of line of text input method of multilingual mixing and device Download PDFInfo
- Publication number
- CN103019397B CN103019397B CN201110279794.6A CN201110279794A CN103019397B CN 103019397 B CN103019397 B CN 103019397B CN 201110279794 A CN201110279794 A CN 201110279794A CN 103019397 B CN103019397 B CN 103019397B
- Authority
- CN
- China
- Prior art keywords
- input
- character
- identification engine
- engine
- identification
- 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.)
- Active
Links
Landscapes
- Character Discrimination (AREA)
Abstract
The line of text input method of a kind of multilingual mixing of the present invention and device, belong to input method field.Described input method comprises: call the input person's handwriting of preset at least macaronic identification engine to the current character gathered and identify, obtain recognition result; At least two character input areas are set, and the identification engine of the different language classification of at least two character input area difference correspondences described in arranging according to the recognition result obtained; Gather the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result.By method of the present invention, according to the recognition result of the character of user's input, provide the input area that different identification engines is corresponding, corresponding identification engine can be called rapidly identify the character script inputted in this input area, draw recognition result, do not need manually frequently to switch identifiable language, facilitate user, improve input efficiency.
Description
Technical field
The present invention relates to input method field, relate to a kind of multiple language input-system, the line of text input method of particularly a kind of multilingual mixing and device.
Background technology
In existing most of input method, all need to provide a corresponding language input system to the input of each language.Such as, the Chinese that existing input method all exists and English input, when needs input Chinese, switch to the state of input in Chinese; When needs input is English, namely switch to the state of English input.Therefore, when inputting multiple different language wherein a kind of, need repeatedly between different input languages, carry out correct switching and use.
But also have and do not need people to be the multiple language input-system of the switching carrying out target language, correspond to multilingual input system as the application number patent file that is CN98109769 just proposes one.This multi-language system is the font information and format information that arrange according to application program, or identifies target language by the information of the ambient As function setting in multiple language input-system.When the target language inputted is Japanese, system uses Japanese processing section to perform Japanese input processing.When the target language inputted is English, system makes processing section in English perform English input processing.When target language is Chinese, system uses Chinese processing part to perform the input processing of Chinese.
Visible, at least there is following defect in multilingual short sentence input of the prior art: for each line of text of input, system can only provide a kind of identification candidate of language, when needing the line of text of an input multilingual mixing, need manually frequently to switch between different language input language, user uses inconvenience.
Summary of the invention
In order to solve input multilingual mixing line of text in need user's manual switchover input language to bring to user inconvenience, the invention provides a kind of line of text input method and device of multilingual mixing, can input in the process of the line of text of multilingual mixing user, the language classification of the text of automatic decision user input, thus provide correct line of text recognition result, and do not need user manually to switch the input language classification of text.
The line of text input method of a kind of multilingual mixing provided by the invention, comprising: call the input person's handwriting of preset at least macaronic identification engine to the current character gathered and identify, obtain recognition result; At least two character input areas are set, and the identification engine of the different language classification of at least two character input area difference correspondences described in arranging according to the recognition result obtained; Gather the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result.
Further, described method also comprises: after determining line of text end of input, obtains the recognition result of the line of text inputted, and show according to the recognition result of the character script of each input and the language model set up in advance.
On the other hand, the line of text input media of a kind of multilingual mixing provided by the invention, comprising:
Initial identification module, identifying for calling the input person's handwriting of preset at least macaronic identification engine to the single character gathered, obtaining recognition result;
Input area arranges module, for arranging at least two character input areas, and the identification engine of at least two corresponding different language classifications of character input area difference described in arranging according to the recognition result obtained;
Judge identification module, for gathering the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result.
The line of text input method of a kind of multilingual mixing provided by the invention and device, according to the recognition result of the character of user's input, adopt nearby principle, at least two input areas are set, the speech recognition engine that different input areas is corresponding different, user inputs in corresponding input area, can call the character script of corresponding identification engine to input fast and identify, and draw recognition result.Both ensure the accuracy of the line of text identification of multilingual mixing, do not need again the language classification of user's manual switchover input text in the process of the line of text of the multilingual mixing of input, convenient for users to use, improve input efficiency.
Accompanying drawing explanation
Fig. 1 shows the multilingual mixing line of text input method process flow diagram of one embodiment of the present of invention;
Fig. 2 shows the multilingual mixing line of text input method inputting interface schematic diagram of one embodiment of the present of invention;
Fig. 3 shows the multilingual mixing line of text input method process flow diagram of an alternative embodiment of the invention;
Fig. 4 shows the schematic diagram of the inputting interface handwriting input character shown in Fig. 2;
Fig. 5 shows the input position prompting frame schematic diagram that the inputting interface shown in Fig. 4 provides;
Fig. 6 shows the schematic diagram of proximal most position place input in the input position prompting frame provided at Fig. 5;
Fig. 7 shows the input position prompting frame schematic diagram that the inputting interface shown in Fig. 6 provides;
Fig. 8 shows the schematic diagram of highest distance position place input in the input position prompting frame provided at Fig. 7;
Fig. 9 shows the schematic diagram that the inputting interface short sentence end of input provided at Fig. 8 provides recognition result;
Figure 10 shows the multilingual mixing line of text input device structure figure of another embodiment of the present invention.
Embodiment
One of the present invention multilingual mixing line of text input method process flow diagram, as shown in Figure 1, comprising: call the input person's handwriting of preset at least macaronic identification engine to the current character gathered and identify, obtain recognition result; At least two character input areas are set, and the identification engine of the different language classification of at least two character input area difference correspondences described in arranging according to the recognition result obtained; Gather the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result.By method of the present invention, according to the recognition result of the character of user's input, provide the input area that different identification engines is corresponding, user inputs in corresponding input area, the character of corresponding identification engine to input can be called rapidly identify, and draw recognition result, facilitate user, improve input efficiency.
The identification engine of preset language of the present invention at least comprises two kinds, as long as the character of preset several language has obvious difference in written handwriting feature, when carrying out multilingual line of text input, just can using the identification engine of this several language as preset speech recognition engine, adopt method disclosed by the invention, realize the input of the line of text of this several language mixing.The identification engine of preset language of the present invention is preferably two kinds, one is Chinese characters identification engine, another kind is western language character recognition engine, as: Chinese identification engine and English identification engine, Chinese identification engine and French identification engine, Korean identify engine and English identification engine, Japanese OCR engine and English identification engine etc.
Below by specific embodiment, content of the present invention is described in further detail, but the present invention is not restricted to this.
In the electronic equipment (as computer, mobile phone etc.) with line of text input function, first display device is needed, described display device shows inputting interface, and the inputting interface of embodiments of the invention comprises: person's handwriting input field 23, identification candidate regions 22 and text editing district 21.Wherein, person's handwriting input field 23 is available to the region that user carries out handwriting input, and user can carry out hand-written by contactor control device by mouse, pointer or finger etc. in this region, input character person's handwriting; Identify that candidate regions 22 is that after identifying that engine identifies for the character script that user inputs, the recognition result obtained is carried out the region shown according to score order from high to low, user can select the identification candidate in this region.The identification candidate that user selects can be sent to this editing area 21 by this electronic equipment; Text editing district 21 is the positions of the target candidate display that user selects.
embodiment 1
In the present embodiment, for preset macaronic identification engine: one is that Chinese identifies engine, another kind is English identification engine, describing preset bilingual identification engine, being called by this bilingual identification engine respectively to distinguish: first identifies that engine, second identifies engine.In the present embodiment, Chinese identifies that engine is the first identification engine, and English identification engine is the second identification engine.Accordingly, first identify that the language classification that engine is corresponding is that first language, second identifies that the language classification that engine is corresponding is second language.Be appreciated that and also English can be identified that engine is the first identification engine, Chinese identifies that engine is the second identification engine, and the present invention is not construed as limiting this.
The one that the present embodiment provides multilingual mixing line of text input method, as shown in Figure 3, comprises following step.
Step 31, calls the input person's handwriting of preset macaronic identification engine to the character gathered and identifies, obtain recognition result.
First, the character script information of Gather and input, and show.As shown in Figure 4, user inputs illustrated content (person's handwriting of " you ") in the person's handwriting input field 23 of the inputting interface of electronic equipment, and electronic equipment gathers the character script of user's input, and shows.After character script end of input being detected, such as detect that the mouse-up time exceedes default character input time, think current character end of input.Electronic equipment calls the input person's handwriting of preset bilingual identification engine to the character gathered and identifies, obtains recognition result.In the present embodiment, preset bilingual identification engine is respectively the first identification engine (Chinese identifies engine) and second and identifies engine (English identification engine), electronic equipment calls described two preset identification engines respectively and identifies the character script information gathered, obtain two groups of recognition results, wherein, described recognition result comprises the score identifying candidate characters and this candidate characters, identify engine flag, described identification candidate characters is according to score order arrangement from high to low, score is higher, illustrate that the person's handwriting of input is that the confidence level of the person's handwriting of this candidate characters is higher.Carry out identifying that the recognition result obtained comprises as called the first identification engine: (" you ", 99.5,1), (" still ", 98.0,1), (" but ", 97.0,1) Call the second identification engine to carry out identifying that the recognition result obtained comprises: (" tip ", 0.15,2), (" Job ", 0.20,2), (" Jod ", 0.09,2) ...Wherein, " you " and " tip " etc. are for identifying candidate characters; 99.5 and 0.15 is score corresponding to " you " and " tip "; 1 represents the first identification engine, and 2 represent the second identification engine.
Step 32, preserves the recognition result obtained, determines the identification engine of the correspondence of the character of current input according to recognition result.
Because the score range of the recognition result of two different language identification engines may be different, after the recognition result obtaining two different identification engines respectively, need the Score Normalization obtaining the identification of two identification engines to identify candidate characters, and the identification candidate characters obtained is arranged according to score order from high to low, obtain and identify candidate character list.And this identification candidate character list is temporarily preserved.Electronic equipment determines that according to the mark of corresponding identification engine the language classification of the candidate word ranked the first in the identification candidate character list obtained is Chinese or English, and determines that the language classification of candidate word is the language classification of the character of current input.By judging the identification engine identification of character, be easy to obtain to identify that the identification engine that character in candidate character list is corresponding is that the first identification engine or second identifies engine (namely Chinese identifies engine or English identification engine), the present embodiment is not repeated herein.When identifying that the score of at least the first two candidate characters in candidate character list has exceeded the score threshold preset, and identification engine corresponding to described at least the first two candidate characters different time, determine the identification engine of identification engine as the character of current input of the default language classification that electronic equipment is arranged.Input content as shown in Figure 4, electronic equipment determines that identification engine that the character of current input is corresponding is for being the first identification engine (namely Chinese identifies engine).Described default score threshold is determined according to the recognition training result of different engine.
Step 33, arranges two character input areas, and the identification engine corresponding according to the character of current input arranges identification engine corresponding to described two character input areas.
Conveniently user inputs fast and identifies, the present invention is around the character of current input, next-door neighbour's current character, set gradually at least two character input areas, described at least two character input areas can horizontally or vertically arrange, and the mapping relations of identification engine corresponding at least two character input areas described in pre-setting and the corresponding identification engine of current input character.Preferably, along the direction of line of text input, at least two character input areas are set gradually.When line of text inputs to the right in the horizontal direction, described setting at least two character input areas set gradually to the right along the right side of the character of current input; When line of text vertically inputs downwards, described setting at least two character input areas set gradually downwards along the below of the character of current input.Also can work as line of text when inputting in the horizontal direction to the right, described setting at least two character input areas are arranged along the right vertical of the character of current input.
In the present embodiment, because preset macaronic identification engine is respectively Chinese and identifies engine (first identifies engine) and English identification engine (second identifies engine), namely the present embodiment is applicable to Chinese and the input of English mixing line of text, according to Chinese with English line of text writing style---level is write from left to right, the character being close to current input on the right side of the character of current input arranges two adjacent character input areas.The present embodiment indicates the position of two character input areas with dashed rectangle, as shown in Figure 5.The quantity of the present invention to character input area is not construed as limiting, but the quantity of character input area should be corresponding with the quantity of preset identification engine.The form of expression of the present invention to character input area is also not construed as limiting, and can be dotted line frame, can also be underscore, bracket, different colours block etc., as long as can enough distinguish multilingual to write region.The position relationship of two character input areas of described setting and the character of current input can set arbitrarily, as horizontally or vertically arranged, can level arrange to the right, also can arrange straight down, can adjacent (as shown in this embodiment), also can non-conterminous (as a character input area on the right side of the character of current input, a character input area is above the character of current input).Preferably, described two character input areas are horizontal on the adjacent right side of the character of current input.
According to the position of the character of current input and the size of input area, obtain and record the position of input area.For the interface shown in Fig. 5, the coordinate arranging the leftmost side, person's handwriting input field 23 is x=0, and rightmost side coordinate is x=240, and in the person's handwriting coordinate of the first character of input, horizontal ordinate maximal value is x
1=40, the original width arranging character input area is W
1=50, interval W between horizontal character input area
2=5, be then close to the input area i.e. horizontal ordinate scope of the first input area of an input character for (40,90), on interval, the input area of an input character i.e. horizontal ordinate scope of the second input area is (100,150).In order to arrange the convenience of input area, between adjacent input area, interval can be there is no.
It is the first identification engine (i.e. Chinese identify engine) based on the identification engine that the character of the current input determined in the step 32 is corresponding, in this step, corresponding according to the character of current input identification engine arranges identification engine corresponding to described two character input areas.According to nearby principle, arranging identification engine corresponding to the input area adjacent with the character of current input is the identification engine that the character of current input is corresponding; The speech recognition engine corresponding with the input area of the character pitch of current input is set and identifies engine for another.In the present embodiment, arranging speech recognition engine corresponding to the input area adjacent with the character of current input is the first identification engine (namely Chinese identifies engine), calls the character script that the first identification engine is identified in input in this region; Arranging the speech recognition engine corresponding with the input area of the character pitch of current input is the second identification engine (namely English identifies engine), calls the character script that the second identification engine is identified in input in this region.When at least two the character input areas arranged are arranged along the right vertical of the character of current input, the corresponding relation of the identification engine of the character of input area and current input can be set arbitrarily in advance, as be arranged in current input character on the right side of identification engine corresponding to the input area of the top identification engine corresponding with the character of current input identical.
Preferably, the described change according to written handwriting, can adjust size and the position of input area accordingly.As in the input area adjacent with the character of current input during input character person's handwriting, when the position of last sampled point of character script of input and the distance of the frame of input area are less than default threshold value, the adjustment away from current character position can be made in the position of this frame, as as described in input area can automatically widen, what the position of another input area adjacent to this region can be corresponding moves to the direction away from current character.
Step 34, the character script of Gather and input, the character input area residing for described character script, calls corresponding identification engine and identifies the character script gathered, obtain recognition result.
At inputting interface as shown in Figure 5, user can proceed input.As shown in Figure 6, when continuing input character in the input area of user's character of an input on being close to, the character script of electronic equipment Gather and input, and according to the position of described character script and input area, determine the character input area residing for described character script.Determine that the concrete grammar of the character input area residing for described character script has a variety of, such as: the input area be in using the starting point coordinate of character script as current input character residing for input area.As shown in Figure 6, user is input character person's handwriting on an electronic device, and the horizontal ordinate of the starting point of the character script collected when electronic equipment is 60, time within the scope of the horizontal ordinate of the first input area, determines that the character of current input is in the first input area.Or, determine according to the coordinate figure scope of the person's handwriting point of this character and the coordinate figure overlapping ranges degree of input area the input area that the character of current input is in.As shown in Figure 6, the degree of overlapping of the scope of the horizontal ordinate of the character of input and the horizontal ordinate of the first input area is greater than the degree of overlapping with the horizontal ordinate of the second input area, therefore, determines that the character of current input is in the first input area.Judge that the method for the input area residing for character of current input is a lot, will not enumerate at this.
After determining that the character of current input is in the first input area, call the character script of character recognition engine corresponding to the first input area to the current input gathered will identify, obtain the recognition result of the character of current input: comprise and identify candidate characters and the score corresponding with each identification candidate characters and identify engine flag.In this example, call the character script of Chinese identification engine corresponding to the first input area to input and identify, the candidate characters obtained, as " very ".
Step 35, preserves the language classification of the character of recognition result and the current input obtained.
Character input area residing for described character script, determine the identification engine that the character of current input is corresponding, the recognition result of the character of current input preserved by electronic equipment, and the identification engine that the character of current input is corresponding.In the present embodiment, because determine in step 34 that the character of current input is in the first input area, therefore preserve the identification engine that this input area is corresponding, namely first identifying engine (Chinese identifies engine), is the identification engine of the correspondence of the character of current input.
Repeated execution of steps 33 to step 35, user can proceed line of text input.User is after input " very ", electronic equipment performs step 33, on " very " right side, two adjacent input areas are set, and to arrange identification engine corresponding to first input area adjacent with the character " very " of current input be Chinesely identify engine, the identification engine corresponding with second input area at character " very " interval of current input is that English identifies engine, and inputting interface as shown in Figure 7.Whether electronic equipment judges to input in interval time at the character preset, still have character script to input, if do not had, then thinks and line of text end of input performs step 36; If had, then perform step 34.
If user needs input second language (namely English), then and the second input area input character person's handwriting at character " very " interval of current input, as shown in Figure 8, the person's handwriting of what user inputted is English word " nice ".In step 34, the character script of Gather and input, the character input area residing for described character script, call corresponding identification engine i.e. English identification engine and identify the character script gathered, acquisition recognition result, as " nice ".
Step 36, obtains and the recognition result of display text lines.
When electronic equipment judges, within character input interval time of presetting, when not having character script to input, then to think line of text end of input.The described character preset input sets, as required as 1 second interval time.The described character preset input is greater than the interval time of each of input character interval time.After determining line of text end of input, the recognition result of the character script that electronic equipment inputs according to each and the language model set up in advance obtain the recognition result of the line of text of input, and show.Wherein, the recognition result of the character script of each input obtains in step 31 and step 34.The detailed process obtaining the recognition result of the line of text of input is as follows: each of the first identification candidate of the first character of input and second character of input identifies that candidate sets up combination to be verified respectively, then inquires about the combined probability of the combination to be verified of setting up by the language model set up in advance; And then select combined probability to exceed the combination specified number of default probability threshold value, set up combination to be verified with the identification candidate of the 3rd character of input, then inquire about the combined probability of the combination to be verified of setting up by the language model set up in advance.By that analogy, the candidate result of multiple combination is obtained.In identification candidate regions 22, the recognition result of the line of text of the multilingual mixing of input is shown according to the combined probability order from big to small of the candidate result of multiple combinations of described acquisition.Said " char " refers to the symbol that an input person's handwriting is corresponding herein, and its recognition result can be an English word or Chinese phrase, depends on the corresponding recognition result that engine provides that identifies.
By the line of text input method of multilingual mixing provided by the invention, by method of the present invention, according to the recognition result of the character of user's input, adopt nearby principle, at least two input areas are set, the speech recognition engine that different input areas is corresponding different, user inputs in corresponding input area, can call the character of corresponding identification engine to input fast and identify, and draw recognition result, facilitate user, improve input efficiency.
embodiment 2
On the other hand, the invention provides a kind of line of text input media of multilingual mixing, as shown in Figure 10, this device comprises:
Initial identification module 101, identifying for calling the input person's handwriting of preset at least macaronic identification engine to the single character gathered, obtaining recognition result;
Input area arranges module 102, for arranging at least two character input areas, and the identification engine of at least two corresponding different language classifications of character input area difference described in arranging according to the recognition result obtained;
Judge identification module 103, for gathering the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result.
Wherein, described initial identification module 101 specifically for the character script information of Gather and input, and shows; After character script end of input being detected, electronic equipment calls preset bilingual identification engine and identifies the input person's handwriting of the character gathered respectively, obtains recognition result.In the present embodiment, preset bilingual identification engine is respectively the first identification engine (Chinese identifies engine) and second and identifies engine (English identification engine), electronic equipment calls described two preset identification engines respectively and identifies the character script information gathered, obtain two groups of recognition results, wherein, described recognition result comprises the score identifying candidate characters and this candidate characters, described identification candidate characters is according to score order arrangement from high to low, score is higher, illustrates that the person's handwriting of input is that the confidence level of the person's handwriting of this candidate characters is higher.
Described input area arranges module 102 and comprises further: position setting unit and identification engine setting unit.Wherein, described position setting unit to be used for around the character of current input and along the direction of line of text input, at least two input areas described in the character being close to current input sets gradually.Be specially according to other writing style of preset class of languages, at least two character input areas are set, the quantity of described input area is corresponding with the kind of preset identification engine, the form of expression of described input area, and the position relationship of the character of input area and current input is with the description of step 34 in the embodiment of the present invention 1.Described identification engine setting unit is for the mapping relations of speech recognition engine that at least two input areas described in pre-setting the are corresponding identification engine corresponding with the character of current input; Comprise, according to the language classification of the character of current input, speech recognition engine corresponding to described two character input areas is set, according to nearby principle, arranging identification engine corresponding to the input area adjacent with the character of current input is identification engine corresponding to the language classification of the character of current input; Arranging the speech recognition engine corresponding with the input area of the character pitch of current input is speech recognition engine corresponding to another language classification.In the present embodiment, arranging speech recognition engine corresponding to the input area adjacent with the character of current input is the first identification engine (namely Chinese identifies engine), calls the character script that the first identification engine is identified in input in this region; Arranging the speech recognition engine corresponding with the input area of the character pitch of current input is the second identification engine (namely English identifies engine), calls the character script that the second identification engine is identified in input in this region.
Described judgement identification module 103 comprises further: person's handwriting collecting unit, region decision unit and recognition unit.Described person's handwriting collecting unit is for gathering the character script of user's input.Described region decision unit is used for the position according to described character script and input area, determines the character input area residing for described character script.Determine that the concrete grammar of the character input area residing for described character script has a variety of, specifically see the step 34 of the embodiment of the present invention 1, can will not enumerate at this.Described recognition unit will identify for calling the character script of identification engine corresponding to the input area determined to the current input gathered, and obtain the recognition result of the character of current input: comprise identification candidate characters and the score corresponding with each identification candidate characters.In this example, call the character script of Chinese identification engine corresponding to the first input area to input and identify, the candidate characters obtained, as " very ".After acquisition recognition result, electronic equipment can preserve the language classification of the recognition result of the character of current input and the character with current input, to continue to arrange input area.
Described input media also comprises and obtains display module 104, for when determining line of text end of input after, according to the recognition result of line of text that the recognition result of the character script of each input and the language model acquisition of setting up in advance input, and shows.Concrete acquisition process is see the step 36 of the embodiment of the present invention 1.
By the device that the embodiment of the present invention provides, according to the recognition result of the character of user's input, provide the input area that different identification engines is corresponding, user inputs in corresponding input area, the character of corresponding identification engine to input can be called rapidly identify, and draw recognition result, facilitate user, improve input efficiency.
Embodiments of the invention also disclose a kind of electronic equipment, comprise contactor control device, display device, also comprise the line of text input media of a kind of multilingual mixing described in embodiment 2.
Although invention has been described above in conjunction with the embodiments, to those skilled in the art, be understandable that, above-described embodiment only for example purposes, should not think the protection domain limiting the present invention with this.Protection scope of the present invention is only limited by claim.Although in above-mentioned explanation, for ease of understanding, succession be have employed to the step of method and describe, it should be pointed out that the order for above-mentioned steps does not do strict restriction.In addition, all or part of step realized in above-described embodiment method is that the hardware that can carry out instruction relevant by program has come, and this program can be stored in a computer read/write memory medium, as: ROM/RAM, magnetic disc, CD etc.Further, accompanying drawing or the apparatus structure shown in embodiment are only schematically show logical organization.Module wherein as separating component display may or may not be physically separate, and the parts as module display also may be or may not be physical modules.
In addition, in detail in the claims, term " comprises " and does not get rid of other parts of existence or step.In addition, although include each feature in different claims, these features can be advantageously combined, and each feature comprises in different claims and do not mean that the combination of these features is infeasible and/or disadvantageous.In addition, single implication is not got rid of multiple.Therefore, the implication of " " etc. is not got rid of multiple.
In addition, those skilled in the art can modify to it, change or replace under the prerequisite not departing from spirit of the present invention, but the various equivalent variations done according to the present invention, still belong to the scope that the present invention is contained.
Claims (10)
1. a line of text input method for multilingual mixing, is characterized in that, comprising:
Call the input person's handwriting of preset at least macaronic identification engine to the current character gathered to identify, obtain recognition result;
At least two character input areas are set, and the identification engine of the different language classification of at least two character input area difference correspondences described in arranging according to the recognition result obtained;
Gather the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result;
Wherein, described recognition result comprises identification candidate characters, and score corresponding to described identification candidate characters and identify engine flag; Described in the described recognition result according to obtaining is arranged, the identification engine of the different language classification that at least two character input areas are corresponding is respectively specially:
The identification candidate characters obtained is arranged according to score order from high to low, obtains and identify candidate character list;
According to the identification engine flag of candidate characters, determine the identification engine that in the identification candidate character list obtained, the candidate characters that ranks the first is corresponding, and determine that this identification engine is the identification engine that the character of current input is corresponding;
Arranging identification engine corresponding to the input area adjacent with the character of current input is the identification engine that the character of current input is corresponding; The speech recognition engine corresponding with the input area of the character pitch of current input is set and identifies engine for another.
2. input method according to claim 1, it is characterized in that, also comprise: after determining line of text end of input, obtain the recognition result of the line of text inputted according to the recognition result of the character script of each input and the language model set up in advance, and show.
3. input method according to claim 1, it is characterized in that, described at least two character input areas are around the character of current input, the character being close to current input sets gradually, and the mapping relations of identification engine corresponding at least two character input areas described in the pre-setting identification engine corresponding with the character of current input.
4. input method according to claim 1, is characterized in that, described preset at least macaronic identification engine comprises: Chinese characters identification engine and western language identification engine, and the character input area of setting is two,
Wherein, described Chinese characters identification engine comprises: Chinese identifies engine, Japanese OCR engine, Korean identifies engine; Described western language identification engine comprises: English identification engine.
5. the input method according to claim 1 or 3, is characterized in that, described character input area is two, and the right side of character in current input, the character level being close to current input sets gradually to the right.
6. input method according to claim 1, is characterized in that, the form of expression of described character input area comprises: dotted line frame, underscore, bracket, different colours block.
7. a line of text input media for multilingual mixing, is characterized in that, comprising:
Initial identification module, identifying for calling the input person's handwriting of preset at least macaronic identification engine to the single character gathered, obtaining recognition result;
Input area arranges module, for arranging at least two character input areas, and the identification engine of at least two corresponding different language classifications of character input area difference described in arranging according to the recognition result obtained;
Judge identification module, for gathering the input person's handwriting of character, according to the input area residing for described input person's handwriting, the identification engine calling corresponding language identifies described input person's handwriting, and obtains recognition result;
Described in the described recognition result according to obtaining is arranged, the identification engine of the different language classification that at least two character input areas are corresponding is respectively specially:
The identification candidate characters obtained is arranged according to score order from high to low, obtains and identify candidate character list;
According to the identification engine flag of candidate characters, determine the identification engine that in the identification candidate character list obtained, the candidate characters that ranks the first is corresponding, and determine that this identification engine is the identification engine that the character of current input is corresponding;
Arranging identification engine corresponding to the input area adjacent with the character of current input is the identification engine that the character of current input is corresponding; The speech recognition engine corresponding with the input area of the character pitch of current input is set and identifies engine for another.
8. input media according to claim 7, is characterized in that, described input area arranges module and comprises further: position setting unit and identification engine setting unit,
Wherein, at least two character input areas described in the character that described position setting unit is used for being close to current input around the character of current input sets gradually;
Described identification engine setting unit is for the mapping relations of speech recognition engine that at least two character input areas described in pre-setting the are corresponding identification engine corresponding with the character of current input; Comprise, the identification engine corresponding according to the character of current input arranges speech recognition engine corresponding to described two character input areas, comprising: arranging identification engine corresponding to the input area adjacent with the character of current input is identification engine corresponding to the language classification of the character of current input.
9. input media according to claim 7, it is characterized in that, also comprise: obtain display module, described acquisition display module is used for after determining line of text end of input, obtain the recognition result of the line of text inputted according to the recognition result of the character script of each input and the language model set up in advance, and show.
10. an electronic equipment, comprises contactor control device, display device, it is characterized in that, also comprises the line of text input media of a kind of multilingual mixing as described in any one of claim 7 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110279794.6A CN103019397B (en) | 2011-09-20 | 2011-09-20 | A kind of line of text input method of multilingual mixing and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110279794.6A CN103019397B (en) | 2011-09-20 | 2011-09-20 | A kind of line of text input method of multilingual mixing and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103019397A CN103019397A (en) | 2013-04-03 |
| CN103019397B true CN103019397B (en) | 2015-11-25 |
Family
ID=47968080
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110279794.6A Active CN103019397B (en) | 2011-09-20 | 2011-09-20 | A kind of line of text input method of multilingual mixing and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103019397B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103488488A (en) * | 2013-09-26 | 2014-01-01 | 贝壳网际（北京）安全技术有限公司 | Text input check method, device ad mobile terminal |
| TWI511030B (en) * | 2014-04-15 | 2015-12-01 | Acer Inc | Method for user interface display and electronic device using the same |
| CN104951100A (en) * | 2015-06-23 | 2015-09-30 | 小米科技有限责任公司 | Character input method and device |
| CN106940596A (en) * | 2016-01-04 | 2017-07-11 | 北京峰盛博远科技股份有限公司 | A kind of recognition methods of multiple characters of handwriting input and system |
| CN110858317B (en) * | 2018-08-24 | 2024-06-14 | 北京搜狗科技发展有限公司 | Handwriting recognition method and device |
| CN117251061B (en) * | 2023-11-17 | 2024-03-15 | 广东省电信规划设计院有限公司 | AIGC-based on-screen intelligent input method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1203398A (en) * | 1997-06-11 | 1998-12-30 | 株式会社东芝 | Multiple language input-system |
| CN101515211A (en) * | 2008-02-22 | 2009-08-26 | 汉王科技股份有限公司 | Handwriting input method, device and user terminal |
| CN101882025A (en) * | 2010-06-29 | 2010-11-10 | 汉王科技股份有限公司 | Hand input method and system |
| CN102103434A (en) * | 2011-03-09 | 2011-06-22 | 王岩泽 | Handwriting input device and method for characters |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102934417B (en) * | 2010-02-19 | 2016-01-06 | 禹舜朝 | Multilingual key input apparatus and method thereof |
-
2011
- 2011-09-20 CN CN201110279794.6A patent/CN103019397B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1203398A (en) * | 1997-06-11 | 1998-12-30 | 株式会社东芝 | Multiple language input-system |
| CN101515211A (en) * | 2008-02-22 | 2009-08-26 | 汉王科技股份有限公司 | Handwriting input method, device and user terminal |
| CN101882025A (en) * | 2010-06-29 | 2010-11-10 | 汉王科技股份有限公司 | Hand input method and system |
| CN102103434A (en) * | 2011-03-09 | 2011-06-22 | 王岩泽 | Handwriting input device and method for characters |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103019397A (en) | 2013-04-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103019397B (en) | A kind of line of text input method of multilingual mixing and device | |
| CN102855082B (en) | Character recognition for overlay text user input | |
| RU2417399C2 (en) | Gesture-based document editor | |
| US10909308B2 (en) | Information processing apparatus, information processing method, and program | |
| US9323456B2 (en) | Multi-character continuous handwriting input method | |
| US20140143721A1 (en) | Information processing device, information processing method, and computer program product | |
| CN100587660C (en) | Method and device for forecasting and discriminating hand-written characters | |
| CN102629158B (en) | Character input method and device on basis of touch screen system | |
| CN101576783B (en) | User interface, equipment and method for hand input | |
| CN102135838A (en) | Method and system for partitioned input of handwritten character string | |
| JP6426417B2 (en) | Electronic device, method and program | |
| EP2897055A1 (en) | Information processing device, information processing method, and program | |
| CN102063620A (en) | Handwriting identification method, system and terminal | |
| CN103092343A (en) | Control method based on camera and mobile terminal | |
| CN102455911A (en) | Handwriting input and display device and control method | |
| CN106227449A (en) | Input control method based on sense of touch vision technique and system | |
| KR101927064B1 (en) | Apparus and method for generating summary data about e-book | |
| CN101673408B (en) | Method and device for embedding character information in shape recognition result | |
| CN111340020A (en) | Formula identification method, device, equipment and storage medium | |
| CN102981693B (en) | A kind of multilingual hand-written inputting method and device | |
| CN102243708B (en) | Handwriting recognition method, handwriting recognition system and handwriting recognition terminal | |
| CN108062301B (en) | Character translation method and device | |
| CN107209640B (en) | Text deletion based on input mode | |
| CN101882025A (en) | Hand input method and system | |
| CN104731766A (en) | Alphabetic writing lexicon establishing method, alphabetic writing lexicon establishing device, inputting method and inputting system |
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 |