CN111124222B - Input switching method and device, electronic equipment and storage medium - Google Patents

Input switching method and device, electronic equipment and storage medium Download PDF

Info

Publication number
CN111124222B
CN111124222B CN201911221443.2A CN201911221443A CN111124222B CN 111124222 B CN111124222 B CN 111124222B CN 201911221443 A CN201911221443 A CN 201911221443A CN 111124222 B CN111124222 B CN 111124222B
Authority
CN
China
Prior art keywords
smoothness
input
determining
judgment result
distance
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
Application number
CN201911221443.2A
Other languages
Chinese (zh)
Other versions
CN111124222A (en
Inventor
闫珂
赵明路
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 CN201911221443.2A priority Critical patent/CN111124222B/en
Publication of CN111124222A publication Critical patent/CN111124222A/en
Application granted granted Critical
Publication of CN111124222B publication Critical patent/CN111124222B/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
    • G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
    • G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
    • G06F3/04847—Interaction techniques to control parameter settings, e.g. interaction with sliders or dials
    • 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
    • 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
    • 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
    • G06F3/04886—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 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus

Landscapes

  • Engineering & Computer Science (AREA)
  • General Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • User Interface Of Digital Computer (AREA)

Abstract

The embodiment of the invention provides an input switching method, an input switching device, electronic equipment and a storage medium, wherein the method comprises the following steps: acquiring a starting track of a user; determining a distance judgment result based on the starting distance of the starting track and the starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real time; and/or determining a smoothness judgment result based on the smoothness of the starting track; an input mode is determined based on the distance determination result and/or the smoothness determination result. According to the method, the device, the electronic equipment and the storage medium provided by the embodiment of the invention, the starting distance threshold value is dynamically adjusted based on the historical input behavior of the user, so that the use habit and the use condition of the user are better adapted; in addition, the input mode is determined based on the smoothness of the starting track, the difference of different input modes is highlighted, the accurate judgment of the different input modes is realized, the false triggering of the input modes is avoided, and the user experience is improved.

Description

Input switching method and device, electronic equipment and storage medium
Technical Field
The present invention relates to the field of input methods, and in particular, to an input switching method and apparatus, an electronic device, and a storage medium.
Background
The input method is used as an interactive entrance between a user and an intelligent terminal, and has the characteristics of natural convenience, high efficiency, high accuracy and the like which are always pursued by the user. Handwriting input and key input are recognized by more and more users as two common input modes.
At present, the hand input and the key input can be simultaneously supported in the same interface of the soft keyboard, namely the hand input can be directly carried out by using the soft keyboard without switching to a special hand-writing keyboard, so that the input switching process is simplified, and the user experience is optimized.
However, in the soft keyboard interface, how to accurately determine whether the user needs to perform the handwriting input or the key input, so as to avoid the false triggering of the handwriting input, is still a problem to be solved by those skilled in the art.
Disclosure of Invention
The embodiment of the invention provides an input switching method, an input switching device, electronic equipment and a storage medium, which are used for solving the problem of high false triggering rate of handwriting input under the existing soft keyboard interface supporting both handwriting input and key input.
In a first aspect, an embodiment of the present invention provides an input switching method, including:
acquiring a starting track of a user;
determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real-time;
and/or determining a smoothness judgment result based on the smoothness of the starting track;
determining an input mode based on the distance determination result and/or the smoothness determination result.
Preferably, the determining a distance determination result based on the pen starting distance of the pen starting track and the pen starting distance threshold further includes:
determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user;
determining the starting distance threshold based on the current input behavior occurrence probability.
Preferably, the determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user specifically includes:
determining the influence probability of the current period based on the occurrence time of each historical input behavior in the current period;
determining the influence probability of the history period based on the input behavior occurrence probability of the history period and the end time of the history period; the historical period is a period before the current period;
and determining the occurrence probability of the current input behavior based on the current cycle influence probability and the historical cycle influence probability.
Preferably, the determining a smoothness judgment result based on the smoothness of the starting trajectory specifically includes:
determining a segmentation smoothness judgment result of any segmented handwriting based on the smoothness of any segmented handwriting in the starting trajectory;
and determining the smoothness judgment result based on the segmentation smoothness judgment result of each segmented handwriting in the starting track.
Preferably, the determining, based on the smoothness of any segmented handwriting in the initial trajectory, a segmentation smoothness determination result of any segmented handwriting specifically includes:
determining the predicted smoothness of any segmented handwriting based on a plurality of continuous segmented handwriting before any segmented handwriting in the starting trajectory;
and determining a segmentation smoothness judgment result of any segmented handwriting based on the smoothness of any segmented handwriting and the predicted smoothness of any segmented handwriting.
Preferably, the determining a judgment result of the smoothness of the segmentation of any segmented handwriting based on the smoothness of any segmented handwriting and the predicted smoothness of any segmented handwriting specifically includes:
calculating the difference ratio of the smoothness and the predicted smoothness of any segmented handwriting in the starting trajectory;
and determining a segmentation smoothness judgment result of any segmented handwriting based on the difference ratio and a preset difference ratio.
Preferably, the determining the smoothness determination result based on the segmentation smoothness determination result of each segmented handwriting in the initial trajectory specifically includes:
and if the segmentation smoothness judgment result of any segmented handwriting is the key input behavior, determining that the smoothness judgment result is the key input behavior.
Preferably, the determining an input mode based on the distance determination result and the smoothness determination result specifically includes:
if the distance judgment result is consistent with the smoothness judgment result, determining the input mode based on the distance judgment result and the smoothness judgment result;
and if the distance judgment result is different from the smoothness judgment result, determining the input mode based on the distance judgment result and the smoothness judgment result and the weights respectively corresponding to the distance judgment result and the smoothness judgment result.
Preferably, the method further comprises the following steps:
and under the handwriting input mode, if the user is detected to continuously click the delete key more than the preset number of times within the preset time, switching to the key input mode.
In a second aspect, an embodiment of the present invention provides an input switching apparatus, including:
the starting track acquiring unit is used for acquiring a starting track of a user;
the distance judgment unit is used for determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real-time;
and/or, a smoothness judgment unit, configured to determine a smoothness judgment result based on the smoothness of the pen-up trajectory;
an input switching unit for determining an input mode based on the distance determination result and/or the smoothness determination result.
In a third aspect, an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a bus, where the processor and the communication interface, the memory complete communication with each other through the bus, and the processor may call a logic instruction in the memory to perform the steps of the method provided in the first aspect.
In a fourth aspect, an embodiment of the present invention provides a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor, implements the steps of the method as provided in the first aspect.
According to the input switching method, the input switching device, the electronic equipment and the storage medium, the starting distance threshold value is dynamically adjusted based on the historical input behavior of the user, so that the use habit and the use condition of the user are better adapted; in addition, the input mode is determined based on the smoothness of the pen-starting track, and the difference of different input modes can be effectively highlighted, so that the different input modes can be accurately distinguished under a soft keyboard interface, the false triggering of the input modes is avoided, and the user experience is improved.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a diagram of a prior art soft keyboard interface supporting both handwriting input and keystroke input;
fig. 2 is a schematic flowchart of an input switching method according to an embodiment of the present invention;
FIG. 3 is a flowchart illustrating a method for determining a starting distance threshold according to an embodiment of the present invention;
fig. 4 is a schematic flowchart of a method for determining an occurrence probability of a current input behavior according to an embodiment of the present invention;
FIG. 5 is a flowchart illustrating a smoothness determination method according to an embodiment of the present invention;
FIG. 6 is a flowchart illustrating a method for determining a segmentation smoothness determination result according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of trajectory prediction according to an embodiment of the present invention;
fig. 8 is a schematic structural diagram of an input switching apparatus according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. 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 invention.
On a touch screen device, a user inputs characters by using pinyin keys of a soft keyboard, but in some special scenes, for example, when characters which cannot be read are written, handwriting is needed to realize input. The common practice in the past is that a user switches to a handwriting special keyboard for inputting, and then switches back to a pinyin keyboard for continuous inputting after completing inputting. With the development and progress of the technical field of input methods, the existing soft keyboard software can directly perform handwriting input by using a soft keyboard without switching to a special handwriting keyboard, so that the input switching process is simplified, and the user experience is optimized.
Fig. 1 is a schematic view of a soft keyboard interface supporting both handwriting input and key input in the prior art, and as shown in fig. 1, in a scenario where the same interface of the soft keyboard simultaneously supports both handwriting input and key input, it is necessary to determine an intention of a user touching, and determine whether the user wants to perform pinyin key input or handwriting input according to a certain determination rule, where accuracy of the determination rule directly affects use experience of the user.
It should be noted that, in the technical field of input methods, a soft keyboard refers to software for inputting characters by pinyin on a touch screen device; the method comprises the following steps that key input refers to the behavior of virtual pinyin key input by using a soft keyboard, and handwriting input refers to the input behavior of character recognition by recognizing character handwriting on the soft keyboard through touch sliding, wherein the handwriting input refers to the handwriting behavior on the soft keyboard which supports key input at the same time; the handwriting error touch refers to the situation that the original intention of key input on the soft keyboard is judged as the handwriting input by mistake, or the situation that a user enters a handwriting state due to an unintended touch screen; the starting of the pen refers to a stage in which the touch is started on the soft keyboard, but the handwriting input or the key input is not determined yet.
In the existing scheme, the soft keyboard judges the real input intention of a user through the pen starting speed of the user during pen starting, and distinguishes key input from handwriting input. The judgment method based on the starting speed is as follows:
in general, a user slides faster in handwriting input and slides slower in key input. Based on the method, the sliding speed of the user after starting the pen can be calculated, the user is determined to be performing handwriting input at a higher speed, and the user is determined to be performing key input at a lower speed. The key factor is to determine the speed threshold of the pen sliding, which is temporarily denoted as S. S is typically a fixed value, or several different thresholds in a stepwise manner, for manual selection by the user.
Although the scheme can judge the user intention to a certain extent, the used threshold values are temporary data and have no dynamic adjustment capability due to the consideration of difficulty and cost of implementation, and cannot be effectively avoided when the user touches by mistake, so that the user's key input operation is easily used as the wrongly-triggered handwriting input operation, and the user's text input experience is influenced. For example, when a user is in a crowded environment (such as on a bus) and uses a soft keyboard for input, the speed of key input changes, and the above scheme easily determines the key input behavior of the user as a handwriting input behavior, which leads to misunderstanding of the input intention of the user and reduces the user experience.
In addition, the scheme belongs to a static scheme, corresponding judgment rules on equipment with the same resolution are also the same, only limited sliding speed adjustment items can be provided for users to select, most users cannot frequently adjust the threshold value to match with the handwriting habits of the users, the scheme is difficult to adapt to the input habits of all the users, and the input intentions of the users cannot be accurately judged. For example, according to the rule that the user performs handwriting input when the sliding speed is greater than the fixed threshold, if the user performs the input at a higher speed when pressing the key and performs the input in a manner similar to sliding on a keyboard interface, the above scheme is adopted to easily determine the key input behavior as the handwriting input behavior by mistake.
In view of the foregoing problems, an embodiment of the present invention provides an input switching method, which may be used to implement switching between key and handwriting input, and may also be used to implement switching between other input modes that need to be implemented by a touch screen, and this is not specifically limited in the embodiment of the present invention. Fig. 2 is a schematic flow chart of an input switching method according to an embodiment of the present invention, and as shown in fig. 2, an execution main body of the method may be a soft keyboard, and the method includes:
step 210, obtaining the pen-out track of the user.
Here, the pen-starting track is input by the user through touching the soft keyboard, and the pen-starting track may include coordinates of each touch point in the pen-starting process of the user, and may further include a sequence of touching each touch point in the pen-starting process of the user, and the like, which is not specifically limited in this embodiment of the present invention. The initial stroke track may be used to determine the input intent of the user, such as whether a key input mode or a handwriting input mode is employed. It should be noted that the key input here may be pinyin key input, stroke key input, five-stroke key input, or english key input, etc.
Step 220, determining a distance judgment result based on the starting distance of the starting track and the starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real time.
Specifically, the pen-up distance, i.e., the distance length value of the touch slide of the pen-up trajectory, may be represented by the number of pixels or the remaining measurement units. The starting distance threshold is used for measuring the starting distance, the distance judgment result is used for representing the user input intention obtained based on the starting distance and the starting distance threshold, and the distance judgment result can be a key input behavior or a handwriting input behavior and the like. For example, when the starting distance is greater than or equal to the starting distance threshold, the distance determination result is the handwriting input behavior, otherwise, the distance determination result is the key input behavior.
It should be noted that, in the embodiment of the present invention, the starting distance threshold is dynamically adjustable. The historical input behavior of the user is input behavior of the user in an input mode which is clear before the current moment, such as historical key input behavior, historical handwriting input behavior and the like. Taking a historical handwriting input behavior as an example, after a user performs handwriting input on a soft keyboard, the user selects a handwritten recognition candidate word to be displayed on a screen, and then a historical handwriting behavior is formed and recorded, wherein the recorded relevant parameters can be the occurrence time of the historical handwriting behavior, the duration of the historical handwriting behavior and the like.
The historical input behavior is continuously updated along with the increase of the times of user input and the time, so that the input habits and the use condition changes of the user are dynamically reflected. Because the historical input behaviors are updated in real time, the starting distance threshold determined based on the historical input behaviors is also dynamically adjusted along with the real-time update of the historical input behaviors so as to adapt to the latest input habits and use conditions of users.
Therefore, before the user input intention is judged based on the starting distance threshold, the starting distance range of the user when the user applies different input modes can be obtained by analyzing the historical input behavior of the user updated in real time, and the dynamic adjustment of the starting distance threshold is further realized, or the probability that the user applies the corresponding input mode to input at the current moment can be predicted by analyzing the time of the historical input behavior of the user updated in real time, and the dynamic adjustment of the starting distance threshold is realized according to the probability that the user applies the corresponding input mode to input.
And step 230, determining a smoothness judgment result based on the smoothness of the pen starting track.
Specifically, when a user inputs by applying different input modes, the shapes of the starting tracks are usually distinguished, for example, in the handwriting input of Chinese characters, the strokes usually have a certain radian, and when the handwriting error touch is generated in the fast key typing, the strokes are usually shorter and straighter. Thus, the smoothness determination result may be determined based on the smoothness of the pen-up trajectory. Here, the smoothness of the initial trajectory is used to represent the smoothness of each segment of the trajectory formed by adjacent trajectory points in the initial trajectory. The smoothness judgment result is used for representing the user input intention obtained based on the starting trajectory smoothness, and the smoothness judgment result can be a key input behavior or a handwriting input behavior and the like.
It should be noted that, step 220 may not be executed to perform step 230, or step 230 may not be executed to perform step 220, or both step 220 and step 230 may be executed, which is not specifically limited in the embodiment of the present invention.
And step 240, determining an input mode based on the distance judgment result and/or the smoothness judgment result.
Specifically, the input mode is a mode that is finally determined that the user is currently using the input, and the input mode may be a key input mode or a handwriting input mode, and the like. In the case where step 230 is not performed in the step 220, the input mode may be determined according to the distance determination result obtained in the step 220; in the case where step 230 is performed without performing step 220, the input mode may be determined according to the smoothness determination result obtained in step 230; in the case where both step 220 and step 230 are performed, the input mode may be determined in combination with the distance determination result obtained in step 220 and the smoothness determination result obtained in step 230. After the input mode is determined, the determined input mode can be executed to realize the automatic switching of the input mode.
According to the method provided by the embodiment of the invention, the starting distance threshold value is dynamically adjusted based on the historical input behavior of the user, so that the use habit and the use condition of the user are better adapted; in addition, the input mode is determined based on the smoothness of the pen-starting track, and the difference of different input modes can be effectively highlighted, so that the different input modes can be accurately distinguished under a soft keyboard interface, the false triggering of the input modes is avoided, and the user experience is improved.
Based on the foregoing embodiment, fig. 3 is a schematic flowchart of a method for determining a starting distance threshold according to an embodiment of the present invention, as shown in fig. 3, in the method, before step 220, the method further includes:
step 201, determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user.
Specifically, after an input behavior corresponding to any input mode occurs, the probability that the input behavior corresponding to the input mode occurs again increases, and the influence of the historical input behavior corresponding to any input mode on the probability that the input behavior corresponding to the input mode occurs again decreases as the distance between the occurrence time of the historical input behavior and the current time increases.
The occurrence probability of the current input behavior is used for indicating the probability of the occurrence of the input behavior corresponding to any input mode at the current moment, the occurrence probability of the current input behavior is influenced by the historical input behavior, and the occurrence time of the historical input behavior determines the influence of the historical input behavior on the occurrence probability of the current input behavior. For example, the current handwriting behavior occurrence probability may be determined based on the occurrence time of the user's historical handwriting behavior, and the current key behavior occurrence probability may be determined based on the occurrence time of the user's historical key behavior.
Here, the historical input behaviors may include all input behaviors in one or more specific input modes within a preset time period, where the preset time period may be one week before the current time, one month before the current time, or the like, and this is not particularly limited in the embodiment of the present invention. According to the occurrence time and the current time of each historical input behavior, the influence of each historical input behavior on the occurrence probability of the current input behavior can be determined, and the occurrence probability of the current input behavior is further obtained.
In step 202, a starting distance threshold is determined based on the occurrence probability of the current input behavior.
For example, the higher the occurrence probability of the current handwriting behavior, the smaller the corresponding pen-up distance threshold, and the lower the occurrence probability of the current handwriting behavior, the larger the corresponding pen-up distance threshold. For another example, the higher the occurrence probability of the current key behavior, the larger the corresponding attack distance threshold, and the lower the occurrence probability of the current key behavior, the smaller the corresponding attack distance threshold.
According to the method provided by the embodiment of the invention, the occurrence probability of the current input behavior is determined based on the occurrence time of the historical input behavior of the user, so that the starting distance threshold is obtained, the dynamic adjustment of the starting distance threshold is realized, and the use habit and the use condition of the user can be better adapted.
Based on any of the above embodiments, fig. 4 is a schematic flowchart of a method for determining occurrence probability of a current input behavior according to an embodiment of the present invention, as shown in fig. 4, in the method, step 201 specifically includes:
step 2011, determine the current cycle impact probability based on the occurrence time of each historical input activity within the current cycle.
Step 2012, determining the influence probability of the history period based on the input behavior occurrence probability of the history period and the end time of the history period; the history period is a period before the current period.
Specifically, the length of the period is set in advance, for example, one week or 3 days or the like. The current period refers to a period in which the current time is located, the historical period refers to a period between the current periods, and the historical period may include one or more periods before the current period.
For each historical input behavior which has occurred in the current period, the influence of each historical input behavior which has been sent in the current period on the occurrence probability of the current input behavior, that is, the influence probability of the current period can be determined according to the occurrence time of each historical input behavior.
For the historical period, each period in the historical period corresponds to an input behavior occurrence probability, the input behavior occurrence probability of the historical period is determined based on the occurrence time of the historical input behavior sent in the historical period in the period, a specific determination method may refer to the current period, and details are not repeated here. Based on the occurrence probability of the input behavior of each period in the historical period and the end time of each period in the historical period, the influence of each period in the historical period on the occurrence probability of the current input behavior can be obtained, and further the influence probability of the historical period can be obtained.
And 2013, determining the occurrence probability of the current input behavior based on the current cycle influence probability and the historical cycle influence probability.
Specifically, after the current period influence probability and the historical period influence probability are obtained, the current period influence probability and the historical period influence probability can be accumulated, and then the occurrence probability of the current input behavior is determined.
For example, historical handwriting behaviors of a user are counted, and the historical handwriting behaviors are divided into historical handwriting behaviors of a current period and historical handwriting behaviors of a historical period according to occurrence time of each historical handwriting behavior. For the historical handwriting behaviors in the current period, the influence of each historical handwriting behavior on the occurrence probability of the current handwriting behavior can be calculated according to the time difference between the occurrence time of each historical handwriting behavior and the current time and by combining a time decay function, and the influence probability of the current period is obtained by superposition. For the historical handwriting behavior in the historical period, the influence of the historical handwriting behavior in the historical period on the occurrence probability of the current handwriting behavior can be calculated according to the time difference between the end time of the historical period and the current time and by combining a time decay function, so that the influence probability of the historical period can be obtained. And then determining the occurrence probability of the current handwriting behavior based on the current period influence probability and the historical period influence probability. Here, the time decay function may be an exponential function.
The probability of occurrence of the current handwriting behavior can be determined by the following formula:
Figure BDA0002300968110000106
in the formula, FcnThe probability of the nth handwriting in the period c, that is, the current handwriting occurrence probability. T isnIs the current time, TiThe moment of the ith occurrence of handwriting in the period c, 0<i<n。Fc-1I.e. probability of occurrence of handwriting of period c-1, T0Is the start time of period c, i.e., the end time of period c-1.
Figure BDA0002300968110000102
In order for the current period to affect the probability,
Figure BDA0002300968110000103
the probability is influenced for the history period.
The current period influence probability is obtained by superposing the influence of each handwriting action on the current handwriting action occurrence probability
Figure BDA0002300968110000104
The historical period influence probability is obtained by dividing the period c-1Probability of occurrence of handwriting Fc-1Influence of period c-1 on occurrence probability of current handwriting behavior
Figure BDA0002300968110000105
And (4) multiplying the two. In the above formula, by
Figure BDA0002300968110000111
May determine the distance T between the time of occurrence of the historical handwriting and the current timen-TiAnd the influence on the current handwriting behavior probability is in a negative exponential relation, namely the longer the current moment is, the smaller the influence on the current handwriting behavior probability is. The historical handwriting behavior can be quantized into the current handwriting behavior occurrence probability which can be used for dynamically adjusting the starting distance threshold value through the formula, so that the accurate adjustment of the starting distance threshold value is realized, and the accurate switching of the input mode is realized.
Correspondingly, step 202 specifically includes: the starting distance threshold is determined based on the current input behavior occurrence probability and a baseline starting distance threshold. For example, the starting distance threshold may be determined by the following formula:
Figure BDA0002300968110000112
in the formula, LcnThe distance threshold value of the nth stroke in the period c is represented, if the distance threshold value is exceeded, the distance judgment result is the handwriting input behavior, and if the distance threshold value is not exceeded, the distance judgment result is the key input behavior; l is a fixed reference starting distance threshold, and can be determined by counting starting distances of each time in historical handwriting behaviors;
Figure BDA0002300968110000113
is to FcnA value of the false triggering measure, F, intermediate between the maximum dynamic threshold and the minimum dynamic threshold, obtained by discretizingcnAnd
Figure BDA0002300968110000114
the negative correlation is presented, and the negative correlation is presented,Fcnthe larger the size, the corresponding
Figure BDA0002300968110000115
The smaller.
Based on any of the above embodiments, fig. 5 is a schematic flowchart of a smoothness determination method according to an embodiment of the present invention, as shown in fig. 5, in the method, step 220 specifically includes:
and step 221, determining a segmentation smoothness judgment result of any segmented handwriting in the starting trajectory based on the smoothness of the segmented handwriting.
Step 222, determining a smoothness judgment result based on the segmentation smoothness judgment result of each segmented handwriting in the starting track.
Specifically, the pen-starting trajectory may be formed by a plurality of segmented scripts, and smoothness of each segmented script in the pen-starting trajectory is analyzed respectively, so that a segmented smoothness judgment result corresponding to each segmented script can be obtained. For example, a smoothness interval may be preset for any segmented handwriting, if the smoothness of the segmented handwriting is not within the corresponding smoothness interval, the segmented smoothness judgment result corresponding to the segmented handwriting is determined to be a key input behavior, and if the smoothness of the segmented handwriting is within the corresponding smoothness interval, the segmented smoothness judgment result corresponding to the segmented handwriting is determined to be a handwriting input behavior.
After the segmentation smoothness judgment result corresponding to each segmentation handwriting is obtained, the segmentation smoothness judgment result corresponding to each segmentation handwriting can be subjected to summary analysis, and the smoothness judgment result for the whole starting trajectory is determined.
Based on any of the above embodiments, fig. 6 is a schematic flowchart of a method for determining a segmentation smoothness judgment result according to an embodiment of the present invention, as shown in fig. 6, in the method, step 221 specifically includes:
step 2211, based on a plurality of continuous segmented handwriting before any segmented handwriting in the initial stroke, determining the predicted smoothness of the segmented handwriting.
Specifically, for any segmented handwriting, based on a plurality of continuous segmented handwriting before the segmented handwriting, the trend of the segmented handwriting in a relatively smooth state can be predicted, and the predicted smoothness of the segmented handwriting is further obtained.
Fig. 7 is a schematic diagram of track prediction according to an embodiment of the present invention, where each black dot in fig. 7 represents a trace point in the initial trace, which is a trace point [ x ] respectively0,y0]、[x1,y1]、[x2,y2]、[x3,y3]. By handwriting point [ x ]2,y2]And [ x ]3,y3]The segmented handwriting in between is taken as an example, and the white dotted circle represents the predicted [ x ]3,y3]Is [ x ', y']。
The smoothness of the segmented handwriting can be represented by the curvature between two stroke points. The formula for the curvature is as follows:
Figure BDA0002300968110000121
whereby [ x ]0,y0]And [ x ]1,y1]The curvature of the segmented handwriting in between is r1，[x1,y1]And [ x ]2,y2]The curvature of the segmented handwriting in between is r2According to r1And r2Can be paired with [ x2,y2]And [ x ]3,y3]The curvature of the segmented handwriting can be predicted by an equal ratio principle, an equal difference principle or other principles, wherein the equal difference principle is taken as an example, x2,y2]And [ x ]3,y3]The predicted smoothness of the segmented handwriting in between, i.e. the predicted curvature r' ═ r2+(r2-r1)。
And 2212, determining a judgment result of the segmentation smoothness of the segmented handwriting based on the smoothness of the segmented handwriting and the predicted smoothness of the segmented handwriting.
Specifically, the actual smoothness of the segmented handwriting is compared with the predicted smoothness obtained through prediction, whether the difference value of the actual smoothness of the segmented handwriting and the predicted smoothness is within a preset difference value interval or whether the percentage of the difference value of the actual smoothness of the segmented handwriting and the predicted smoothness is within a preset range is judged, and whether the segmented handwriting is bent greatly is further judged, so that a segmented smoothness judgment result is obtained.
Based on any of the above embodiments, in this method, step 2212 specifically includes: calculating the difference ratio of the smoothness of any segmented handwriting in the initial stroke track and the predicted smoothness; and determining the segmentation smoothness judgment result of the segmented handwriting based on the difference ratio and a preset difference ratio.
For example, when distinguishing between key input and handwriting input, if the difference ratio is greater than a preset difference ratio, the segmentation smoothness judgment result of the segmented handwriting is determined as the key input behavior, otherwise, the segmentation smoothness judgment result of the segmented handwriting is determined as the handwriting input behavior.
By handwriting point [ x ]2,y2]And [ x ]3,y3]The smoothness is r by taking the segmented handwriting in between as an example3The predicted smoothness is r', and the difference between the predicted smoothness and the predicted smoothness is shown as follows:
Figure BDA0002300968110000131
if the preset difference ratio is 30%, if the difference ratio is larger than the preset difference ratio, determining that the judgment result of the segmentation smoothness of the segmented handwriting is the key input behavior; otherwise, determining that the judgment result of the segmentation smoothness of the segmented handwriting is the handwriting input behavior. It should be noted that the value of the preset difference ratio can be adjusted according to actual conditions.
Based on any of the above embodiments, in the method, step 222 specifically includes: and if the judgment result of the segmentation smoothness of any segmented handwriting is the key input behavior, determining the smoothness judgment result as the key input behavior.
Specifically, in the judgment of the segmentation smoothness of the initial stroke track, if the segmentation smoothness judgment result of each segmentation handwriting in the initial stroke track is a handwriting input behavior, determining that the smoothness judgment result is the handwriting input behavior; however, when the judgment result of the segmentation smoothness of the segmented handwriting is the key input behavior, the fact that the starting trajectory has large bending is indicated, and the judgment result of the smoothness is determined to be the key input behavior.
Based on any of the above embodiments, in the method, step 240 specifically includes: if the distance judgment result is consistent with the smoothness judgment result, determining an input mode based on the distance judgment result and the smoothness judgment result; and if the distance judgment result and the smoothness judgment result are different, determining the input mode based on the distance judgment result and the smoothness judgment result as well as the weights respectively corresponding to the distance judgment result and the smoothness judgment result.
Specifically, when the distance determination result and the smoothness determination result exist at the same time, the input mode may be determined in two cases:
when the distance judgment result is consistent with the smoothness judgment result, the corresponding input mode can be determined directly according to the behavior indicated by the distance judgment result and the smoothness judgment result; for example, if both the distance determination result and the smoothness determination result are the key input behaviors, the corresponding input mode is the key input mode, and if both the distance determination result and the smoothness determination result are the handwriting input behaviors, the corresponding input mode is the handwriting input mode.
When the distance determination result and the smoothness determination result are different, a further determination may be made based on a weight of both set in advance, thereby determining the input mode. For example, assuming that the weight of the distance determination result is 60% and the weight of the smoothness determination result is 40%, when the distance determination result is a key input behavior and the smoothness determination result is a handwriting input behavior, calculating a difference ratio P1 between the stroke starting distance and a stroke starting distance threshold, and if P1> (1-60%), determining that the input mode is a key input mode; when the distance judgment result is the handwriting input behavior and the smoothness judgment result is the key input behavior, calculating a smoothness difference ratio of the smoothness of the segmented handwriting and the predicted smoothness, and calculating a difference ratio P2 of the smoothness difference ratio and a preset difference ratio, wherein if P2> (1-40%), the input mode is determined to be the key input mode; otherwise, determining the input mode as a handwriting input mode.
In addition, in the existing input method, some special keys on the soft keyboard are not protected, so that further errors after the user triggers handwriting by mistake are easily caused. For example, after the user is determined by the input method software to perform handwriting input, the user wants to perform a deletion operation on the handwriting input triggered by mistake, and continues to perform a click operation on the deletion key of the soft keyboard.
In this regard, based on any of the above embodiments, the method further comprises: and under the handwriting input mode, if the user is detected to continuously click the delete key more than the preset number of times within the preset time, switching to the key input mode.
Specifically, the preset time is a preset period of time. After the input mode is determined to be the handwriting input mode, if the fact that the user continuously clicks the delete key within the preset time is detected, the fact that handwriting mistaken touch occurs is determined, the user tries to return to the key input mode, the handwriting input mode is released at the moment, the input mode is switched to the key input mode, the delete operation of the user is responded, and therefore delete cost after the handwriting mistaken touch can be reduced.
Based on any one of the embodiments, an embodiment of the present invention provides an input switching method, including the following steps:
first, the pen-up trajectory of the user is acquired.
Secondly, determining the occurrence probability of the current handwriting behavior based on the occurrence time of the historical handwriting behavior of the user, thereby determining the starting distance threshold. And comparing the starting distance of the starting track with a starting distance threshold, if the starting distance is greater than or equal to the starting distance threshold, determining that the distance judgment result is the handwriting input behavior, otherwise, determining that the distance judgment result is the key input behavior, and calculating a difference value ratio P1 between the starting distance and the starting distance threshold compared with the starting distance threshold.
In addition, for each segmented handwriting in the initial trajectory, smoothness and predicted smoothness of each segmented handwriting are calculatedObtaining the difference ratio of the smoothness of each segmented handwriting and the predicted smoothness; if the smoothness difference ratio of the smoothness of each segmented handwriting and the smoothness difference ratio of the predicted smoothness is less than or equal to a preset difference ratio, determining the smoothness judgment result as a handwriting input behavior; otherwise, determining the smoothness judgment result as the key input behavior, and calculating a difference ratio P2 between the smoothness difference ratio and a preset difference ratio. Suppose in FIG. 7, a locus point [ x ]2,y2]And [ x ]3,y3]The smoothness of the segmented handwriting in between is r3If the predicted smoothness is r' and the difference ratio between the predicted smoothness and the predicted smoothness is greater than the preset difference ratio of 0.3, P2 is represented by the following formula:
Figure BDA0002300968110000151
after obtaining the distance determination result and the smoothness determination result, there are four cases as follows:
(1) the distance judgment result and the smoothness judgment result are both key input behaviors, and the corresponding input mode is a key input mode;
(2) the distance judgment result and the smoothness judgment result are both handwriting input behaviors, and the corresponding input mode is a handwriting input mode;
(3) the distance judgment result is a key input behavior, the smoothness judgment result is a handwriting input behavior, and if the distance judgment result is P1> (1-alpha), the input mode is determined to be a key input mode; otherwise, determining the input mode as a handwriting input mode; where α is the weight of the distance determination result;
(4) the distance judgment result is a handwriting input behavior, the smoothness judgment result is a key input behavior, and if the distance judgment result is P2> (1-beta), the input mode is determined to be a key input mode; otherwise, determining the input mode as a handwriting input mode; where β is a weight of the smoothness determination result, and α + β is 1.
In addition, after the input mode is determined to be the handwriting input mode, if the fact that the user continuously clicks the delete key within the preset time is detected, the fact that the handwriting is mistakenly touched is determined, the handwriting input mode is released, the input mode is switched to the key input mode, the delete operation of the user is responded, and therefore delete cost after the handwriting is mistakenly touched can be reduced.
According to the method provided by the embodiment of the invention, the starting distance threshold value is dynamically adjusted based on the historical handwriting behavior of the user, so that the use habit and the use condition of the user are better adapted; in addition, the input mode is determined based on the smoothness of the starting track, so that the difference between key input and handwriting input can be effectively highlighted, the accurate judgment of the key input and the handwriting input under a soft keyboard interface is realized, the false triggering of the handwriting input is avoided, and the user experience is improved.
Based on any of the above embodiments, fig. 8 is a schematic structural diagram of an input switching apparatus according to an embodiment of the present invention, as shown in fig. 8, the apparatus includes a starting trajectory obtaining unit 810, an input switching unit 840, a distance determining unit 820 and/or a smoothness determining unit 830;
the starting trajectory acquiring unit 810 is configured to acquire a starting trajectory of a user;
the distance judgment unit 820 is used for determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real-time;
the smoothness judgment unit 830 is configured to determine a smoothness judgment result based on the smoothness of the pen-up trajectory;
the input switching unit 840 is configured to determine an input mode based on the distance determination result and/or the smoothness determination result.
According to the device provided by the embodiment of the invention, the starting distance threshold value is dynamically adjusted based on the historical input behavior of the user, so that the use habit and the use condition of the user are better adapted; in addition, the input mode is determined based on the smoothness of the pen-starting track, and the difference of different input modes can be effectively highlighted, so that the different input modes can be accurately distinguished under a soft keyboard interface, the false triggering of the input modes is avoided, and the user experience is improved.
Based on any embodiment above, the apparatus further comprises:
a behavior probability determination unit for determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user;
and the distance threshold value determining unit is used for determining the starting distance threshold value based on the current input behavior occurrence probability.
Based on any of the above embodiments, in the apparatus, the behavior probability determining unit is specifically configured to:
determining the influence probability of the current period based on the occurrence time of each historical input behavior in the current period;
determining the influence probability of the history period based on the input behavior occurrence probability of the history period and the end time of the history period; the historical period is a period before the current period;
and determining the occurrence probability of the current input behavior based on the current cycle influence probability and the historical cycle influence probability.
In any of the above embodiments, in the apparatus, the smoothness determining unit 830 includes:
the segmentation judgment subunit is used for determining a segmentation smoothness judgment result of any segmented handwriting based on the smoothness of any segmented handwriting in the starting trajectory;
and the integral judgment subunit is used for determining the smoothness judgment result based on the segmented smoothness judgment result of each segmented handwriting in the starting track.
Based on any one of the above embodiments, in the apparatus, the segmentation judgment subunit includes:
the smoothness prediction module is used for determining the predicted smoothness of any segmented handwriting based on a plurality of continuous segmented handwriting before any segmented handwriting in the starting trajectory;
and the smoothness judgment module is used for determining the judgment result of the segmentation smoothness of any segmented handwriting based on the smoothness of any segmented handwriting and the predicted smoothness of any segmented handwriting.
Based on any one of the embodiments, in the apparatus, the smoothness determining module is specifically configured to:
calculating the difference ratio of the smoothness and the predicted smoothness of any segmented handwriting in the starting trajectory;
and determining a segmentation smoothness judgment result of any segmented handwriting based on the difference ratio and a preset difference ratio.
Based on any one of the above embodiments, in the apparatus, the overall judgment subunit is specifically configured to:
and if the segmentation smoothness judgment result of any segmented handwriting is the key input behavior, determining that the smoothness judgment result is the key input behavior.
Based on any of the above embodiments, in the apparatus, the input switching unit 840 is specifically configured to:
if the distance judgment result is consistent with the smoothness judgment result, determining the input mode based on the distance judgment result and the smoothness judgment result;
and if the distance judgment result is different from the smoothness judgment result, determining the input mode based on the distance judgment result and the smoothness judgment result and the weights respectively corresponding to the distance judgment result and the smoothness judgment result.
Based on any embodiment above, the apparatus further comprises:
and the deletion switching unit is used for switching to the key input mode if detecting that the user continuously clicks the deletion key for more than a preset number of times within a preset time under the handwriting input mode.
Fig. 9 is a schematic structural diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 9, the electronic device may include: a processor (processor)910, a communication Interface (Communications Interface)920, a memory (memory)930, and a communication bus 940, wherein the processor 910, the communication Interface 920, and the memory 930 communicate with each other via the communication bus 940. Processor 910 may invoke logic instructions in memory 930 to perform the following method: acquiring a starting track of a user; determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real-time; and/or determining a smoothness judgment result based on the smoothness of the starting track; determining an input mode based on the distance determination result and/or the smoothness determination result.
Furthermore, the logic instructions in the memory 930 may be implemented in software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Embodiments of the present invention further provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the method provided in the foregoing embodiments when executed by a processor, and the method includes: acquiring a starting track of a user; determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the starting distance threshold is determined based on historical input behavior of the user, the historical input behavior being updated in real-time; and/or determining a smoothness judgment result based on the smoothness of the starting track; determining an input mode based on the distance determination result and/or the smoothness determination result.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.

Claims (10)

1. An input switching method, comprising:
acquiring a starting track of a user;
determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the pen-up distance is a distance length value of a touch swipe of a pen-up trajectory, the pen-up distance threshold is determined based on historical input behavior of the user, the historical input behavior is updated in real-time;
determining a smoothness judgment result based on the smoothness of the starting track;
determining an input mode based on the distance determination result and the smoothness determination result;
the determining a distance judgment result based on the starting distance of the starting track and the starting distance threshold comprises:
if the starting distance is larger than or equal to the starting distance threshold, determining that the distance judgment result is a handwriting input behavior, otherwise, determining that the distance judgment result is a key input behavior;
the determining a distance judgment result based on the starting distance of the starting trajectory and the starting distance threshold further includes:
determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user;
determining the starting distance threshold based on the current input behavior occurrence probability;
the determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user specifically includes:
determining the influence probability of the current period based on the occurrence time of each historical input behavior in the current period;
determining the influence probability of the history period based on the input behavior occurrence probability of the history period and the time difference between the end time of the history period and the current time, and combining a time decay function; the historical period is a period before the current period;
and determining the occurrence probability of the current input behavior based on the current cycle influence probability and the historical cycle influence probability.
2. The input switching method according to claim 1, wherein the determining a smoothness determination result based on the smoothness of the initial trajectory specifically includes:
determining a segmentation smoothness judgment result of any segmented handwriting based on the smoothness of any segmented handwriting in the starting trajectory;
and determining the smoothness judgment result based on the segmentation smoothness judgment result of each segmented handwriting in the starting track.
3. The input switching method according to claim 2, wherein the determining a judgment result of the smoothness of the segmentation of any segmented handwriting based on the smoothness of any segmented handwriting in the initial trajectory specifically comprises:
determining the predicted smoothness of any segmented handwriting based on a plurality of continuous segmented handwriting before any segmented handwriting in the starting trajectory;
and determining a segmentation smoothness judgment result of any segmented handwriting based on the smoothness of any segmented handwriting and the predicted smoothness of any segmented handwriting.
4. The input switching method according to claim 3, wherein the determining a judgment result of the smoothness of the segmentation of any segmented handwriting based on the smoothness of any segmented handwriting and the predicted smoothness of any segmented handwriting specifically comprises:
calculating the difference ratio of the smoothness and the predicted smoothness of any segmented handwriting in the starting trajectory;
and determining a segmentation smoothness judgment result of any segmented handwriting based on the difference ratio and a preset difference ratio.
5. The input switching method according to claim 2, wherein the determining the smoothness determination result based on the smoothness determination result of each segmented handwriting in the initial trajectory specifically includes:
and if the segmentation smoothness judgment result of any segmented handwriting is the key input behavior, determining that the smoothness judgment result is the key input behavior.
6. The input switching method according to any one of claims 1 to 5, wherein the determining an input mode based on the distance determination result and the smoothness determination result specifically includes:
if the distance judgment result is consistent with the smoothness judgment result, determining the input mode based on the distance judgment result and the smoothness judgment result;
and if the distance judgment result is different from the smoothness judgment result, determining the input mode based on the distance judgment result and the smoothness judgment result and the weights respectively corresponding to the distance judgment result and the smoothness judgment result.
7. The input switching method according to any one of claims 1 to 5, further comprising:
and under the handwriting input mode, if the user is detected to continuously click the delete key more than the preset number of times within the preset time, switching to the key input mode.
8. An input switching device, comprising:
the starting track acquiring unit is used for acquiring a starting track of a user;
the distance judgment unit is used for determining a distance judgment result based on the starting distance of the starting track and a starting distance threshold; wherein the pen-up distance is a distance length value of a touch swipe of a pen-up trajectory, the pen-up distance threshold is determined based on historical input behavior of the user, the historical input behavior is updated in real-time;
the smoothness judgment unit is used for determining a smoothness judgment result based on the smoothness of the pen starting track;
an input switching unit for determining an input mode based on the distance determination result and the smoothness determination result;
wherein the distance determination unit is specifically configured to:
if the starting distance is larger than or equal to the starting distance threshold, determining that the distance judgment result is a handwriting input behavior, otherwise, determining that the distance judgment result is a key input behavior;
further comprising:
a behavior probability determination unit for determining the occurrence probability of the current input behavior based on the occurrence time of the historical input behavior of the user;
a distance threshold determination unit, configured to determine the starting distance threshold based on the current input behavior occurrence probability;
the behavior probability determination unit is specifically configured to:
determining the influence probability of the current period based on the occurrence time of each historical input behavior in the current period;
determining the influence probability of the history period based on the input behavior occurrence probability of the history period and the time difference between the end time of the history period and the current time, and combining a time decay function; the historical period is a period before the current period;
and determining the occurrence probability of the current input behavior based on the current cycle influence probability and the historical cycle influence probability.
9. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the input switching method according to any one of claims 1 to 7 when executing the program.
10. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the input switching method according to any one of claims 1 to 7.
CN201911221443.2A 2019-12-03 2019-12-03 Input switching method and device, electronic equipment and storage medium Active CN111124222B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201911221443.2A CN111124222B (en) 2019-12-03 2019-12-03 Input switching method and device, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201911221443.2A CN111124222B (en) 2019-12-03 2019-12-03 Input switching method and device, electronic equipment and storage medium

Publications (2)

Publication Number Publication Date
CN111124222A CN111124222A (en) 2020-05-08
CN111124222B true CN111124222B (en) 2022-02-01

Family

ID=70497303

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201911221443.2A Active CN111124222B (en) 2019-12-03 2019-12-03 Input switching method and device, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN111124222B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN112801239B (en) * 2021-01-28 2023-11-21 科大讯飞股份有限公司 Input recognition method, input recognition device, electronic equipment and storage medium

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101620480A (en) * 2008-06-30 2010-01-06 戴静芬 Method for realizing handwritten stroke input on touch screen
CN102184074A (en) * 2011-04-21 2011-09-14 安徽科大讯飞信息科技股份有限公司 Keyboard, automatic hand input switching method and device and mobile terminal
CN102193736A (en) * 2011-04-21 2011-09-21 安徽科大讯飞信息科技股份有限公司 Input method and system supporting multimode automatic switching
CN104793727A (en) * 2014-01-21 2015-07-22 安徽科大讯飞信息科技股份有限公司 Method and system for achieving individual multi-mode input
US10101849B2 (en) * 2016-02-17 2018-10-16 Boe Technology Group Co., Ltd. Touch monitoring method, touch monitoring device, and terminal
CN108700996A (en) * 2016-02-23 2018-10-23 迈思慧公司 System and method for multi input management

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101118472B (en) * 2006-07-31 2010-05-12 联想移动通信科技有限公司 Device and method supporting hand-written input and keyboard input
CN106412223A (en) * 2016-02-21 2017-02-15 魏新成 Method and system for dial-up search through direct handwriting input on virtual dialing pad

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101620480A (en) * 2008-06-30 2010-01-06 戴静芬 Method for realizing handwritten stroke input on touch screen
CN102184074A (en) * 2011-04-21 2011-09-14 安徽科大讯飞信息科技股份有限公司 Keyboard, automatic hand input switching method and device and mobile terminal
CN102193736A (en) * 2011-04-21 2011-09-21 安徽科大讯飞信息科技股份有限公司 Input method and system supporting multimode automatic switching
CN104793727A (en) * 2014-01-21 2015-07-22 安徽科大讯飞信息科技股份有限公司 Method and system for achieving individual multi-mode input
US10101849B2 (en) * 2016-02-17 2018-10-16 Boe Technology Group Co., Ltd. Touch monitoring method, touch monitoring device, and terminal
CN108700996A (en) * 2016-02-23 2018-10-23 迈思慧公司 System and method for multi input management

Also Published As

Publication number Publication date
CN111124222A (en) 2020-05-08

Similar Documents

Publication Publication Date Title
US11868609B2 (en) Dynamic soft keyboard
US8922489B2 (en) Text input using key and gesture information
CA2514470C (en) System and method for continuous stroke word-based text input
US10585583B2 (en) Method, device, and terminal apparatus for text input
EP2696273B1 (en) Responding to selection of a displayed character string
CN108700996B (en) System and method for multiple input management
JP2018515817A (en) How to improve control by combining eye tracking and speech recognition
US20130120282A1 (en) System and Method for Evaluating Gesture Usability
KR20070114329A (en) Virtual keyboard system with automatic correction
US9098184B2 (en) Information processing apparatus, information processing method and medium for storing information processing program
KR20180064371A (en) System and method for recognizing multiple object inputs
CN107085471B (en) Input method error correction method and device based on user input speed
US8436829B1 (en) Touchscreen keyboard simulation for performance evaluation
CN103713845B (en) Method for screening candidate items and device thereof, text input method and input method system
CN113867521B (en) Handwriting input method and device based on gesture visual recognition and electronic equipment
CN111124222B (en) Input switching method and device, electronic equipment and storage medium
CN107797676B (en) Single character input method and device
CN107132927B (en) Input character recognition method and device for recognizing input characters
CN110554780A (en) sliding input method and device
CN113190160A (en) Input error correction method, computing device and medium for analyzing hand tremor false touch
Udapola et al. Braille messenger: Adaptive learning based non-visual touch screen text input for the blind community using braille
CN111913646A (en) Information sending method and device
CN109758763A (en) Character input method and device based on game pad
Mock et al. KeyValuate: A framework for rapid evaluation of adaptive keyboards on touchscreens
CN112163400A (en) Information processing method and device

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