CN111078028A - Input method, related device and readable storage medium - Google Patents

Input method, related device and readable storage medium Download PDF

Info

Publication number
CN111078028A
CN111078028A CN201911249731.9A CN201911249731A CN111078028A CN 111078028 A CN111078028 A CN 111078028A CN 201911249731 A CN201911249731 A CN 201911249731A CN 111078028 A CN111078028 A CN 111078028A
Authority
CN
China
Prior art keywords
input
weight
input mode
user input
track
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN201911249731.9A
Other languages
Chinese (zh)
Other versions
CN111078028B (en
Inventor
戴晓楠
余飞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
iFlytek Co Ltd
Original Assignee
iFlytek Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by iFlytek Co Ltd filed Critical iFlytek Co Ltd
Priority to CN201911249731.9A priority Critical patent/CN111078028B/en
Publication of CN111078028A publication Critical patent/CN111078028A/en
Application granted granted Critical
Publication of CN111078028B publication Critical patent/CN111078028B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
    • G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
    • G06F3/0233—Character input methods
    • G06F3/0236—Character input methods using selection techniques to select from displayed items
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0487—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser
    • G06F3/0488—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures
    • G06F3/04883—Interaction techniques based on graphical user interfaces [GUI] using specific features provided by the input device, e.g. functions controlled by the rotation of a mouse with dual sensing arrangements, or of the nature of the input device, e.g. tap gestures based on pressure sensed by a digitiser using a touch-screen or digitiser, e.g. input of commands through traced gestures for inputting data by handwriting, e.g. gesture or text

Abstract

After the input tracks of the user are collected, the weights of candidate words of at least two input modes are determined according to the input tracks of the user, a final candidate result is determined according to the weights of the candidate words of the at least two input modes and displayed to the user, and the final candidate result simultaneously contains the candidate words of the at least two input modes.

Description

Input method, related device and readable storage medium
Technical Field
The present application relates to the field of input methods, and more particularly, to an input method, a related device, and a readable storage medium.
Background
With the continuous development of social science and technology, intelligent electronic devices with touch screens are gradually popularized, and accordingly, in order to support the user input function of the intelligent electronic devices, various touch screen input modes have been developed, such as: pinyin input mode, stroke input mode, handwriting input mode, sliding input mode, etc.
At present, for two touch screen input modes, namely a handwriting input mode and a sliding input mode, a user can only select to use the handwriting input mode or select to use the sliding input mode in one input process, when the user selects to use the handwriting input mode, the intelligent electronic device can only recognize a track formed by the moving position of the user on a screen to obtain a handwriting input result, and when the user selects to perform sliding input, the intelligent electronic device can only recognize the track formed by the moving position of the user on the screen to obtain a sliding input result.
Since the user interaction methods of the handwriting input method and the slide input method are the same and input is performed through a trajectory formed by a position where the user moves on the screen, an input method combining the handwriting input method and the slide input method is required in order to enable the user to input more efficiently.
Disclosure of Invention
In view of the above, the present application is proposed to provide an input method, a related device, and a readable storage medium. The specific scheme is as follows:
an input method, comprising:
collecting a user input track;
determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes;
determining a final candidate result according to the weight of the candidate word in each input mode;
and displaying the final candidate result.
Optionally, the determining a weight of each input mode candidate word according to the user input trajectory includes:
calculating the weight of each input mode of the user input track;
acquiring the priority of candidate words of each input mode of the user input track;
and determining the weight of the candidate word of each input mode according to the weight of each input mode and the priority of the candidate word of each input mode.
Optionally, the calculating a weight value of each input mode of the user input trajectory includes:
determining at least one characteristic of the user input trajectory;
respectively calculating the weight of each input mode of the at least one characteristic;
and calculating the weight value of each input mode of the user input track according to the weight value of each input mode of the at least one characteristic.
Optionally, the determining at least one characteristic of the user input trajectory comprises:
determining an initial region characteristic, and/or an initial direction characteristic, and/or a horizontal and vertical projection length characteristic, and/or a discrete degree characteristic of the user input track.
Optionally, calculating a weight of each input mode of the stroke starting area feature includes:
acquiring coordinates of a first point of the user input track;
judging whether the coordinate of a first point of the user input track is in a preset starting area of each input mode;
when the coordinate of a first point of the user input track is in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a first numerical value;
and when the coordinate of the first point of the user input track is not in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a second numerical value.
Optionally, calculating a weight of each input mode of the starting direction feature includes:
acquiring the angle of a first stroke of the user input track;
acquiring a reference angle of each input mode;
and determining the weight of each input mode of the starting direction characteristic according to the angle of the first stroke of the user input track and the reference angle of each input mode.
Optionally, calculating a weight for each input mode of the horizontal and vertical projection length features includes:
calculating a total distance that the user input trajectory moves in a horizontal direction;
calculating a total distance that the user input trajectory moves in a vertical direction;
and calculating the weight value of each input mode of the horizontal and vertical projection length characteristics according to the total distance of the user input track moving in the horizontal direction and the total distance of the user input track moving in the vertical direction.
Optionally, calculating a weight for each input mode of the discrete degree feature includes:
calculating a variance of points included in the user input trajectory;
and calculating the weight of each input mode of the discrete degree characteristic according to the variance of the points contained in the user input track and a preset discrete degree parameter.
Optionally, the determining a final candidate result according to the weight of the candidate word in each input mode includes:
and sequencing the candidate words in at least two input modes according to the sequence of the weight values from large to small to generate a final candidate result.
Optionally, the at least two input modes include:
handwriting input mode and sliding input mode.
An input device, comprising:
the acquisition unit is used for acquiring a user input track;
the candidate word weight determining unit is used for determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes;
the candidate result determining unit is used for determining a final candidate result according to the weight of the candidate word of each input mode;
and the candidate result display unit is used for displaying the final candidate result.
Optionally, the candidate word weight determining unit includes:
the weight calculation unit is used for calculating the weight of each input mode of the user input track;
the priority acquiring unit is used for acquiring the priority of the candidate words of each input mode of the user input track;
and the weight determining unit is used for determining the weight of the candidate word of each input mode according to the weight of each input mode and the priority of the candidate word of each input mode.
Optionally, the weight calculation unit includes:
a feature determination unit for determining at least one feature of the user input trajectory;
a feature weight calculation unit for calculating a weight of each input mode of the at least one feature;
and the input mode weight calculation unit is used for calculating the weight of each input mode of the user input track according to the weight of each input mode of the at least one characteristic.
Optionally, the feature determining unit is specifically configured to:
determining an initial region characteristic, and/or an initial direction characteristic, and/or a horizontal and vertical projection length characteristic, and/or a discrete degree characteristic of the user input track.
Optionally, the feature weight calculation unit includes: a stroke starting area feature weight calculation unit;
the pen-starting area feature weight calculation unit is used for acquiring the coordinate of a first point of the user input track; judging whether the coordinate of a first point of the user input track is in a preset starting area of each input mode; when the coordinate of a first point of the user input track is in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a first numerical value; and when the coordinate of the first point of the user input track is not in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a second numerical value.
Optionally, the feature weight calculation unit includes: a stroke starting direction feature weight calculation unit;
the starting direction feature weight calculation unit is used for acquiring the angle of the first stroke of the user input track; acquiring a reference angle of each input mode; and determining the weight of each input mode of the starting direction characteristic according to the angle of the first stroke of the user input track and the reference angle of each input mode.
Optionally, the feature weight calculation unit includes: a horizontal and vertical projection length feature weight calculation unit;
the horizontal and vertical projection length feature weight calculation unit is used for calculating the total distance of the movement of the user input track in the horizontal direction; calculating a total distance that the user input trajectory moves in a vertical direction; and calculating the weight value of each input mode of the horizontal and vertical projection length characteristics according to the total distance of the user input track moving in the horizontal direction and the total distance of the user input track moving in the vertical direction.
Optionally, the feature weight calculation unit includes: a discrete degree feature weight calculation unit;
the discrete degree feature weight calculation unit is used for calculating the variance of points contained in the user input track; and calculating the weight of each input mode of the discrete degree characteristic according to the variance of the points contained in the user input track and a preset discrete degree parameter.
Optionally, the candidate result determining unit is specifically configured to:
and sequencing the candidate words in at least two input modes according to the sequence of the weight values from large to small to generate a final candidate result.
Optionally, the at least two input modes include:
handwriting input mode and sliding input mode.
An input system comprising a memory and a processor;
the memory is used for storing programs;
the processor is configured to execute the program to implement the steps of the input method.
A readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, carries out the steps of the input method as described above.
By means of the technical scheme, the application discloses an input method, related equipment and a readable storage medium, after the input track of a user is collected, the weight values of candidate words of at least two input modes are determined according to the input track of the user, a final candidate result is determined according to the weight values of the candidate words of the at least two input modes and displayed to the user, the final candidate result simultaneously comprises the candidate words of the at least two input modes, and based on the scheme, the input mode combining the at least two input modes can be achieved, so that the user can use the at least two input modes simultaneously in one input process, and the input efficiency is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flowchart of an input method disclosed in an embodiment of the present application;
FIG. 2 is a schematic diagram of a user input trajectory formed when a user moves a handwriting tool on a keyboard of an intelligent electronic device according to an embodiment of the present application;
FIG. 3 is a schematic diagram illustrating a final candidate result according to an embodiment of the present disclosure;
FIG. 4 is a schematic diagram of a preset pen starting area of a handwriting input method disclosed in an embodiment of the present application;
FIG. 5 is a schematic diagram of a preset pen start area of a sliding input method disclosed in an embodiment of the present application;
FIG. 6 is a diagram illustrating reference angles of a handwriting input method according to an embodiment of the present application;
FIG. 7 is a schematic view of a reference angle of a skating input method disclosed in an embodiment of the present application;
fig. 8 is a schematic structural diagram of an input device disclosed in an embodiment of the present application;
fig. 9 is a schematic structural diagram of an input system according to an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Referring to fig. 1, fig. 1 is a schematic flow chart of an input method disclosed in an embodiment of the present application, where the method includes the following steps:
s101: and collecting a user input track.
When a user uses an intelligent electronic device (e.g., a smart phone, a tablet computer, etc.) with a touch screen, if there is an input demand, a handwriting tool (e.g., a finger, a stylus, etc.) can perform various operations (e.g., moving the handwriting tool on the touch screen, clicking the touch screen with the handwriting tool, etc.) on the touch screen of the intelligent electronic device to generate a touch event, so as to form a plurality of points, which can form a user input track, in other words, the user input track is a data set formed by coordinates of the plurality of points. The coordinates of each point contain coordinate values in the x and y directions.
For easy understanding, please refer to fig. 2, fig. 2 is a schematic diagram of a user input trajectory formed when a user moves a handwriting tool on a keyboard of an intelligent electronic device according to an embodiment of the present application, a trajectory corresponding to a "good" word at the keyboard in fig. 2 is the user input trajectory, and as can be seen from fig. 2, the user input trajectory includes a plurality of points.
In the present application, the user input trajectory may be collected in various ways, and the way of collecting the user input trajectory is a mature technology at present, and therefore, the present application is not repeated.
S102: determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes.
As an implementable manner, in the present application, the user input trajectory may be generated by the user on the premise of selecting at least two input manners, and when the user selects at least two input manners, the weight of each input manner candidate word selected by the user needs to be determined according to the user input trajectory in the present application. For example, the user selects two input modes as a handwriting input mode and a sliding input mode.
As another possible implementation manner, in this application, the user input trajectory may also be generated by the user on the premise that one input manner is selected, and the user input trajectory matches the input manner selected by the user, in which case, at least one other input manner similar to the input principle of the input manner selected by the user may be determined, and the weight of the input manner candidate word selected by the user may be determined according to the user input trajectory, and the weight of the input manner candidate word selected by the user may be determined. For example, the input mode selected by the user is a handwriting input mode, and the other input mode having a similar input principle to the input mode selected by the user is a slide input mode.
As still another possible implementation manner, in the present application, the user input trajectory is generated by the user on the premise that one input manner is selected, but the user input trajectory cannot match the input manner selected by the user, in this case, at least two input manners matching the user input trajectory may be determined, and the weight of the at least two input manner candidate words matching the user input trajectory may be determined according to the user input trajectory. For example, the input mode selected by the user is a pinyin input mode, and the input modes matched with the user track are a handwriting input mode and a sliding input mode.
Since the user interaction modes of the handwriting input mode and the sliding input mode are consistent and the input is performed by forming a relatively obvious track at the position moved by the user on the screen, in the application, the at least two preferred input modes can be the handwriting input mode and the sliding input mode. However, in other input methods (such as a pinyin input method, a stroke input method, and the like), the user may also move on the screen during the input process, and the position of the movement may also be understood as one of the input tracks of the user, so that the at least two input methods may also be other input methods besides a handwriting input method and a slide input method, and the application is not limited at all.
It should be noted that, the implementation manner of determining the weight of each input mode candidate word according to the user input trajectory may be various, and will be described in detail through the following contents, and details are not described here. And determining the weight value of the same candidate word possibly in different modes.
S103: and determining a final candidate result according to the weight value of each input mode candidate word.
In the present application, the final candidate result is a candidate word that combines at least two input modes, the specific combination mode may be multiple, and in the present application, the candidate words are combined according to the weight of each input mode candidate word, and as an implementable mode, the candidate words of at least two input modes may be sorted according to the weight of each candidate word in the order from large to small of the weight to generate the final candidate result.
It should be noted that, because different ways are adopted, the weights of the determined same candidate word may be different. Thus, the final candidates may also differ.
S104: and displaying the final candidate result.
In the present application, the final candidate result may be presented on a candidate bar of the intelligent electronic device keyboard.
For easy understanding, please refer to fig. 3, fig. 3 is a schematic diagram illustrating a final candidate result disclosed in the embodiment of the present application, a top column of the keyboard in fig. 3 is a candidate column, and "malicious" and "one" are candidate words. Wherein the weight of the candidate word ranked in front is greater than the weight of the candidate word ranked behind.
It should be noted that, in order to enable the user to distinguish the input modes corresponding to different candidate words, the candidate words of at least one input mode may be identified, for example, a word "write" in the upper right corner of "one" in fig. 3 indicates that the input mode corresponding to the candidate word "one" is a handwriting input mode.
According to the input method disclosed by the embodiment, after the input track of the user is collected, the candidate words of at least two input modes are determined according to the input track of the user, the final candidate result is determined according to the weights of the candidate words of the at least two input modes and displayed to the user, and the final candidate result simultaneously contains the candidate words of the at least two input modes.
In the method and the device, the weight of each input mode of the user input track and the priority of each candidate word can be comprehensively considered, and the weight of each candidate word under each input mode is determined. Therefore, the present application further discloses a specific implementation manner for determining the weight of each input mode candidate word according to the user input trajectory, and the implementation manner includes the following steps:
s201: and calculating the weight value of each input mode of the user input track.
It should be noted that the weight value of each input mode of the user input trajectory refers to a probability value that the user input trajectory matches with a certain input mode.
S202: and acquiring the priority of the candidate words of each input mode of the user input track.
The priority of the candidate word of each input mode of the user input trajectory refers to the priority of each candidate word output by the recognition engine of a certain input mode. The priority of the candidate words of each input mode of the user input track can be obtained through the recognition engine of each input mode, the recognition engines of various input modes can be realized based on the existing mature technology, and the application is not limited at all. Taking a handwriting input mode as an example, inputting a user input track into a recognition engine of the handwriting input mode, wherein the recognition engine of the handwriting input mode can output candidate word information, and each candidate word information not only comprises the content of a candidate word, but also comprises the priority of the candidate word.
S203: and determining the weight of the candidate word of each input mode according to the weight of each input mode and the priority of the candidate word of each input mode.
In the present application, the weight of the candidate word for each input method may be determined in various ways, for example, the weight of each input method and the sum of the priorities of the candidate words for each input method may be calculated, and the product of the weight of each input method and the priority of the candidate word for each input method may also be calculated.
For convenience of understanding, assume that F is a handwriting input mode and a sliding input mode respectivelywrite(x) The final weight of the xth handwriting input mode candidate word, EwriteWeight of handwriting input mode for user input trace, fwrite(x) And (4) candidate word priority for the xth handwriting input mode. The final weight of the xth handwriting input mode candidate word can be calculated by the following formula:
Fwrite(x)＝Ewrite×fwrite(x)
suppose Fswype(x) The final weight of the candidate word for the xth sliding input mode, EswypeWeight of sliding input mode for inputting track for user, fwrite(x) The priority of the candidate word for the x-th sliding input mode. Then the x-th sliding input mode candidate word can be calculated by the following formulaThe final weight of (2):
Fswype(x)＝Eswype＝fswype(x)
in this application, an implementation of calculating a weight of each input mode of a user input trajectory is also disclosed, which includes the following steps:
s301: at least one characteristic of the user input trajectory is determined.
The at least one characteristic of the user input trajectory may include any one or more of an attack region characteristic, an attack direction characteristic, a horizontal and vertical projection length characteristic, and a degree of dispersion characteristic of the user input trajectory. It should be noted that there is a case where the weights of one or more features of at least two input modes are consistent, and in this case, it is indicated that the probability that which input mode the user input trajectory matches is higher, which cannot be distinguished from the one or more features. Therefore, the more features considered, the more accurate the weight of each input mode of the user input trajectory obtained finally.
S302: and respectively calculating the weight value of each input mode of the at least one characteristic.
In this application, the weight value of each input mode of each feature refers to a probability value that each feature is matched with a certain input mode. It should be noted that, for different features, the weight of each input mode of the feature may be calculated in different manners, which will be specifically described in the following embodiments, and the detailed description of the embodiment is omitted.
S303: and calculating the weight value of each input mode of the user input track according to the weight value of each input mode of the at least one characteristic.
In the present application, the weight value of each input mode of the user input trajectory may be calculated in various ways, for example, the sum of the weight values of each input mode of the at least one feature may be calculated as the weight value of each input mode of the user input trajectory. Alternatively, the product of the weights for each input method of the at least one feature may be calculated as the weight for each input method of the user input trajectory. The present application is not limited to this.
For convenience of understanding, at least two input modes are a handwriting input mode and a sliding input mode respectively, and at least one characteristic is a starting area characteristic, a starting direction characteristic, a horizontal and vertical projection length characteristic and a discrete degree characteristic of a user input track:
suppose with EwriteWeight value of handwriting input mode for representing user input track, using Ewrite_rWeight of handwriting input mode for representing characteristics of starting area, using Ewrite_dWeight of handwriting input mode for representing starting direction characteristic, using Ewrite_lWeight of handwriting input mode for representing horizontal and vertical projection length characteristics, using Ewrite_sAnd the weight of the handwriting input mode representing the characteristic of the discrete degree.
Then the weight of the handwriting input mode of the user input track can be calculated by the following formula:
Ewrite＝Ewrite_r×Ewrite_d×Ewrite_l×Ewrite_s
suppose with EswypeWeight of sliding input mode representing user input trajectory, using Eswype_rWeight of sliding input mode for representing the characteristics of the starting area, using Eswype_dWeight of sliding input mode for indicating starting direction characteristic, using Eswype_lWeight of sliding input mode for representing horizontal and vertical projection length characteristics, using Eswype_sAnd representing the weight of the sliding input mode of the discrete degree characteristic.
Then the weight of the sliding input mode of the user input track can be calculated by the following formula:
Eswype＝Eswype_r×Eswype_d×Eswype_l×Eswype_s
in this application, a specific implementation manner of calculating the weight of each input manner of each feature is also disclosed, which specifically includes the following steps:
as an implementable embodiment, the present application discloses an implementation method for calculating a weight of each input mode of a stroke starting area feature, which may include the following steps:
s401: coordinates of a first point of the user input trajectory are obtained.
It should be noted that the first point of the user input trajectory may be a starting point of the user input trajectory, that is, a first point generated when the user operates the touch screen.
S402: judging whether the coordinate of a first point of the user input track is in a preset starting area of each input mode; executing S403 when the coordinates of the first point of the user input track are within the preset starting area of each input mode, and executing S404 when the coordinates of the first point of the user input track are not within the preset starting area of each input mode.
Note that the pen-start area is an area for limiting the pen-start position. The initial pen area can be preset in the development process for each input mode.
Taking the handwriting input mode as an example, according to the writing habit of the user, the user writes characters from top to bottom and from left to right. Of course, there are also a few words that start with from right to left. In order to conform to the writing habit of the user and consider the situation of a few characters, in the present application, when the preset starting area of the handwriting input method is defined, since the user is unlikely to start writing from the rightmost side for handwriting input, the width of the keyboard may be divided into 5 equal parts in the horizontal direction, the 4/5 area on the left side is the preset starting area of the handwriting input method, and the 1/5 area on the right side is not the preset starting area of the handwriting input method. Similarly, the user is unlikely to start writing upwards from the bottom row of the keyboard for handwriting input, so that, in the vertical direction, the area of the bottom row of keys of the keyboard can be excluded, and the remaining area is the preset writing starting area of the handwriting input mode.
For easy understanding, please refer to fig. 4, where fig. 4 is a schematic diagram illustrating a preset pen starting area of a handwriting input method disclosed in an embodiment of the present application, and in fig. 4, an area inside a frame is the preset pen starting area of the handwriting input method.
Taking the sliding input mode as an example, because the input principle of the sliding input mode is that the user slides on the software board to replace the clicking of the key, according to the principle, if the user performs the sliding input, the starting position of the pen must be within the input key area. Therefore, the preset pen starting area of the sliding input mode can be an area corresponding to an alphabetic key in the keyboard.
For easy understanding, please refer to fig. 5, fig. 5 is a schematic diagram of a preset pen starting area of a sliding input mode disclosed in an embodiment of the present application, and in fig. 5, an area inside a frame is the preset pen starting area of the sliding input mode.
S403: and determining the weight value of each input mode of the starting area characteristics as a first numerical value.
S404: and determining the weight value of each input mode of the starting area characteristic as a second numerical value.
It should be noted that, in this application, if the starting point is located within the preset starting area of a certain input mode, the weight of the input mode of the starting area characteristic is determined to be a first numerical value, and if the starting point is located outside the preset starting area of the certain input mode, the weight of the input mode of the starting area characteristic is determined to be a second numerical value.
For ease of understanding, assume x0，y0Inputting the abscissa and ordinate, respectively, of the first point of the trajectory for the user, if x0，y0Determining the weight E of the handwriting input mode of the characteristics of the stroke starting area when the handwriting input mode is in the preset stroke starting areawrite_rIs 1 if x0，y0When the handwriting input mode is not in the preset starting area of the handwriting input mode, determining the weight E of the handwriting input mode of the starting area characteristicwrite_rIs 0. Assuming that the preset pen-up area of the handwriting input mode is simply referred to as the handwriting pen-up area, the formula is as follows:
Figure BDA0002308680870000131
let x be0，y0Inputting the abscissa and ordinate, respectively, of the first point of the trajectory for the user, if x0，y0In the process of sliding inputDetermining the weight E of the sliding input mode of the stroke starting area characteristic when the preset stroke starting area of the mode is inswype_r Is 1 if x0，y0When the input mode is not in the preset starting area of the sliding input mode, determining the weight E of the sliding input mode of the starting area characteristicswype_rIs 0. Assuming that the preset pen-up area of the sliding input mode is simply called as a sliding pen-up area, the formula is as follows:
Figure BDA0002308680870000132
it should be further noted that, there is a case where the preset pen starting regions of the at least two input modes overlap, at this time, the weights of the at least two input modes of the pen starting region feature are both the first numerical values, and this case indicates that the probability that the user input trajectory matches which input mode cannot be distinguished from the pen starting region feature is higher, and therefore, other features of the user input trajectory may be considered.
As another possible implementation manner, the present application discloses an implementation method for calculating a weight of each input manner of the starting direction feature, and the method may include the following steps:
s501: and acquiring the angle of the first stroke of the user input track.
It should be noted that, the angle of the first stroke of the user input trajectory may be obtained by first extracting the first stroke of the user input trajectory and then calculating the angle of the first stroke. The extraction mode of the first stroke and the angle calculation mode of the first stroke can be realized by adopting the existing mature algorithm, and the description is omitted in the application.
S502: and acquiring the reference angle of each input mode.
It should be noted that the manner of obtaining the reference angle for each input manner may be different according to the input manner.
Taking a handwriting input mode as an example, according to statistics of characters, the first stroke of a single character cannot occur to the conditions of horizontal left, oblique upper left corner and horizontal upward. Therefore, if it is detected that the user has first presented these situations, it may be considered not to be handwritten input. Therefore, the preset angle interval can be set for the handwriting input mode, when the angle of the first stroke is in the interval, the user input track can be considered to be matched with the handwriting input mode, and when the angle interval of the first stroke is not in the interval, the user input track can be considered to be not matched with the handwriting input mode. Therefore, the reference angle of the handwriting input mode can be a preset angle interval.
It should be noted that, in the present application, the preset angle interval of the handwriting input method may be an empirical value, such as (0,255), or may be dynamically adjusted according to the habit of the user.
For easy understanding, please refer to fig. 6, where fig. 6 is a schematic diagram illustrating reference angles of a handwriting input method disclosed in an embodiment of the present application, and in the circular area of fig. 6, an angle corresponding to a gray area is a preset angle interval of the handwriting input method.
Taking the sliding input mode as an example, it can be seen from the rule of the combination of the initial consonants and the final consonants of the pinyin that the second letter of the pinyin is only a e i o u h v n. If you are entered, the pinyin string is ni and the second pinyin character is i. Thus, the possibility of several keys from each letter key to a e i o u h v n on the keyboard can be exhausted.
For easy understanding, please refer to fig. 7, fig. 7 is a schematic view illustrating a reference angle of a sliding input mode disclosed in an embodiment of the present application. As can be seen from FIG. 7, taking the button D as an example, according to the rule of the combination of the initials and finals, only possible combinations are DA, DE, DU, DI, and DO, so if the starting point of the first stroke is D, and the user wants to perform the sliding input, the ending point of the first stroke is only A, E, U, I, O.
Therefore, in the application, the current key corresponding to the first point of the first stroke can be determined, then the target key corresponding to the current key is determined according to the combination of the initial consonants and the final consonants of the Chinese pinyin, and then the angle of the target key is calculated. The angle of the target key is the reference angle of the sliding input mode.
It should be noted that, when calculating the angle of the target key, a straight line connecting the current key and the center point of the target key may be obtained, and the inclination angle of the straight line is the angle of the target key.
S503: and determining the weight of each input mode of the starting direction characteristic according to the angle of the first stroke of the user input track and the reference angle of each input mode.
In this application, different manners may be adopted to determine the weight of each input manner of the starting direction feature according to the angle of the first stroke of the user input trajectory and the reference angle of each input manner, which will be described in detail below.
As an implementation manner, the present application provides a specific implementation manner for determining a weight of each input manner of the starting direction feature according to an angle of a first stroke of the user input trajectory and the reference angle of each input manner, where the implementation manner may be:
judging whether the angle of the first stroke of the user input track is within the preset angle interval of each input mode or not; when the angle of the first stroke of the user input track is within the preset angle interval of each input mode, determining the weight of each input mode of the starting direction characteristic as a first numerical value; and when the angle of the first stroke of the user input track is not within the preset angle interval of each input mode, determining the weight of each input mode of the starting direction characteristic as a second numerical value.
For ease of understanding, the following description will be given by taking a handwriting input method as an example.
Suppose Ewrite_dThe weight of the handwriting input mode of the starting direction characteristic is calculated according to the following formula, wherein theta is the angle of the first stroke, and the value range is 15-255 degrees:
Figure BDA0002308680870000151
as another possible implementation manner, the present application provides another specific implementation manner for determining the weight of each input manner of the starting direction feature according to the angle of the first stroke of the user input trajectory and the reference angle of each input manner, where the specific implementation manner may be: and calculating a normal distribution probability value corresponding to the target key according to the angle of the first stroke of the user input track and the angle of the target key, and determining that the weight of the sliding input mode of the starting direction characteristic is the highest value of the normal distribution probability corresponding to the target key.
For ease of understanding, the following description will take a coasting input mode as an example.
In the process of starting the pen by the user, a certain error exists between the direction drawn by the user and the direction of the actual key and the key, and the error can be considered to meet normal distribution. If the current user initiated point is on the D key, the direction of the first stroke may only be to key A, E, U, I, O. If the normal distribution is satisfied in each direction, the probability that the key D slides in each angle is the highest value of the normal distributions of the key directions.
Thus, E can be assumedswype_dThe weight of the sliding input mode which is the starting direction characteristic, { R } is the target key of the current key, x is the angle of the first stroke, thetaiIs the angle of the ith target key.
The normal distribution probability formula is as follows:
Figure BDA0002308680870000161
wherein the parameter μ is θiBecause it is at θiIs the center point. To reach the highest value of 1, the parameter σ is
Figure BDA0002308680870000162
The calculation formula of the weight of the sliding input mode with the starting direction characteristics can be obtained after the calculation formula is introduced, and the calculation formula is as follows:
Figure BDA0002308680870000163
as another possible implementation manner, the present application discloses an implementation method for calculating a weight value of each input manner of the horizontal and vertical projection length features, which may include the following steps:
s601: calculating a total distance the user input trajectory moves in a horizontal direction.
In the present application, the total distance that the user input trajectory moves in the horizontal direction may be calculated from the coordinates of the points in the user input trajectory. Suppose LsThe total distance of the movement of the user input track in the horizontal direction is input, n is the number of the middle points of the user input track, xiIs the x-coordinate value of the ith point, yiIs the y coordinate value of the ith point. The specific calculation method is as follows:
Figure BDA0002308680870000164
s602: calculating a total distance the user input trajectory moves in a vertical direction.
In the present application, the total distance that the user input trajectory moves in the vertical direction may be calculated from the coordinates of the points in the user input trajectory. Suppose LhThe total distance of the movement of the track in the vertical direction is input by the user, n is the number of the middle points of the track input by the user, and xiIs the x-coordinate value of the ith point, yiIs the y coordinate value of the ith point. The specific calculation method is as follows:
Figure BDA0002308680870000165
s603: and calculating the weight value of each input mode of the horizontal and vertical projection length characteristics according to the total distance of the user input track moving in the horizontal direction and the total distance of the user input track moving in the vertical direction.
In this application, the weight of each input mode of the horizontal and vertical projection length features may be calculated according to a ratio of a total distance that the user input trajectory moves in a horizontal direction to a total distance that the user input trajectory moves in a vertical direction.
Taking at least two input modes as a handwriting input mode and a sliding input mode as an example, when the sliding input mode is adopted for input, because an area formed by keyboard keys is a rectangle and is far longer than the vertical direction in the horizontal direction, in the input process, under the most part of conditions, the moving distance of a user input track in the horizontal direction is much longer than that in the vertical direction. And the handwriting input mode is adopted to write according to the font when in input, and the moving distance of the input track of the user in the horizontal direction is equivalent to the moving distance in the vertical direction, or the moving distance in the vertical direction is longer. Therefore, in the present application, the weight of the handwriting input mode of the horizontal and vertical projection length features and the weight of the sliding input mode of the horizontal and vertical projection length features may be calculated based on the ratio of the total distance of the user input track moving in the horizontal direction to the total distance of the user input track moving in the vertical direction.
Suppose Ewrite_lWeight of handwriting input for horizontal and vertical projection length features, Eswype_lFor the weight of the sliding input mode of the horizontal and vertical projection length features, the calculation formula can be as follows:
Figure BDA0002308680870000171
Figure BDA0002308680870000172
as another possible implementation manner, the present application discloses an implementation method for calculating a weight of each input manner of the feature of the discrete degree, and the method may include the following steps:
s701: calculating the discrete degree characteristic of the user input track.
In the present application, the variance of points in the user input trajectory may be calculated as a discrete degree characteristic of the user input trajectory.
Assuming that S is a discrete degree feature, n is the number of points in the user input track, xi, yi are coordinate values of the ith point, the average value of x, the average value of y can be calculated:
Figure BDA0002308680870000181
Figure BDA0002308680870000182
the degree of dispersion is characterized by:
Figure BDA0002308680870000183
s702: and calculating the weight of each input mode of the discrete degree characteristic according to the discrete degree characteristic of the user input track and a preset discrete degree parameter.
In the method, the discrete degree characteristic of the user input track and the absolute value of the difference between the preset discrete degree parameters can be obtained first, and then the weight of each input mode of the discrete degree characteristic is calculated according to the ratio of the absolute value of the difference to the preset discrete degree parameters.
For convenience of understanding, the detailed description is given by taking as an example at least two input modes as a handwriting input mode and a sliding input mode, and the specific examples are as follows:
according to the input principle, the key of the handwriting input mode for identifying the input track of the user is a track path, and the key of the sliding input mode for identifying the input track of the user is a turning point in the track and a passing position, and how the curve of the track has no significance on sliding input. Generally, the positions of the points formed by the handwriting input method are more concentrated, and the positions of the points formed by the sliding input method are more dispersed.
Suppose Ewrite_sHand characterised by discrete degreeWeight of write input mode, Eswype_sThe weight of the sliding input mode with the characteristic of discrete degree, a is a preset parameter of discrete degree, and can be adjusted through actual conditions, and the calculation formula can be as follows:
Figure BDA0002308680870000184
Figure BDA0002308680870000185
the input device disclosed in the embodiments of the present application is described below, and the input device described below and the input method described above may be referred to correspondingly.
Referring to fig. 8, fig. 8 is a schematic structural diagram of an input device disclosed in the embodiment of the present application. As shown in fig. 8, the input device may include:
an acquisition unit 81 for acquiring a user input trajectory;
a candidate word weight determining unit 82, configured to determine a weight of a candidate word in each input mode according to the user input trajectory; each input mode is one of at least two input modes;
a candidate result determining unit 83, configured to determine a final candidate result according to the weight of the candidate word in each input manner;
a candidate result presenting unit 84, configured to present the final candidate result.
As an implementation manner, the candidate word weight determining unit includes:
the weight calculation unit is used for calculating the weight of each input mode of the user input track;
the priority acquiring unit is used for acquiring the priority of the candidate words of each input mode of the user input track;
and the weight determining unit is used for determining the weight of the candidate word of each input mode according to the weight of each input mode and the priority of the candidate word of each input mode.
As an implementation manner, the weight calculation unit includes:
a feature determination unit for determining at least one feature of the user input trajectory;
a feature weight calculation unit for calculating a weight of each input mode of the at least one feature;
and the input mode weight calculation unit is used for calculating the weight of each input mode of the user input track according to the weight of each input mode of the at least one characteristic.
As an implementation manner, the feature determining unit is specifically configured to:
determining an initial region characteristic, and/or an initial direction characteristic, and/or a horizontal and vertical projection length characteristic, and/or a discrete degree characteristic of the user input track.
As an implementation manner, the feature weight calculation unit includes: a stroke starting area feature weight calculation unit;
the pen-starting area feature weight calculation unit is used for acquiring the coordinate of a first point of the user input track; judging whether the coordinate of a first point of the user input track is in a preset starting area of each input mode; when the coordinate of a first point of the user input track is in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a first numerical value; and when the coordinate of the first point of the user input track is not in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a second numerical value.
As an implementation manner, the feature weight calculation unit includes: a stroke starting direction feature weight calculation unit;
the starting direction feature weight calculation unit is used for acquiring the angle of the first stroke of the user input track; acquiring a reference angle of each input mode; and determining the weight of each input mode of the starting direction characteristic according to the angle of the first stroke of the user input track and the reference angle of each input mode.
As an implementation manner, the feature weight calculation unit includes: a horizontal and vertical projection length feature weight calculation unit;
the horizontal and vertical projection length feature weight calculation unit is used for calculating the total distance of the movement of the user input track in the horizontal direction; calculating a total distance that the user input trajectory moves in a vertical direction; and calculating the weight value of each input mode of the horizontal and vertical projection length characteristics according to the total distance of the user input track moving in the horizontal direction and the total distance of the user input track moving in the vertical direction.
As an implementation manner, the feature weight calculation unit includes: a discrete degree feature weight calculation unit;
the discrete degree feature weight calculation unit is used for calculating the variance of points contained in the user input track; and calculating the weight of each input mode of the discrete degree characteristic according to the variance of the points contained in the user input track and a preset discrete degree parameter.
As an implementation manner, the candidate result determining unit is specifically configured to:
and sequencing the candidate words in at least two input modes according to the sequence of the weight values from large to small to generate a final candidate result.
As an implementation, the at least two input manners include:
handwriting input mode and sliding input mode.
Fig. 9 is a block diagram showing a hardware configuration of an input system, and referring to fig. 9, the hardware configuration of the input system may include: at least one processor 1, at least one communication interface 2, at least one memory 3 and at least one communication bus 4;
in the embodiment of the application, the number of the processor 1, the communication interface 2, the memory 3 and the communication bus 4 is at least one, and the processor 1, the communication interface 2 and the memory 3 complete mutual communication through the communication bus 4;
the processor 1 may be a central processing unit CPU, or an application specific Integrated circuit asic, or one or more Integrated circuits configured to implement embodiments of the present invention, etc.;
the memory 3 may include a high-speed RAM memory, and may further include a non-volatile memory (non-volatile memory) or the like, such as at least one disk memory;
wherein the memory stores a program and the processor can call the program stored in the memory, the program for:
collecting a user input track;
determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes;
determining a final candidate result according to the weight of the candidate word in each input mode;
and displaying the final candidate result.
Alternatively, the detailed function and the extended function of the program may be as described above.
Embodiments of the present application further provide a storage medium, where a program suitable for execution by a processor may be stored, where the program is configured to:
collecting a user input track;
determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes;
determining a final candidate result according to the weight of the candidate word in each input mode;
and displaying the final candidate result.
Alternatively, the detailed function and the extended function of the program may be as described above.
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 apparatus 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 apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
The embodiments in the present description 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.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (13)

1. An input method, comprising:
collecting a user input track;
determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes;
determining a final candidate result according to the weight of the candidate word in each input mode;
and displaying the final candidate result.
2. The method of claim 1, wherein determining a weight of each input mode candidate word according to the user input trajectory comprises:
calculating the weight of each input mode of the user input track;
acquiring the priority of candidate words of each input mode of the user input track;
and determining the weight of the candidate word of each input mode according to the weight of each input mode and the priority of the candidate word of each input mode.
3. The method according to claim 2, wherein the calculating the weight of each input mode of the user input trajectory comprises:
determining at least one characteristic of the user input trajectory;
respectively calculating the weight of each input mode of the at least one characteristic;
and calculating the weight value of each input mode of the user input track according to the weight value of each input mode of the at least one characteristic.
4. The method of claim 3, wherein the determining at least one characteristic of the user input trajectory comprises:
determining an initial region characteristic, and/or an initial direction characteristic, and/or a horizontal and vertical projection length characteristic, and/or a discrete degree characteristic of the user input track.
5. The method of claim 4, wherein calculating the weight of each input mode of the stroke starting area feature comprises:
acquiring coordinates of a first point of the user input track;
judging whether the coordinate of a first point of the user input track is in a preset starting area of each input mode;
when the coordinate of a first point of the user input track is in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a first numerical value;
and when the coordinate of the first point of the user input track is not in the preset starting area of each input mode, determining the weight of each input mode of the starting area characteristic as a second numerical value.
6. The method of claim 4, wherein calculating the weight of each input mode of the starting direction feature comprises:
acquiring the angle of a first stroke of the user input track;
acquiring a reference angle of each input mode;
and determining the weight of each input mode of the starting direction characteristic according to the angle of the first stroke of the user input track and the reference angle of each input mode.
7. The method of claim 4, wherein calculating the weight for each input mode of the horizontal and vertical projection length features comprises:
calculating a total distance that the user input trajectory moves in a horizontal direction;
calculating a total distance that the user input trajectory moves in a vertical direction;
and calculating the weight value of each input mode of the horizontal and vertical projection length characteristics according to the total distance of the user input track moving in the horizontal direction and the total distance of the user input track moving in the vertical direction.
8. The method of claim 4, wherein calculating the weight of each input mode of the discrete degree feature comprises:
calculating a variance of points included in the user input trajectory;
and calculating the weight of each input mode of the discrete degree characteristic according to the variance of the points contained in the user input track and a preset discrete degree parameter.
9. The method of claim 1, wherein determining a final candidate result according to the weight of the candidate word for each input mode comprises:
and sequencing the candidate words in at least two input modes according to the sequence of the weight values from large to small to generate a final candidate result.
10. The method according to any one of claims 1 to 9, wherein the at least two input modes comprise:
handwriting input mode and sliding input mode.
11. An input device, comprising:
the acquisition unit is used for acquiring a user input track;
the candidate word weight determining unit is used for determining the weight of each input mode candidate word according to the user input track; each input mode is one of at least two input modes;
the candidate result determining unit is used for determining a final candidate result according to the weight of the candidate word of each input mode;
and the candidate result display unit is used for displaying the final candidate result.
12. An input system comprising a memory and a processor;
the memory is used for storing programs;
the processor, configured to execute the program, implementing the steps of the input method according to any one of claims 1 to 10.
13. A readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the steps of the input method according to any one of claims 1 to 10.
CN201911249731.9A 2019-12-09 2019-12-09 Input method, related device and readable storage medium Active CN111078028B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911249731.9A CN111078028B (en) 2019-12-09 2019-12-09 Input method, related device and readable storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911249731.9A CN111078028B (en) 2019-12-09 2019-12-09 Input method, related device and readable storage medium

Publications (2)

Publication Number Publication Date
CN111078028A true CN111078028A (en) 2020-04-28
CN111078028B CN111078028B (en) 2023-11-21

Family

ID=70313385

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911249731.9A Active CN111078028B (en) 2019-12-09 2019-12-09 Input method, related device and readable storage medium

Country Status (1)

Country Link
CN (1) CN111078028B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111090340A (en) * 2019-12-24 2020-05-01 科大讯飞股份有限公司 Input method candidate result display method, related equipment and readable storage medium

Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1991717A (en) * 2005-12-28 2007-07-04 中兴通讯股份有限公司 Virtual keyboard and hand-write synergic input system and realization method thereof
JP2012099008A (en) * 2010-11-04 2012-05-24 Nec Casio Mobile Communications Ltd Character input support device, character input support method and portable terminal device
CN102736821A (en) * 2011-03-31 2012-10-17 腾讯科技（深圳）有限公司 Method and apparatus for determining candidate words based on sliding path
CN102880302A (en) * 2012-07-17 2013-01-16 重庆优腾信息技术有限公司 Word identification method, device and system on basis of multi-word continuous input
US20130021248A1 (en) * 2011-07-18 2013-01-24 Kostas Eleftheriou Data input system and method for a touch sensor input
CN103345305A (en) * 2013-07-22 2013-10-09 百度在线网络技术（北京）有限公司 Method and device for controlling candidate words of mobile terminal input method and mobile terminal
CN104102625A (en) * 2013-04-15 2014-10-15 佳能株式会社 Method and equipment for improving spelling by using keyboard layout information
CN104932786A (en) * 2015-06-02 2015-09-23 百度在线网络技术（北京）有限公司 Method and device for presenting sequence of candidate words
CN105094368A (en) * 2015-07-24 2015-11-25 上海二三四五网络科技有限公司 Control method and control device for frequency modulation ordering of input method candidate item
WO2016150346A1 (en) * 2015-03-20 2016-09-29 上海触乐信息科技有限公司 Text input method and device
WO2016202101A1 (en) * 2015-06-16 2016-12-22 北京奇虎科技有限公司 Method and device for displaying candidate item based on input method
CN106354276A (en) * 2016-08-29 2017-01-25 北京元心科技有限公司 Hybrid input method and device suitable for multiple input methods and electronic equipment
CN106569618A (en) * 2016-10-19 2017-04-19 武汉悦然心动网络科技股份有限公司 Recurrent-neural-network-model-based sliding input method and system
CN106896932A (en) * 2016-06-07 2017-06-27 阿里巴巴集团控股有限公司 A kind of candidate word recommends method and device
US20170316086A1 (en) * 2014-09-09 2017-11-02 Beijing Sogou Technology Development Co., Ltd. Input method, device, and electronic apparatus
CN108197243A (en) * 2017-12-29 2018-06-22 北京奇虎科技有限公司 Method and device is recommended in a kind of input association based on user identity
CN108549493A (en) * 2018-04-04 2018-09-18 科大讯飞股份有限公司 Candidate word screening technique and relevant device
WO2019045185A1 (en) * 2017-08-31 2019-03-07 Phill It Co., Ltd. Mobile device and method for correcting character string entered through virtual keyboard

Patent Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1991717A (en) * 2005-12-28 2007-07-04 中兴通讯股份有限公司 Virtual keyboard and hand-write synergic input system and realization method thereof
JP2012099008A (en) * 2010-11-04 2012-05-24 Nec Casio Mobile Communications Ltd Character input support device, character input support method and portable terminal device
CN102736821A (en) * 2011-03-31 2012-10-17 腾讯科技（深圳）有限公司 Method and apparatus for determining candidate words based on sliding path
US20130021248A1 (en) * 2011-07-18 2013-01-24 Kostas Eleftheriou Data input system and method for a touch sensor input
CN102880302A (en) * 2012-07-17 2013-01-16 重庆优腾信息技术有限公司 Word identification method, device and system on basis of multi-word continuous input
CN104102625A (en) * 2013-04-15 2014-10-15 佳能株式会社 Method and equipment for improving spelling by using keyboard layout information
CN103345305A (en) * 2013-07-22 2013-10-09 百度在线网络技术（北京）有限公司 Method and device for controlling candidate words of mobile terminal input method and mobile terminal
US20170316086A1 (en) * 2014-09-09 2017-11-02 Beijing Sogou Technology Development Co., Ltd. Input method, device, and electronic apparatus
WO2016150346A1 (en) * 2015-03-20 2016-09-29 上海触乐信息科技有限公司 Text input method and device
CN104932786A (en) * 2015-06-02 2015-09-23 百度在线网络技术（北京）有限公司 Method and device for presenting sequence of candidate words
WO2016202101A1 (en) * 2015-06-16 2016-12-22 北京奇虎科技有限公司 Method and device for displaying candidate item based on input method
CN105094368A (en) * 2015-07-24 2015-11-25 上海二三四五网络科技有限公司 Control method and control device for frequency modulation ordering of input method candidate item
CN106896932A (en) * 2016-06-07 2017-06-27 阿里巴巴集团控股有限公司 A kind of candidate word recommends method and device
CN106354276A (en) * 2016-08-29 2017-01-25 北京元心科技有限公司 Hybrid input method and device suitable for multiple input methods and electronic equipment
CN106569618A (en) * 2016-10-19 2017-04-19 武汉悦然心动网络科技股份有限公司 Recurrent-neural-network-model-based sliding input method and system
WO2019045185A1 (en) * 2017-08-31 2019-03-07 Phill It Co., Ltd. Mobile device and method for correcting character string entered through virtual keyboard
CN108197243A (en) * 2017-12-29 2018-06-22 北京奇虎科技有限公司 Method and device is recommended in a kind of input association based on user identity
CN108549493A (en) * 2018-04-04 2018-09-18 科大讯飞股份有限公司 Candidate word screening technique and relevant device

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111090340A (en) * 2019-12-24 2020-05-01 科大讯飞股份有限公司 Input method candidate result display method, related equipment and readable storage medium
CN111090340B (en) * 2019-12-24 2024-02-13 科大讯飞股份有限公司 Input method candidate result display method, related equipment and readable storage medium

Also Published As

Publication number Publication date
CN111078028B (en) 2023-11-21

Similar Documents

Publication Publication Date Title
US9013428B2 (en) Electronic device and handwritten document creation method
CN100437739C (en) System and method for continuous stroke word-based text input
EP2756369B1 (en) Soft keyboard interface
CN108027876B (en) System for recognizing multiple object inputs, method and product thereof
CN105210027B (en) Handwriting input is identified using rotatable support line
US9529448B2 (en) Data entry systems and methods
CN105229574A (en) Reduce the error rate based on the keyboard touched
JP4851547B2 (en) Mode setting system
EP2828733A1 (en) Gestural input at a virtual keyboard
US8989496B2 (en) Electronic apparatus and handwritten document processing method
US20130300676A1 (en) Electronic device, and handwritten document display method
US20210350122A1 (en) Stroke based control of handwriting input
US9182908B2 (en) Method and electronic device for processing handwritten object
US20190196712A1 (en) Systems and Methods for Facilitating Data Entry into Small Screen Electronic Devices
US20230244379A1 (en) Key function execution method and apparatus, device, and storage medium
JP5567097B2 (en) Electronic device, handwritten document display method, and display program
EP1513053A2 (en) Apparatus and method for character recognition
CN108701215A (en) The system and method for multipair image structures for identification
KR100713407B1 (en) Pen input method and apparatus in pen computing system
US9183276B2 (en) Electronic device and method for searching handwritten document
CN111078028A (en) Input method, related device and readable storage medium
JP6599504B2 (en) Touch error calibration method and system
JP6223687B2 (en) Electronic device and handwritten document search method
JP5735126B2 (en) System and handwriting search method
US20150089432A1 (en) Quick data entry systems and methods

Legal Events

Date Code Title Description
PB01 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