CN105843414B - Input method input correction method and input method device - Google Patents
Input method input correction method and input method device Download PDFInfo
- Publication number
- CN105843414B CN105843414B CN201510016736.2A CN201510016736A CN105843414B CN 105843414 B CN105843414 B CN 105843414B CN 201510016736 A CN201510016736 A CN 201510016736A CN 105843414 B CN105843414 B CN 105843414B
- Authority
- CN
- China
- Prior art keywords
- character string
- sequence
- corrected
- correction
- displaying
- 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
Images
Landscapes
- Input From Keyboards Or The Like (AREA)
- User Interface Of Digital Computer (AREA)
Abstract
The invention provides an input correction method of an input method and an input method device, which aim to improve the input efficiency. The method comprises the following steps: generating a first character string sequence according to the input key sequence and displaying the first character string sequence; capturing target gesture information generated by a terminal screen, and extracting a character string to be corrected from the first character string sequence according to the target gesture information; and converting the character string to be corrected to obtain a correction result, and displaying the correction result. The correction result is determined by directly correcting on the terminal screen through the gesture, the correction speed is improved, the character strings do not need to be selected in sequence to determine the segmentation result, and the correction efficiency is improved.
Description
Technical Field
The invention relates to the technical field of input methods, in particular to an input correction method of an input method and an input method device.
Background
With the popularization of mobile terminals, more and more character input of users is completed on the mobile terminals, and the users can input by adopting various types of keyboards such as a full keyboard or a Sudoku keyboard and the like when inputting on the mobile terminals by using an input method.
However, during the input process of the user, a plurality of segmentation schemes may exist in the input character string, and the currently recommended segmentation scheme may not be required by the user. For example, when the user inputs "dislike", the user correspondingly inputs the character string "fangan", and the obtained segmented character string is "fang 'an", while the actually segmented character string required by the user is "fan' gan". At this time, the user needs to reselect the slicing scheme, which results in a reduction in input efficiency.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide an input correction method for an input method, so as to improve input efficiency.
Correspondingly, the embodiment of the invention also provides an input method device which is used for ensuring the realization and the application of the method.
In order to solve the above problems, the present invention discloses an input correction method for an input method, comprising: generating a first character string sequence according to the input key sequence and displaying the first character string sequence; capturing target gesture information generated by a terminal screen, and extracting a character string to be corrected from the first character string sequence according to the target gesture information; and converting the character string to be corrected to obtain a correction result, and displaying the correction result.
Optionally, the step of capturing target gesture information generated by the terminal screen includes: capturing gesture operation behaviors on a terminal screen in real time, and judging the gesture operation behaviors; and when the gesture operation behavior is judged to be a preset correction behavior, generating target gesture information according to the preset correction behavior.
Optionally, the step of generating target gesture information according to the preset correction behavior includes: capturing initial position information and end position information sliding on a terminal screen according to the preset correction behavior; and generating target gesture information by adopting the starting position information and the ending position information.
Optionally, the step of extracting a character string to be corrected from the first character string sequence according to the target gesture information includes: matching the initial position information and the termination position information in the target gesture information with the display position of the first character string sequence on a terminal screen respectively; and extracting a character string sequence corresponding to the matched display position from the first character string sequence to be used as a character string to be corrected.
Optionally, the step of converting the character string to be corrected to obtain a correction result and displaying the correction result includes: canceling the segmentation result of the character string to be corrected; re-segmenting the character strings to be corrected to obtain at least one corrected character string as a correction result; and displaying the correction result while displaying the first character string sequence.
Optionally, the first character string sequence is generated according to a key sequence of a nine-grid keyboard; the step of converting the character string to be corrected to obtain a correction result and displaying the correction result comprises the following steps: determining a key sequence to be corrected corresponding to the character string to be corrected; converting the key sequence to be corrected to obtain at least one corrected character string as a correction result; and displaying the correction result while displaying the first character string sequence.
Optionally, the step of determining the key sequence to be corrected corresponding to the character string to be corrected includes: acquiring an original key sequence corresponding to the first character string sequence; and extracting the key sequence to be corrected corresponding to the matched display position from the original key sequence according to the matched display position of the character string to be corrected in the first character string sequence.
Optionally, the method further includes: determining other character strings except the character string to be corrected from the first character string sequence; the step of displaying the correction result comprises the following steps: and keeping the display of the other character strings in the first character string sequence, and popping up and displaying a display menu of each corrected character string in a correction result at a display position corresponding to the character string to be corrected, wherein the display menu is a floating menu or a pull-down menu.
Optionally, the method further includes: when the gesture operation behavior is judged to be a preset correction behavior, starting a magnifying lens on a terminal screen; and amplifying and displaying the characters in the first character string sequence passing through the sliding on the terminal screen in the magnifying glass according to the preset correction behavior.
Optionally, the method further includes: selecting a correction character string from the display menu according to the selection instruction; generating a second character string sequence by adopting the selected correction character string and other character strings; and displaying the second character string sequence and each candidate item of the second character string sequence in the terminal screen.
The embodiment of the invention also discloses an input method device, which comprises the following steps: the display module is used for generating and displaying a first character string sequence according to the input key sequence; and displaying the correction result; the gesture capturing module is used for capturing target gesture information generated by a terminal screen; the character extraction module is used for extracting a character string to be corrected from the first character string sequence according to the target gesture information; and the correction module is used for converting the character string to be corrected to obtain a correction result and displaying the correction result.
Optionally, the gesture capturing module includes: the judging submodule is used for capturing gesture operation behaviors on a terminal screen in real time and judging the gesture operation behaviors; and the information generation submodule is used for generating target gesture information according to the preset correction behavior when the gesture operation behavior is judged to be the preset correction behavior.
Optionally, the information generating sub-module is configured to capture start position information and end position information of sliding on a terminal screen according to the preset correction behavior; and generating target gesture information by adopting the starting position information and the ending position information.
Optionally, the character extraction module includes: the position matching submodule is used for respectively matching the starting position information and the ending position information in the target gesture information with the display position of the first character string sequence on the terminal screen; and the extraction submodule is used for extracting the character string sequence corresponding to the matched display position from the first character string sequence to be used as the character string to be corrected.
Optionally, the correction module is configured to cancel the segmentation result of the character string to be corrected; re-segmenting the character strings to be corrected to obtain at least one corrected character string as a correction result; and the display module is used for displaying the correction result while displaying the first character string sequence.
Optionally, the first character string sequence is generated according to a key sequence of a nine-grid keyboard; the correction module is used for determining a correction key sequence corresponding to the character string to be corrected; converting the correction key sequence to obtain at least one correction character string as a correction result; and the display module is used for displaying the correction result while displaying the first character string sequence.
Optionally, the modification module includes: the obtaining submodule is used for obtaining an original key sequence corresponding to the first character string sequence; and the sequence matching submodule is used for extracting a correction key sequence corresponding to the matched display position from the original key sequence according to the matched display position of the character string to be corrected in the first character string sequence.
Optionally, the correction module is further configured to determine, from the first character string sequence, other character strings except the character string to be corrected; the display module is used for keeping display of other character strings in the first character string sequence, and popping up and displaying a display menu of each corrected character string in the corrected result at a display position corresponding to the result character string, wherein the display menu is a floating menu or a pull-down menu.
Optionally, the method further includes: the magnifying module is used for starting a magnifying lens on a terminal screen when the gesture operation behavior is judged to be a preset correction behavior; and amplifying and displaying the characters in the first character string sequence passing through the sliding on the terminal screen in the magnifying glass according to the preset correction behavior.
Optionally, the correction module is further configured to select a correction character string from the display menu according to a selection instruction; generating a second character string sequence by adopting the selected correction character string and other character strings; the display module is further configured to display the second character string sequence and each candidate item of the second character string sequence in the terminal screen.
Compared with the prior art, the embodiment of the invention has the following advantages:
and generating a first character string sequence according to the input key sequence and displaying the first character string sequence, wherein if the first character string sequence is not in accordance with the expectation of the user, the user can directly correct the first character string sequence on the terminal screen through gesture operation, and the input method can capture target gesture information generated by the terminal screen and has higher identification speed on an error character string. And then selecting a character string to be corrected from the first character string sequence according to the target gesture information, wherein the character string to be corrected is caused by the fact that a conversion display result is not in accordance with expectation, but not a character string input error, so that the character string to be corrected is converted again to obtain a correction result, and then the correction result is displayed, so that the correction is directly performed on a terminal screen through a gesture to determine the correction result, the correction speed is increased, the character string does not need to be selected in sequence to determine a segmentation result and the like, and the correction efficiency is improved.
Drawings
FIG. 1 is a flow chart of the steps of an embodiment of an input modification method of an input method of the present invention;
FIG. 2 is a flow chart illustrating the steps of an alternative embodiment of an input modification method of an input method of the present invention;
FIG. 3 is a schematic diagram illustrating input method modification provided by an embodiment of the invention;
FIG. 4 is a block diagram of an input method apparatus according to an embodiment of the present invention;
fig. 5 is a block diagram of an alternative configuration of an input method apparatus embodiment of the present invention.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention comprehensible, embodiments accompanied with figures are described in further detail below.
When a user inputs an input method on a mobile terminal such as a mobile phone, various segmentation schemes may exist in an input character string, and if the fed back segmentation scheme is not accurate, the user needs to reselect to influence the input efficiency.
For example, the user may use a squared keyboard for input due to the limited screen size of the mobile terminal. The nine-grid keyboard refers to an input method keyboard which is arranged according to the form of the nine-grid, so that input characters of the nine-grid keyboard are represented by 10 keys of 0-9, and for character input, one number key can be adopted to correspond to a plurality of characters, such as a plurality of pinyin letters, a plurality of English characters, a plurality of Chinese strokes and the like.
Taking pinyin as an example, each key in the nine-square-grid keyboard of the input method corresponds to at least 3 characters. Therefore, in the process of inputting by using the nine-grid keyboard, at least 3 possibilities exist for each character through clicking the character string generated by the keys, and the coincident code rate of the input character string of the nine-grid keyboard is greatly improved. For example, "326426" is sequentially input on the nine-grid keyboard, wherein 2 corresponds to the character abc, 3 corresponds to the character def, 4 corresponds to the character ghi, and 6 corresponds to the character mno, then the "326426" corresponding input character string may include "dao 'hao", "fang' an", "dan 'gao", "fan' gan", "dang 'an", and "da' nian", etc., and the same input may correspond to multiple segmentation schemes.
When more keys are selected, more character string sequences can be correspondingly formed, and the corresponding segmentation schemes and the corresponding candidate segmentation results are greatly increased, namely the repetition rate of the Sudoku keyboard is generally higher, so that segmentation tones are more energy-saving, the problem that the segmentation tones are inconsistent with expectations or have larger differences occurs, and at the moment, a user can only input again, or each segmentation tone is selected in sequence, so that the input efficiency of the user is greatly influenced.
Therefore, one of the core concepts of the embodiments of the present invention is to provide an input modification method for an input method to improve input efficiency. And generating a first character string sequence according to the input key sequence and displaying the first character string sequence, wherein if the first character string sequence is not in accordance with the expectation of the user, the user can directly correct the first character string sequence on the terminal screen through gesture operation, and the input method can capture target gesture information generated by the terminal screen and has higher identification speed on an error character string. And then selecting a character string to be corrected from the first character string sequence according to the target gesture information, wherein the character string to be corrected is caused by the fact that a conversion display result is not in accordance with expectation, but not a character string input error, so that the character string to be corrected is converted again to obtain a correction result, and then the correction result is displayed, so that the correction result is determined by directly correcting on a terminal screen through a gesture, the correction speed is increased, the character string does not need to be selected in sequence to determine a segmentation result and the like, and the correction efficiency is improved.
Example one
Referring to fig. 1, a flowchart illustrating steps of an embodiment of an input correction method of an input method according to the present invention is shown, which may specifically include the following steps:
and 102, generating a first character string sequence according to the input key sequence and displaying the first character string sequence.
The method comprises the steps of obtaining a corresponding key sequence according to selection of a user on keys on a keyboard of an input method, converting the key sequence into a first character string sequence after the key sequence is received by an input method kernel, then matching the first character string sequence to determine corresponding candidate items, and then displaying the first character string sequence and the corresponding candidate items on a terminal screen.
For example, the user sequentially selects a key "64943326426" on the jiugong keyboard, where the key 2 corresponds to the character abc, the key 3 corresponds to the character def, the key 4 corresponds to the character ghi, the key 6 corresponds to the character mno, and the key 9 corresponds to the character xwyz, so that the key sequence "64943326426" corresponds to the input character string, which may include "ni 'zhe' dao 'hao", "ni' zhe 'fang' an", "ni 'zhe' dan 'gao", "ni' xie 'fang' an", "ni 'zhe' dang 'an", "ni' xie 'dang' an", and "mi 'xi' de 'biao", and the like, and the input method kernel may select the input character string with the highest probability as the first character string sequence, for example, display the first character string sequence "ni' zhe 'dao' and display its corresponding candidate.
The embodiment can be applied to various types of keyboards of input methods, such as a 26-key keyboard, a nine-square-grid keyboard and the like, and various input modes of each type of keyboard exist, such as pinyin, five-stroke, stroke and the like, so that characters can be Chinese letters, English letters, strokes and the like.
And 104, capturing target gesture information generated by a terminal screen, and extracting a character string to be corrected from the first character string sequence according to the target gesture information.
When the user views the first displayed character string sequence and finds that the character string is not the character string expected to be input, the character string can be corrected. Currently, a touch screen is usually adopted in a mobile terminal, so that a user can directly perform correction on the screen through gesture operations, such as sliding, clicking and other gesture operations, and determine a character string to be corrected according to gesture operation behaviors of the user. In this embodiment, the gesture operation refers to that the user inputs information on the terminal screen by using a hand operation such as a palm or a finger.
The input method can capture the gesture operation behavior of the user on the terminal screen in real time, so that the target gesture information is obtained, and at the moment, the segmentation result of each character string does not need to be selected in sequence, so that the correction speed is high. And extracting a character string to be corrected from the first character string sequence according to the target gesture information, wherein the character string to be corrected comprises at least one character in the embodiment.
As described above, if the user uses the gesture of sliding on the screen, the corresponding target gesture information may be captured, so as to select the character string to be corrected as "dao' hao".
And 106, converting the character string to be corrected to obtain a correction result, and displaying the correction result.
The character string to be corrected is not input expected by a user, so the character string to be corrected is corrected, the current character string to be corrected is determined by correction instead of the expected result because the coincident code rate of the input method is higher, and the kernel conversion result of the input method is not the expected result, but the character string is not input error, so the character string to be corrected is re-converted and segmented to obtain the corrected character string as the correction result, and the correction result is displayed for the user to select.
In summary, the first character string sequence is generated and displayed according to the input key sequence, if the first character string sequence is not in accordance with the expectation of the user, the user can directly perform correction on the terminal screen through gesture operation, and the input method can capture the target gesture information generated by the terminal screen, so that the recognition speed of the wrong character string is high. And then selecting a character string to be corrected from the first character string sequence according to the target gesture information, wherein the error of the character string to be corrected is that a conversion display result is not in accordance with expectation, but a character string input error is not, so that the character string to be corrected is converted again to obtain a correction result, and then the correction result is displayed, so that the correction is directly performed on a terminal screen through a gesture to determine the correction result, the correction speed is improved, the character string does not need to be selected in sequence to determine a segmentation result and the like, and the correction efficiency is improved.
Example two
On the basis of the above embodiments, the present embodiment discusses in detail the step of correcting the character string by the gesture.
Referring to fig. 1, a flowchart illustrating steps of an alternative embodiment of an input modification method of an input method according to the present invention is shown, which may specifically include the following steps:
The first character string sequence is generated according to the key sequence of each type of keyboard such as a 26-key keyboard or a Sudoku keyboard.
For a first character string sequence generated by a key sequence selected by a user on a Sudoku keyboard, if the first character string sequence does not conform to the input expected by the user, the first character string sequence can be corrected. The user can adopt gesture operation to correct.
Therefore, the gesture operation behavior on the terminal screen can be captured in real time, then the gesture operation behavior is judged, when the gesture operation behavior is judged, comprehensive judgment can be performed through the position triggered by the gesture operation behavior on the terminal screen, the actual operation behavior and the like, for example, a corresponding preset correction rule can be configured, if the gesture operation behavior conforms to the preset correction rule, the gesture operation behavior is judged to be the preset correction behavior, and otherwise, the gesture operation behavior is not the preset correction behavior. For example, the preset modification rule is configured as a sliding operation within a preset range above the first character string sequence, and the sliding operation can be a sliding operation from left to right or a sliding operation from right to left. And if the preset correction rule is configured to draw a circle on the screen in a sliding manner, the character string to be corrected is circled into the circle.
Therefore, the preset correction behavior is detected by judging the current gesture operation behavior, for example, if the gesture operation behavior is detected to be the clicking operation on the candidate item of the input method, the gesture operation behavior is judged not to be the preset correction behavior, and the clicked candidate item can be displayed on the screen. If the first string sequence is "ni ' zhe ' dao ' hao", capturing the sliding operation behavior starting to the left on the character "a" of the string "hao", it may be determined that it is the preset correction behavior.
And step 206, when the gesture operation behavior is judged to be the preset correction behavior, starting a magnifying glass on a terminal screen.
And 208, amplifying and displaying the characters in the first character string sequence passing through the sliding on the terminal screen in the magnifying glass according to the preset correction behavior.
Because the size of the screen of the mobile terminal is limited, the first character string sequence which is usually displayed is smaller, and the distance between the characters in the sequence is closer, in order to enable a user to more accurately determine the corrected position during correction, when the current gesture operation behavior is judged to be the preset correction behavior, a magnifier can be started in the display area of the input method, the magnifier is adopted to magnify and display the characters which pass through the current sliding, namely when the sliding of the user around the first character string sequence accords with the preset correction rule, the positions which pass through the sliding correspond to the positions of the characters in the first character string, therefore, the characters which pass through the sliding process can be magnified and displayed in the magnifier to prompt the user of the characters which are currently slid, and the user can conveniently determine whether the correction is completed.
And 210, generating target gesture information according to the preset correction behavior.
When the current gesture operation behavior is judged to be the preset correction behavior, target gesture information is generated according to the preset correction behavior to correct the first character string sequence, namely the target gesture information is determined according to the position where the preset correction behavior slides.
In an optional embodiment of the present invention, the step of generating the target gesture information according to the preset correction behavior includes: capturing initial position information and end position information sliding on a terminal screen according to the preset correction behavior; and generating target gesture information by adopting the starting position information and the ending position information.
After the current gesture operation behavior is judged to be the preset correction behavior, the initial position information of the preset correction behavior sliding on the terminal screen is captured, then the current sliding position is captured along with the execution of the sliding until the correction is completed, and the end position information of the preset correction behavior is determined. The start position information and the end position information may be represented by coordinate information of a terminal screen, and the like, which is not limited in this embodiment. Target gesture information is then generated using the starting location information and the ending location information.
In the above example, the initial position is the position corresponding to the character "a" in "hao", and the display through the magnifying glass stops at the position corresponding to the character "d" during the sliding process, that is, the end position is the position corresponding to the character "d".
And step 212, matching the initial position information and the terminal position information in the target gesture information with the display position of the first character string sequence on the terminal screen respectively.
Step 214, extracting a character string sequence corresponding to the matched display position from the first character string sequence as a character string to be corrected.
The character string to be corrected can be extracted from the first character string sequence through the target gesture information, namely, the initial position information in the target gesture information is matched with the display position of the first character string sequence on the terminal screen, and the termination position information is matched with the display position of the first character string sequence on the terminal screen, so that characters at two ends of the character string to be corrected are determined. And extracting the matched characters from the first character string sequence, wherein the character string sequence between the matched characters forms a character string to be corrected.
In this embodiment, the initial position information and the end position information are matched with the first character string sequence, where the character string to be corrected may be determined from characters corresponding to the initial position information and the end position information, or the character string between the characters corresponding to the initial position information and the end position information may be determined as the character string to be corrected, which may be set according to actual requirements, which is not limited in this embodiment.
As in the above example, the characters at the two ends are the character "a" and the character "d" in "hao", respectively, and the character string to be corrected is "dao' hao". For another example, for the character string "ni ' zhe ' dao ' hao ' bu ' tai ' hao", the character corresponding to the start position information is "e", and the character corresponding to the end position information is "b", the character string "dao ' hao" between the two characters may be selected as the character string to be corrected.
And step 216, converting the character string to be corrected to obtain a correction result.
The character string to be corrected is determined and then corrected, which is different from correction caused by error input, the embodiment needs to reconstruct the character string to be corrected, that is, because the key sequence of the input method keyboard can match with various character strings, and each character string also has one or more segmentation schemes, the character string to be corrected needs to be re-segmented.
In an optional embodiment of the present invention, the step of converting the character string to be corrected to obtain a correction result and displaying the correction result includes: canceling the segmentation result of the character string to be corrected; re-segmenting the character strings to be corrected to obtain at least one corrected character string as a correction result; and displaying the correction result while displaying the first character string sequence.
Because the character string to be corrected is caused by segmentation error, the segmentation result of the character string to be corrected is cancelled, and the character string to be corrected is restored to the original input character string before segmentation. If the corrected character string ' fang ' an ' input by the 26-key keyboard is cancelled, the original input character string ' fangan ' is restored and obtained. Then, the original character string is cut again, and the cutting result of the corrected character string is deleted or ignored during cutting, so that at least one corrected character string is obtained as the cutting result. And if the 'fang' an 'and the' fan 'gan' are obtained after the 'fangan' is re-segmented, ignoring the 'fang' an 'and obtaining a correction character string' fan 'gan' to be used as a correction result for displaying.
In another optional embodiment of the present invention, the first string sequence is generated according to a key sequence of a nine-grid keyboard; the step of converting the character string to be corrected to obtain a correction result and displaying the correction result comprises the following steps: determining a key sequence to be corrected corresponding to the character string to be corrected; converting the key sequence to be corrected to obtain at least one corrected character string as a correction result; and displaying the correction result while displaying the first character string sequence.
In this embodiment, a nine-grid keyboard may be used for input, but each key in the nine-grid keyboard may correspond to a plurality of characters, and different segmentation results may also be caused by different matched characters, so that the character string to be corrected is first restored to the correction key sequence. The character string "dao' hao" to be corrected in the above example is restored to the correction key sequence "326426". And then, re-matching characters according to the key sequence to be corrected and converting to obtain at least one corrected character string as a correction result.
In an optional embodiment of the present invention, the step of determining the correction key sequence corresponding to the character string to be corrected includes: acquiring an original key sequence corresponding to the first character string sequence; and extracting a corrected key sequence corresponding to the matched display position from the original key sequence according to the matched display position of the character string to be corrected in the first character string sequence.
When the character string to be corrected is restored, the original key sequence restored by the first character string sequence can be obtained firstly, then the key characters of the characters at the two corresponding ends of the character string to be corrected are matched from the original key sequence according to the display positions of the character string to be corrected matched in the first character string sequence, namely the positions of the characters at the two ends of the character string to be corrected determined by matching, the two key characters and the key character between the two key characters are extracted, and the corresponding key character sequence is used as the corrected key sequence.
For the restored corrected key sequence, the characters corresponding to the keys can be re-matched to obtain one or more matched character strings, then each character string is segmented to obtain each segmentation result, the segmentation result corresponding to the character string to be corrected is deleted from the segmentation results, the corresponding probability of each segmented result after screening is calculated, and then the characters are sorted from large to small according to the probability. Each segmentation result can be used as a correction character string, or a part of the segmentation results are selected as correction character strings according to the sorting sequence, and all the correction character strings are used as correction results.
For example, the above operations may be performed by using a scoring model in the input method, such as entering the first character string sequence, the character string to be corrected (or the character positions at both ends of the character string to be corrected) and the original keystroke sequence corresponding to the first character string sequence as parameters. Restoring the corrected key sequence corresponding to the character string to be corrected, fixing the rest non-corrected character parts which are not replaced, namely other characters, and then performing recoding enumeration sequencing on the corrected key sequence according to a scoring model.
The scoring model formula is as follows:
score (pinyin) ═ ArgMax hanzi { Translate92Py (pinyin | modifier key sequence) } pylangue (py-before, pinyin, py-after) } TranslatePy2Hz (hanzi | pinyin) } hzlangege (hz-before, hanzi, hz-after);
the scoring model can obtain the highest x mapping enumerations of pinyin- > hanzi (Pinyin to Chinese character), wherein x is a positive integer. Wherein HzLanggug is a Chinese string language model; TranslatePy2Hz is the probability of a syllable string being converted to the optimal Chinese string under the syllable string; PyLanggue is a syllable string language model; translate92Py is the probability that a 9-key string (i.e., keystroke sequence) will be converted to an alternative syllable string.
Therefore, by the aid of the scoring model, after parameters are input, each segmentation result and corresponding probability can be rapidly acquired.
In order to make the user more clearly correct the character strings in the first character string sequence, the first character string sequence can be kept displayed, and correction results are displayed at the same time. Of course, the fact that the first character string is kept displayed does not mean that the display of the first character string sequence is completely unchanged, and for example, the color of the character string to be corrected extracted from the first character string sequence may be changed to highlight the character string to be corrected as a correction position, or the character string to be corrected may be displayed as a deletion mark, such as adding a deletion line to the character string to be corrected.
In an optional embodiment of the present invention, the method further comprises: determining other character strings except the character string to be corrected from the first character string sequence; the step of displaying the correction result includes: and keeping the display of other character strings in the first character string sequence, and popping up and displaying a display menu of each corrected character string in the correction result at the display position corresponding to the result character string, wherein the display menu is a floating menu or a pull-down menu.
In this embodiment, after determining the character string to be corrected, another character string in the first character string sequence may also be determined, where the another character string is a character string in the first character string sequence except for the character string to be corrected. Therefore, when the correction result is displayed, the display of other character strings in the displayed first character string sequence is kept unchanged, and the character string to be corrected displayed in the first character string sequence can be different from other character strings, such as changing the color of the character string to be corrected, displaying a deletion mark, and the like.
And popping up a display menu at the position of the character string to be corrected, and loading each corrected character string in the correction result in the display menu, wherein the display menu can be a floating menu or a pull-down menu.
The user can select the correction character string through the display menu, and only the correction character string is selected from the display menu according to the selection fed back by the user. And then replacing the character string to be corrected in the first character string sequence with the selected corrected character string, and generating a second character string sequence by the selected corrected character string and other character strings.
And then, converting and matching the second character string sequence with the corresponding candidate item, so that when the second character string sequence is displayed in the terminal screen, the candidate item matched with the second character string sequence is displayed.
In summary, the preset correction behavior of the first character string sequence is determined by capturing the gesture operation behavior on the terminal screen in real time, so that the corresponding target gesture information is obtained, the character string to be corrected is determined according to the target gesture information, the correction accuracy is higher by directly performing the correction through the gesture according to the display of the first character string on the screen, the gesture operation selection speed is higher, the correction efficiency is further improved, and the input efficiency is improved.
Secondly, when the correction result is displayed, the first character string sequence and the correction result can be displayed at the same time, the display of other character strings in the first character string sequence can be kept unchanged, and the correction character strings are displayed by adopting a display window, so that a user can conveniently determine the correction position and quickly select the correction character strings to finish correction.
And thirdly, when the gesture operation behavior is judged to be the preset correction behavior, a magnifying lens can be started on the terminal screen, characters in the first character string sequence passing through the sliding on the terminal screen are magnified and displayed by the magnifying lens, namely the characters currently sliding to are clearly displayed, and a basis is provided for a user to quickly and accurately slide and select the character string to be corrected.
EXAMPLE III
On the basis of the above embodiments, the present embodiment exemplifies the step of correcting through gestures in the input method.
Taking the nine-grid keyboard input as an example, the user currently expects the input to be "this scheme is not good", so the original key sequence "6494332642628824426" is obtained after clicking the key, the first character string sequence "ni 'zhe' dao 'ha' bu 'tai' hao" with the maximum segmentation probability is obtained by the input method kernel, and the corresponding display result is shown in fig. 3.
Partial input in the first character string sequence is not expected, and the user can directly correct the partial input on the terminal screen through gestures. If the user performs gesture operation, namely the user firstly clicks a terminal screen to select the character string in the first character string sequence to slide from the e syllable to the right side, namely the character corresponding to the starting position is e.
And calling a magnifier after the gesture operation behavior of the user is determined to be the preset correction behavior, wherein the magnifier is used for auxiliary sliding correction, namely, part of character strings subjected to sliding are amplified and displayed until the gesture can be finished after the gesture is finished being corrected, such as syllable b, the auxiliary magnifier is closed, and the finishing position of finishing correction is recorded, namely, the character corresponding to the finishing position is b. Determining the character string to be corrected as 'daohao' from the character string between the character e corresponding to the starting position and the character b corresponding to the ending position "
Thereafter, a correction result formed by the correction character string may be determined using the scoring model. Namely, the sliding head and tail positions, the first character string sequence "ni 'zhe' dao 'hao' bu 'tai' hao" and the original keystroke sequence "326426" are used as input parameters and are transmitted into the scoring model.
The scoring model is performed as follows: p (pinyin | ni 'zhe' … 'bu' tai 'hao, you this' … 'is not so good)' HzLanguage (this 'Hanzi string' is not so good) 'TranslatePy 2Hz (Hanzi string | Pinyin)' PyLanguage (zhe 'pinyin' bu 'tai' hao) 'Translate 92Py (pinyin |9 key sequence 3264' 26)
Obtaining score of comprehensive consideration of the calculated syllable string (namely character string) and the Chinese character, namely obtaining segmentation probability value, such as obtaining the following character string sequence:
(1)ni’zhe’dan’gao’bu’tai’hao；
(2)ni’zhe’fan’gan’bu’tai’hao；
(3)ni’zhe’fang’an’bu’tai’hao；
……
after the segmentation results are sorted according to the probability values, the first 3 segmentation results are obtained as correction character strings, namely fang ' an \ dan ' gao \ fan ' gan, and the correction character strings are adopted to form correction results.
Then, a display menu pops up on the terminal screen to display the first character string sequence and the correction result, and a pull-up menu or a pull-down menu can be used for displaying, and one way of displaying is shown in fig. 3.
More than 3 corrected character strings may be displayed in the display menu, and when the display menu cannot completely display the corrected character strings, the corrected character strings are displayed and selected based on the sliding of the user.
When a certain corrected string is selected, the pop-up display menu is closed, and at this time, a second string sequence composed of the corrected string and other strings is displayed, and corresponding candidates are displayed as shown in fig. 3.
In summary, in the input stage of the input method, the defined preset correction behaviors of the gestures such as the left-side positioning right-slide gesture, the right-side positioning left-slide gesture and the like can select the character string to be corrected in the first character string sequence through the preset correction behaviors, so that the cost that the input efficiency is influenced by selecting the segmented character by clicking for many times due to the fact that the character string needs to be corrected when a long sentence is input is reduced. The operation cost and the time cost of correcting the input string by the user are effectively reduced, and the input efficiency is further improved. And moreover, the starting of the magnifier effectively improves the accuracy of syllable string selection operation.
It should be noted that, for simplicity of description, the method embodiments are described as a series of acts or combination of acts, but those skilled in the art will recognize that the present invention is not limited by the illustrated order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments of the present invention. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred and that no particular act is required to implement the invention.
Example four
On the basis of the above embodiment, the present embodiment also provides an input method apparatus.
Referring to fig. 4, a block diagram of an input method device according to an embodiment of the present invention is shown, which may specifically include the following modules:
a display module 402, configured to generate and display a first character string sequence according to an input key sequence; and displaying the correction result.
And a gesture capturing module 404 for capturing target gesture information generated by the terminal screen.
And a character extraction module 406, configured to extract a character string to be corrected from the first character string sequence according to the target gesture information.
And the correction module 408 is configured to convert the character string to be corrected to obtain a correction result, and display the correction result.
And generating a first character string sequence according to the input key sequence and displaying the first character string sequence, wherein if the first character string sequence is not in accordance with the expectation of the user, the user can directly correct the first character string sequence on the terminal screen through gesture operation, and the input method can capture target gesture information generated by the terminal screen and has higher identification speed on an error character string. And then selecting a character string to be corrected from the first character string sequence according to the target gesture information, wherein the character string to be corrected is caused by the fact that a conversion display result is not in accordance with expectation, but not a character string input error, so that the character string to be corrected is converted again to obtain a correction result, and then the correction result is displayed, so that the correction result is determined by directly correcting on a terminal screen through a gesture, the correction speed is increased, the character string does not need to be selected in sequence to determine a segmentation result and the like, and the correction efficiency is improved.
Referring to fig. 5, a block diagram showing an alternative structure of an embodiment of an input method apparatus of the present invention may specifically include the following modules:
the gesture capture module 404, comprising: the judging submodule 40402 is used for capturing gesture operation behaviors on a terminal screen in real time and judging the gesture operation behaviors; the information generating sub-module 40404 is configured to, when it is determined that the gesture operation behavior is a preset correction behavior, generate target gesture information according to the preset correction behavior.
The information generating submodule 40404 is configured to capture start position information and end position information of sliding on a terminal screen according to the preset correction behavior; and generating target gesture information by adopting the starting position information and the ending position information.
The character extraction module 406 includes: a position matching submodule 40602, configured to match, with the display position of the first character string sequence on the terminal screen, the initial position information and the end position information in the target gesture information respectively; the extracting sub-module 40604 is configured to extract a character string sequence corresponding to the matched display position from the first character string sequence, as a character string to be corrected.
The correction module 408 is configured to cancel the segmentation result of the character string to be corrected; re-segmenting the character strings to be corrected to obtain at least one corrected character string as a correction result; and the display module is used for displaying the correction result while displaying the first character string sequence.
The correction module 408 is configured to determine a correction key sequence corresponding to the character string to be corrected; converting the correction key sequence to obtain at least one correction character string as a correction result; the display module 402 is configured to display the correction result while displaying the first string sequence.
The modification module 408 includes: an obtaining sub-module 40802, configured to obtain an original key sequence corresponding to the first character string sequence; and the sequence matching submodule 40804 is configured to extract a modified key sequence corresponding to the matched display position from the original key sequence according to the matched display position of the character string to be modified in the first character string sequence.
The correcting module 408 is further configured to determine, from the first character string sequence, a character string other than the character string to be corrected; the display module 402 is configured to keep displaying other character strings in the first character string sequence, and pop up a display menu for displaying each correction character string in the correction result at a display position corresponding to the result character string, where the display menu is a floating menu or a pull-down menu.
The magnifying module 410 is used for starting a magnifying glass on a terminal screen when the gesture operation behavior is judged to be a preset correction behavior; and amplifying and displaying the characters in the first character string sequence passing through the sliding on the terminal screen in the magnifying glass according to the preset correction behavior.
The modification module 408 is further configured to select a modified character string from the display menu according to a selection instruction; generating a second character string sequence by adopting the selected correction character string and other character strings; the display module 402 is further configured to display the second character string sequence and each candidate item of the second character string sequence in the terminal screen.
In summary, the preset correction behavior of the first character string sequence is determined by capturing the gesture operation behavior on the terminal screen in real time, so that the corresponding target gesture information is obtained, the character string to be corrected is determined according to the target gesture information, the correction accuracy is higher by directly performing the correction through the gesture according to the display of the first character string on the screen, the gesture operation selection speed is higher, the correction efficiency is further improved, and the input efficiency is improved.
Secondly, when the correction result is displayed, the first character string sequence and the correction result can be displayed at the same time, the display of other character strings in the first character string sequence can be kept unchanged, and the correction character strings are displayed by adopting a display window, so that a user can conveniently determine the correction position and quickly select the correction character strings to finish correction.
And thirdly, when the gesture operation behavior is judged to be the preset correction behavior, a magnifying lens can be started on the terminal screen, characters in the first character string sequence passing through the sliding on the terminal screen are magnified and displayed by the magnifying lens, namely the characters currently sliding to are clearly displayed, and a basis is provided for a user to quickly and accurately slide and select the character string to be corrected.
For the device embodiment, since it is basically similar to the method embodiment, the description is simple, and for the relevant points, refer to the partial description of the method embodiment.
The embodiments in the present specification are described in a progressive manner, each embodiment focuses on differences from other embodiments, and the same and similar parts among the embodiments are referred to each other.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications of these embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the embodiments of the invention.
Finally, it should also be noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or terminal that comprises the element.
The input correction method of the input method and the input method device provided by the invention are described in detail, the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, there may be variations in the specific embodiments and the application scope, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (20)
1. An input correction method for an input method, comprising:
generating a first character string sequence according to the input key sequence and displaying the first character string sequence;
capturing target gesture information generated by a terminal screen, and extracting a character string to be corrected from the first character string sequence according to the target gesture information; the target gesture information includes a circling gesture, and the character string to be corrected includes: the first string sequence includes strings that fall within the circled result;
converting the character string to be corrected to obtain a correction result, and displaying the correction result;
the first character string sequence is generated according to a key sequence of a Sudoku keyboard; the converting the character string to be corrected to obtain a correction result includes:
obtaining one or more matched character strings according to the key sequence to be corrected corresponding to the character string to be corrected;
segmenting the matched character string to obtain a segmentation result;
and deleting the segmentation result corresponding to the character string to be corrected from the segmentation result to obtain a correction result.
2. The method according to claim 1, wherein the step of capturing the target gesture information generated by the terminal screen comprises:
capturing gesture operation behaviors on a terminal screen in real time, and judging the gesture operation behaviors;
and when the gesture operation behavior is judged to be a preset correction behavior, generating target gesture information according to the preset correction behavior.
3. The method according to claim 2, wherein the step of generating target gesture information according to the preset correction behavior comprises:
capturing initial position information and end position information sliding on a terminal screen according to the preset correction behavior;
and generating target gesture information by adopting the starting position information and the ending position information.
4. The method according to claim 3, wherein the step of extracting a character string to be corrected from the first character string sequence according to the target gesture information comprises:
matching the initial position information and the termination position information in the target gesture information with the display position of the first character string sequence on a terminal screen respectively;
and extracting a character string sequence corresponding to the matched display position from the first character string sequence to be used as a character string to be corrected.
5. The method according to claim 1, wherein the step of converting the character string to be corrected to obtain a correction result and displaying the correction result comprises:
canceling the segmentation result of the character string to be corrected;
re-segmenting the character strings to be corrected to obtain at least one corrected character string as a correction result;
and displaying the correction result while displaying the first character string sequence.
6. The method according to claim 1, wherein the step of converting the character string to be corrected to obtain a correction result and displaying the correction result comprises:
determining a key sequence to be corrected corresponding to the character string to be corrected;
converting the key sequence to be corrected to obtain at least one corrected character string as a correction result;
and displaying the correction result while displaying the first character string sequence.
7. The method according to claim 6, wherein the step of determining the key sequence to be modified corresponding to the character string to be modified comprises:
acquiring an original key sequence corresponding to the first character string sequence;
and extracting the key sequence to be corrected corresponding to the matched display position from the original key sequence according to the matched display position of the character string to be corrected in the first character string sequence.
8. The method of claim 4, 5 or 6, further comprising:
determining other character strings except the character string to be corrected from the first character string sequence;
the step of displaying the correction result comprises the following steps:
and keeping the display of the other character strings in the first character string sequence, and popping up and displaying a display menu of each corrected character string in a correction result at a display position corresponding to the character string to be corrected, wherein the display menu is a floating menu or a pull-down menu.
9. The method of claim 2, further comprising:
when the gesture operation behavior is judged to be a preset correction behavior, starting a magnifying lens on a terminal screen;
and amplifying and displaying the characters in the first character string sequence passing through the sliding on the terminal screen in the magnifying glass according to the preset correction behavior.
10. The method of claim 8, further comprising:
selecting a correction character string from the display menu according to the selection instruction;
generating a second character string sequence by adopting the selected correction character string and other character strings;
and displaying the second character string sequence and each candidate item of the second character string sequence in the terminal screen.
11. An input method apparatus, comprising:
the display module is used for generating and displaying a first character string sequence according to the input key sequence; and displaying the correction result;
the gesture capturing module is used for capturing target gesture information generated by a terminal screen;
the character extraction module is used for extracting a character string to be corrected from the first character string sequence according to the target gesture information; the target gesture information includes a circling gesture, and the character string to be corrected includes: the first string sequence includes strings that fall within the circled result;
the correction module is used for converting the character string to be corrected to obtain a correction result and displaying the correction result;
the first character string sequence is generated according to a key sequence of a Sudoku keyboard; the correction module comprises:
the matching module is used for obtaining one or more matched character strings according to the key sequence to be corrected corresponding to the character string to be corrected;
the segmentation module is used for segmenting the matched character string to obtain a segmentation result;
and the deleting module is used for deleting the segmentation result corresponding to the character string to be corrected from the segmentation result so as to obtain a correction result.
12. The input method apparatus of claim 11, wherein the gesture capture module comprises:
the judging submodule is used for capturing gesture operation behaviors on a terminal screen in real time and judging the gesture operation behaviors;
and the information generation submodule is used for generating target gesture information according to the preset correction behavior when the gesture operation behavior is judged to be the preset correction behavior.
13. The input method device according to claim 12, characterized in that:
the information generation submodule is used for capturing initial position information and end position information sliding on a terminal screen according to the preset correction behavior; and generating target gesture information by adopting the starting position information and the ending position information.
14. The input method apparatus of claim 13, wherein the character extraction module comprises:
the position matching submodule is used for respectively matching the starting position information and the ending position information in the target gesture information with the display position of the first character string sequence on the terminal screen;
and the extraction submodule is used for extracting the character string sequence corresponding to the matched display position from the first character string sequence to be used as the character string to be corrected.
15. The input method apparatus according to claim 11,
the correction module is used for canceling the segmentation result of the character string to be corrected; re-segmenting the character strings to be corrected to obtain at least one corrected character string as a correction result;
and the display module is used for displaying the correction result while displaying the first character string sequence.
16. The input method device of claim 11, wherein the first sequence of character strings is generated from a sequence of keys of a nine-grid keyboard;
the correction module is used for determining a correction key sequence corresponding to the character string to be corrected; converting the correction key sequence to obtain at least one correction character string as a correction result;
and the display module is used for displaying the correction result while displaying the first character string sequence.
17. The input method apparatus of claim 16, wherein the modification module comprises:
the obtaining submodule is used for obtaining an original key sequence corresponding to the first character string sequence;
and the sequence matching submodule is used for extracting a correction key sequence corresponding to the matched display position from the original key sequence according to the matched display position of the character string to be corrected in the first character string sequence.
18. The input method apparatus according to claim 14, 15 or 16,
the correction module is further used for determining other character strings except the character string to be corrected from the first character string sequence;
the display module is used for keeping display of other character strings in the first character string sequence, and popping up and displaying a display menu of each corrected character string in the correction result at the corresponding display position of the character string to be corrected, wherein the display menu is a floating menu or a pull-down menu.
19. The input method apparatus according to claim 12, further comprising:
the magnifying module is used for starting a magnifying lens on a terminal screen when the gesture operation behavior is judged to be a preset correction behavior; and amplifying and displaying the characters in the first character string sequence passing through the sliding on the terminal screen in the magnifying glass according to the preset correction behavior.
20. The input method apparatus of claim 18,
the correction module is also used for selecting a correction character string from the display menu according to the selection instruction; generating a second character string sequence by adopting the selected correction character string and other character strings;
the display module is further configured to display the second character string sequence and each candidate item of the second character string sequence in the terminal screen.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510016736.2A CN105843414B (en) | 2015-01-13 | 2015-01-13 | Input method input correction method and input method device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510016736.2A CN105843414B (en) | 2015-01-13 | 2015-01-13 | Input method input correction method and input method device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105843414A CN105843414A (en) | 2016-08-10 |
| CN105843414B true CN105843414B (en) | 2022-03-08 |
Family
ID=56579810
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510016736.2A Active CN105843414B (en) | 2015-01-13 | 2015-01-13 | Input method input correction method and input method device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105843414B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108803891B (en) * | 2017-04-28 | 2024-02-02 | 北京搜狗科技发展有限公司 | Information display method and device, electronic equipment and storage medium |
| CN107678560B (en) * | 2017-08-31 | 2021-10-08 | 科大讯飞股份有限公司 | Candidate result generation method and device of input method, storage medium and electronic equipment |
| CN109871131A (en) * | 2017-12-05 | 2019-06-11 | 北京搜狗科技发展有限公司 | A kind of method and device that character string is split |
| CN109901725B (en) * | 2017-12-07 | 2022-05-06 | 北京搜狗科技发展有限公司 | Pinyin string segmentation method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07192081A (en) * | 1993-12-27 | 1995-07-28 | Toshiba Corp | Handwritten character input device |
| CN101986249A (en) * | 2010-07-14 | 2011-03-16 | 上海无戒空间信息技术有限公司 | Method for controlling computer by using gesture object and corresponding computer system |
| CN102243561A (en) * | 2010-05-10 | 2011-11-16 | 腾讯科技（深圳）有限公司 | Method and device for modifying input information |
| CN103164038A (en) * | 2011-12-15 | 2013-06-19 | 汉王科技股份有限公司 | Japanese input method and Japanese input device of touch screen terminal |
Family Cites Families (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| AU5299700A (en) * | 1999-05-27 | 2000-12-18 | America Online, Inc. | Keyboard system with automatic correction |
| US7098896B2 (en) * | 2003-01-16 | 2006-08-29 | Forword Input Inc. | System and method for continuous stroke word-based text input |
| JP5186484B2 (en) * | 2006-04-20 | 2013-04-17 | ノキア コーポレイション | Data input to electronic devices using handwriting |
| US8232973B2 (en) * | 2008-01-09 | 2012-07-31 | Apple Inc. | Method, device, and graphical user interface providing word recommendations for text input |
| CN101943952B (en) * | 2010-01-27 | 2014-07-09 | 北京搜狗科技发展有限公司 | Mixed input method of at least two languages and input method system |
| KR101557358B1 (en) * | 2010-02-25 | 2015-10-06 | 엘지전자 주식회사 | Method for inputting a string of charaters and apparatus thereof |
| WO2011122627A1 (en) * | 2010-03-29 | 2011-10-06 | 京セラ株式会社 | Information processing device and character input method |
| CN102445994B (en) * | 2010-09-30 | 2018-05-04 | 北京搜狗科技发展有限公司 | A kind of intelligent input method and input method system |
| CN102662575A (en) * | 2012-03-27 | 2012-09-12 | 上海量明科技发展有限公司 | Method for modifying text, client and system |
| WO2013172522A1 (en) * | 2012-05-14 | 2013-11-21 | 전남대학교산학협력단 | Terminal capable of text message makeup and control method |
| CN102779002B (en) * | 2012-06-19 | 2015-05-20 | 邓朝进 | Touch screen keyboard |
| JP2014149612A (en) * | 2013-01-31 | 2014-08-21 | Nippon Hoso Kyokai <Nhk> | Voice recognition error correction device and its program |
| CN103136180A (en) * | 2013-02-25 | 2013-06-05 | 北京极兴莱博信息科技有限公司 | Text segment copying and pasting method and device and terminal for implementing same |
| CN103699233B (en) * | 2013-12-20 | 2019-04-09 | 百度在线网络技术（北京）有限公司 | Character string input method and input unit |
-
2015
- 2015-01-13 CN CN201510016736.2A patent/CN105843414B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH07192081A (en) * | 1993-12-27 | 1995-07-28 | Toshiba Corp | Handwritten character input device |
| CN102243561A (en) * | 2010-05-10 | 2011-11-16 | 腾讯科技（深圳）有限公司 | Method and device for modifying input information |
| CN101986249A (en) * | 2010-07-14 | 2011-03-16 | 上海无戒空间信息技术有限公司 | Method for controlling computer by using gesture object and corresponding computer system |
| CN103164038A (en) * | 2011-12-15 | 2013-06-19 | 汉王科技股份有限公司 | Japanese input method and Japanese input device of touch screen terminal |
Non-Patent Citations (2)
| Title |
|---|
| Extraction of domain-specific phenomenal terms based on separator and contextual terms;LIU Li等;《Journal of South China University of Technology》;20110715;第39卷(第7期);第145-149页 * |
| 中文专利文献术语抽取;徐川等;《计算机工程与设计》;20130616;第34卷(第6期);第2175-2179页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105843414A (en) | 2016-08-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US9703462B2 (en) | Display-independent recognition of graphical user interface control | |
| TWI321294B (en) | Method and device for determining at least one recognition candidate for a handwritten pattern | |
| US9881224B2 (en) | User interface for overlapping handwritten text input | |
| CN103270483B (en) | There is the system of gesture identification unit | |
| JP2018515817A (en) | How to improve control by combining eye tracking and speech recognition | |
| US20150242761A1 (en) | Interactive visualization of machine-learning performance | |
| US20110047514A1 (en) | Recording display-independent computerized guidance | |
| CN106484131B (en) | Input error correction method and input method device | |
| EP2897055A1 (en) | Information processing device, information processing method, and program | |
| CN105843414B (en) | Input method input correction method and input method device | |
| US20180300542A1 (en) | Drawing emojis for insertion into electronic text-based messages | |
| WO2016107344A1 (en) | Method and device for screening on-screen candidate items of input method | |
| JP5832980B2 (en) | Handwriting input support device, method and program | |
| US9405558B2 (en) | Display-independent computerized guidance | |
| US9286527B2 (en) | Segmentation of an input by cut point classification | |
| JP2019537103A (en) | Method and apparatus for translating characters | |
| CN106484132B (en) | Input error correction method and input method device | |
| JP2017511917A (en) | Method and apparatus for recognizing musical symbols | |
| KR20130093672A (en) | Method, apparatus, and computer program product for overlapped handwriting | |
| EP2806336A1 (en) | Text prediction in a text input associated with an image | |
| US20150193410A1 (en) | System for editing a text of a portable terminal and method thereof | |
| JP2013206141A (en) | Character input device, character input method, and character input program | |
| JP5807342B2 (en) | Character recognition device and program | |
| CN105589570B (en) | A kind of method and apparatus handling input error | |
| JP2012234512A (en) | Method for text segmentation, computer program product and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |