CN108469912A - A kind of character input method and system - Google Patents
A kind of character input method and system Download PDFInfo
- Publication number
- CN108469912A CN108469912A CN201810102902.4A CN201810102902A CN108469912A CN 108469912 A CN108469912 A CN 108469912A CN 201810102902 A CN201810102902 A CN 201810102902A CN 108469912 A CN108469912 A CN 108469912A
- Authority
- CN
- China
- Prior art keywords
- word
- pen
- user
- write
- character input
- 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.)
- Pending
Links
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
- G06F3/03—Arrangements for converting the position or the displacement of a member into a coded form
- G06F3/033—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor
- G06F3/0354—Pointing devices displaced or positioned by the user, e.g. mice, trackballs, pens or joysticks; Accessories therefor with detection of 2D relative movements between the device, or an operating part thereof, and a plane or surface, e.g. 2D mice, trackballs, pens or pucks
- G06F3/03545—Pens or stylus
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/107—Static hand or arm
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Multimedia (AREA)
- User Interface Of Digital Computer (AREA)
- Character Discrimination (AREA)
Abstract
The invention discloses a kind of character input method and systems, are related to machine learning field.This method includes:When the attitude data that user using pen when being write, and acquisition pen moves;Analyzing processing is carried out to attitude data according to preset processing model, obtains character features;Corresponding word is matched from preset database according to character features, obtains the word that user is write.A kind of character input method provided by the invention and system, by to user when being write using pen, the attitude data that pen movement generates is analyzed and is handled, obtain the character features for the word that user is write, and corresponding word is matched from database accordingly, user is realized when writing using pen, so that it may the word that user is write is input in the devices such as computer in real time to facilitate, improve the convenience of word input.
Description
Technical field
The present invention relates to machine learning field more particularly to a kind of character input method and systems.
Background technology
Currently, in existing input device, in addition to traditional keyboard, there are handwriting pad, textual scan pen etc..It is existing
Input unit all has many use spaces and the limitation using tool in use, and user can not write with a pen on paper
Word convenient be input in computer in real time.For example, handwriting pad can only be write on fixed plate, or even also need to spy
Fixed electronic pen, it is very inconvenient during use, in another example, textual scan pen can only carry out the word finished writing on paper
Scanning, it is also very inconvenient during use.
Invention content
The technical problem to be solved by the present invention is in view of the deficiencies of the prior art, provide a kind of character input method and be
System.
The technical solution that the present invention solves above-mentioned technical problem is as follows:
A kind of character input method, including:
When user using pen when writing, the attitude data of the pen movement is obtained;
Analyzing processing is carried out to the attitude data according to preset processing model, obtains character features;
Corresponding word is matched from preset database according to the character features, obtains the text that the user is write
Word.
The beneficial effects of the invention are as follows:A kind of character input method provided by the invention, by making to write with a pen to user
When word, the attitude data that pen movement generates is analyzed and is handled, and obtains the character features for the word that user is write, and accordingly from
Corresponding word is matched in database, realize user when writing using pen, so that it may in real time be write user with facilitating
Word is input in the devices such as computer, improves the convenience of word input.
Based on the above technical solution, the present invention can also be improved as follows.
Further, described that analyzing processing is carried out to the attitude data according to preset processing model, obtain word spy
Before sign, further include:
Denoising is carried out to the attitude data.
Advantageous effect using above-mentioned further scheme is:It, can by carrying out denoising to collected attitude data
To improve the availability of attitude data, the identification process of word can be simplified.
Further, described when user using pen when being write, before the attitude data for obtaining the pen movement, also wrap
It includes:
The jitter amplitude for judging the pen obtains the use when the jitter amplitude of the pen is more than default jitter amplitude
It writes using the pen at family.
Advantageous effect using above-mentioned further scheme is:It is detected, can be judged by the jitter amplitude to pen
The state of pen is to write or vacantly, can realize that just the attitude data of acquisition pen, reduces and provided to hardware when pen is when writing
The occupancy in source, the convenience for improving the accuracy of identification and using.
Further, described when user using pen when being write, before the attitude data for obtaining the pen movement, also wrap
It includes:
Multiple users are obtained to carry out repeatedly writing obtained lteral data respectively;
Machine learning algorithm training is carried out to the processing model according to the lteral data.
Advantageous effect using above-mentioned further scheme is:Machine learning by carrying out great amount of samples to processing model is calculated
Method is trained, and processing Model Identification can be made to go out the word of different fonts different-style, can improve the accuracy and practicality of identification
Property.
Further, described that machine learning algorithm training is carried out to the processing model according to the lteral data, specifically
Including:
When the lteral data is first kind word, using the first kind word as sample, to the processing
Model carries out machine learning algorithm training;
When the lteral data is Second Type word, using the stroke of the Second Type word as sample, to institute
It states processing model and carries out machine learning algorithm training, then by the combination of strokes after training at word;
Wherein, the first kind word is the word not being made of stroke, and the Second Type word is by group of strokes
At word.
Advantageous effect using above-mentioned further scheme is:By judging word to be identified, when to be identified
When word is made of stroke, machine learning training is carried out to the stroke of word and is combined into word after identifying stroke, it can
It realizes the identification that the machines such as Chinese character are difficult to word, can save the time, improve working efficiency, and identification can be improved
Accuracy rate.
The another technical solution that the present invention solves above-mentioned technical problem is as follows:
A kind of character input system, including:Pen, attitude transducer and receiving terminal, the attitude transducer are arranged described
On pen, the receiving terminal is used to when user using the pen when writing, obtain the collected pen of the attitude transducer
The attitude data of movement, and analyzing processing is carried out to the attitude data according to preset processing model, character features are obtained, and
Corresponding word is matched from preset database according to the character features, obtains the word that the user is write.
The beneficial effects of the invention are as follows:A kind of character input system provided by the invention, when user using pen when being write,
The attitude data that pen movement generates is obtained by attitude transducer, and is analyzed and is handled by receiving terminal, user institute is obtained
The character features for the word write, and corresponding word is matched from database accordingly, user is realized when writing using pen, just
Conveniently the word that user is write can be input in the devices such as computer in real time, improve the convenience of word input.
Further, the receiving terminal is additionally operable to carry out denoising to the attitude data.
Further, further include:Processor on the pen is set, and the jitter amplitude for judging the pen works as institute
When stating the jitter amplitude of pen more than default jitter amplitude, obtains the user and write using the pen.
Further, the receiving terminal, which is additionally operable to obtain multiple users, carries out repeatedly writing obtained lteral data respectively,
And machine learning algorithm training is carried out to the processing model according to the lteral data.
Further, the receiving terminal is specifically used for when the lteral data is first kind word, by described first
Type word carries out machine learning algorithm training as sample, to the processing model, when the lteral data is Second Type
When word, using the stroke of the Second Type word as sample, machine learning algorithm training is carried out to the processing model, then
By the combination of strokes after training at word, wherein the first kind word is the word not being made of stroke, described
Two type words are the word being made of stroke.
The advantages of additional aspect of the invention, will be set forth in part in the description, and will partly become from the following description
It obtains obviously, or practice is recognized through the invention.
Description of the drawings
Fig. 1 is a kind of flow diagram that one embodiment of character input method provides of the present invention;
Fig. 2 is a kind of flow diagram that another embodiment of character input method provides of the present invention;
Fig. 3 is a kind of structural framing figure that one embodiment of character input system provides of the present invention.
Specific implementation mode
The principle and features of the present invention will be described below with reference to the accompanying drawings, and illustrated embodiment is served only for explaining the present invention,
It is not intended to limit the scope of the present invention.
As shown in Figure 1, for a kind of flow diagram that one embodiment of character input method provides of the present invention, this implementation
The character input method that example provides, the word that user need not be wanted to input by keyboard, board etc. are input to computer
In, it is only necessary to harvester of the installation comprising attitude transducer acquires the attitude data of pen in real time on pen, and passes through receiving terminal
Processing analysis is carried out to attitude data, corresponding word is matched from database, so that it may with user using the pen on paper or
It when writing on other objects, enters text into computer in real time, specifically, this method may include:
S1, when the attitude data that user using pen when being write, and acquisition pen moves.
It should be noted that user, when being write using pen, meeting is centered on the certain point among penholder, pen tip and tail
It is moved in opposite direction, then the harvester containing attitude transducer can be arranged at pen tip, for acquiring pen
The harvester containing attitude transducer can also be arranged in attitude data at tail, when being arranged at tail, acquisition
After the attitude data of pen, the overturning with left and right up and down is carried out to the character features identified.
Attitude data can be user when being write using pen, pen generate acceleration information and angular velocity data, pass through
The acceleration information and angular velocity data of pen during exercise, so that it may to identify the posture and angle of pen.Attitude data can be with
Including position data, analyzes the posture of pen by binding site data, can more accurately identify word.
S2 carries out analyzing processing to attitude data according to preset processing model, obtains character features.
It should be noted that preset processing model can be realized by being stored with the chip of pre-set programs, for example, can be with
Processing model is trained by supervised training method, multiple word is carried out respectively with different people and writes collected number
It is trained according to for sample, so that it may when collecting new attitude data, to identify corresponding word.
For example, corresponding acceleration signature and angular speed feature when each word is write can be stored in processing model,
And the order information of these features has specific acceleration and angular speed feature by taking " o " as an example, since " o " is enclosed shape
Shape, then its acceleration start when and at the end of direction on the contrary, and size it is close, be symmetric, angular speed also be in symmetrically
Distribution, then after receiving acceleration information and angular velocity data, so that it may which, to be judged, these can serve as " o "
Character features are identified.
It should be noted that the character features of each word are different, the above embodiment for only providing a word,
The analyzing processing process of his word can be arranged and adjust according to actual demand.
S3 matches corresponding word according to character features from preset database, obtains the word that user is write.
After obtaining character features, so that it may from prestoring in database of the character features with word correspondence, to match
Corresponding word.
A kind of character input method provided in this embodiment, by the way that, when being write using pen, pen movement generates to user
Attitude data is analyzed and is handled, and obtains the character features for the word that user is write, and match correspond to from database accordingly
Word, realize user when writing using pen, so that it may the word that user is write is input to computer in real time to facilitate
In equal devices, the convenience of word input is improved.
As shown in Fig. 2, for a kind of flow diagram that another embodiment of character input method provides of the present invention, this method
May include:
S1, when the attitude data that user using pen when being write, and acquisition pen moves.
It should be noted that the explanation of step same as the previously described embodiments in the present embodiment, can refer to above-mentioned implementation
In example pair it should be noted that details are not described herein.
S2 carries out analyzing processing to attitude data according to preset processing model, obtains character features.
S3 matches corresponding word according to character features from preset database, obtains the word that user is write.
Preferably, before step S1, can also include:
S01 obtains multiple users and carries out repeatedly writing obtained lteral data respectively.
S02 carries out machine learning algorithm training according to lteral data to processing model.
It should be noted that when user is when writing, there is special writing style for each word, although
Everyone writing style is different, but when each word of writing, the posture and exercise data of pen have certain rule, only
Want the quantity of sample sufficiently large, so that it may by machine learning method, to allow the writing style that machine learning is different, distinguish,
The different fonts that different writing styles are write can be detected.
Preferably, machine learning algorithm training is carried out to processing model according to lteral data, specifically included:
When lteral data is first kind word, using first kind word as sample, machine is carried out to processing model
Learning algorithm is trained, for example, supervised training method may be used.
When lteral data be Second Type word when, using the stroke of Second Type word be used as sample, to handle model into
Row machine learning algorithm is trained, then by the combination of strokes after training at word, for example, supervised training method may be used.
Wherein, first kind word is the word not being made of stroke, and Second Type word is the word being made of stroke,
For example, first kind word can be English, Spanish etc., Second Type word can be Chinese, Japanese etc..
Preferably, before step S1, can also include:
S03 judges the jitter amplitude of pen, when the jitter amplitude of pen is more than default jitter amplitude, obtains user and is using
Pen writes.
It should be noted that the jitter amplitude of pen can be judged by judging the rate of acceleration change of pen, when pen is hanging
Deng not in the state of writing, the jitter amplitude of pen is smaller, the change frequency of acceleration also very little, when pen is in the state of writing,
Its jitter amplitude is larger, and acceleration does not stop to change, and by the change frequency of predetermined acceleration, and acquires the real time acceleration of pen,
It may determine that whether pen is in the state of writing.
It can also judge that the jitter amplitude of pen also may be used for example, by installing motion sensor additional on pen by other means
Accurately to judge the dither state of pen.
Preferably, before step S2, further include:
S04 carries out denoising to attitude data.
For example, Kalman filtering algorithm processing can be carried out to attitude data, identification and the process with training can be simplified.
A kind of character input method provided in this embodiment, by the way that, when being write using pen, pen movement generates to user
Attitude data is analyzed and is handled, and obtains the character features for the word that user is write, and match correspond to from database accordingly
Word, realize user when writing using pen, so that it may the word that user is write is input to computer in real time to facilitate
In equal devices, the convenience of word input is improved.
And by carrying out denoising to collected attitude data, the availability of attitude data, Neng Goujian can be improved
Change the identification process of word.It is detected by the jitter amplitude to pen, can judge that the state of pen is to write or hanging
Sky can realize that just the attitude data of acquisition pen, reduces the occupancy to hardware resource, improve the standard of identification when pen is when writing
True property and the convenience used.Machine learning algorithm by carrying out great amount of samples to processing model is trained, and processing mould can be made
Type identifies the word of different fonts different-style, can improve accuracy and the practicability of identification.By to text to be identified
Word is judged, when word to be identified is made of stroke, is carried out machine learning training to the stroke of word, is being identified pen
After drawing, it is combined into word, can realize the identification that the machines such as Chinese character are difficult to word, can be saved the time, improves work
Efficiency, and the accuracy rate of identification can be improved.
As shown in figure 3, for a kind of structural framing figure that one embodiment of character input system provides of the present invention, the system
May include:Pen 1, attitude transducer 2 and receiving terminal 3, attitude transducer 2 are arranged on pen 1, and receiving terminal 3 is used to exist as user
When writing using pen 1, the attitude data of 2 collected pen 1 of attitude transducer movement is obtained, and according to preset processing model pair
Attitude data carries out analyzing processing, obtains character features, and corresponding text is matched from preset database according to character features
Word obtains the word that user is write.
It should be noted that receiving terminal 3 refers to receive the attitude data of the movement of pen 1, and can be to attitude data
The device handled can be actually corresponding function may be implemented in computer, mobile phone etc. device or equipment.
It is appreciated that in order to make attitude transducer 2 and receiving terminal 3 realize its function, wireless transmission should still be provided on pen 1
The devices such as module, battery.These devices can integrate, and can also be stitched together, can also according to design requirement or
The different location in pen 1 is arranged in use demand.
Pen 1 provided in this embodiment can be the pen 1 that can arbitrarily write on paper, or 1 shape of pen
Rod etc..
Preferably, receiving terminal 3 is additionally operable to carry out denoising to attitude data.
Preferably, further include:The processor 4 being arranged on pen 1, the jitter amplitude for judging pen 1, when the shake of pen 1
When amplitude is more than default jitter amplitude, obtains user and write using pen 1.
Preferably, receiving terminal 3, which is additionally operable to obtain multiple users, carries out repeatedly writing obtained lteral data respectively, and according to
Lteral data carries out machine learning algorithm training to processing model.
Preferably, receiving terminal 3 is specifically used for when lteral data is first kind word, using first kind word as sample
This, carries out machine learning algorithm training, when lteral data is Second Type word, by Second Type word to processing model
1 stroke of pen is used as sample, carries out machine learning algorithm training to processing model, then the pen 1 after training is drawn and is combined into word,
In, first kind word is not draw the word formed by pen 1, and Second Type word is to draw the word formed by pen 1.
A kind of character input system provided in this embodiment passes through attitude transducer 2 when user using pen 1 when writing
The attitude data that the movement of pen 1 generates is obtained, and is analyzed and is handled by receiving terminal 3, the text for the word that user is write is obtained
Word feature, and corresponding word is matched from database accordingly, user is realized when writing using pen 1, so that it may to facilitate reality
When the word that user is write is input in the devices such as computer, improve word input convenience.
Reader should be understood that in the description of this specification reference term " one embodiment ", " is shown " some embodiments "
The description of example ", " specific example " or " some examples " etc. mean specific features described in conjunction with this embodiment or example, structure,
Material or feature are included at least one embodiment or example of the invention.In the present specification, above-mentioned term is shown
The statement of meaning property need not be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
It is apparent to those skilled in the art that for convenience of description and succinctly, the dress of foregoing description
The specific work process with unit is set, can refer to corresponding processes in the foregoing method embodiment, details are not described herein.
In several embodiments provided herein, it should be understood that disclosed device and method can pass through it
Its mode is realized.For example, the apparatus embodiments described above are merely exemplary, for example, the division of unit, only
A kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component can combine or
Person is desirably integrated into another system, or some features can be ignored or not executed.
The unit illustrated as separating component may or may not be physically separated, and be shown as unit
Component may or may not be physical unit, you can be located at a place, or may be distributed over multiple networks
On unit.Some or all of unit therein can be selected according to the actual needs to realize the mesh of the embodiment of the present invention
's.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing unit, it can also
It is that each unit physically exists alone, can also be during two or more units are integrated in one unit.It is above-mentioned integrated
The form that hardware had both may be used in unit is realized, can also be realized in the form of SFU software functional unit.
It, can if integrated unit is realized in the form of SFU software functional unit and when sold or used as an independent product
To be stored in a computer read/write memory medium.Based on this understanding, technical scheme of the present invention substantially or
Say that all or part of the part that contributes to existing technology or the technical solution can embody in the form of software products
Out, which is stored in a storage medium, including some instructions are used so that a computer equipment
(can be personal computer, server or the network equipment etc.) executes all or part of each embodiment method of the present invention
Step.And storage medium above-mentioned includes:USB flash disk, read-only memory (ROM, Read-OnlyMemory), is deposited mobile hard disk at random
The various media that can store program code such as access to memory (RAM, RandomAccessMemory), magnetic disc or CD.
More than, specific implementation mode only of the invention, but scope of protection of the present invention is not limited thereto, and it is any to be familiar with
Those skilled in the art in the technical scope disclosed by the present invention, can readily occur in various equivalent modifications or substitutions,
These modifications or substitutions should be covered by the protection scope of the present invention.Therefore, protection scope of the present invention should be wanted with right
Subject to the protection domain asked.
Claims (10)
1. a kind of character input method, which is characterized in that including:
When user using pen when writing, the attitude data of the pen movement is obtained;
Analyzing processing is carried out to the attitude data according to preset processing model, obtains character features;
Corresponding word is matched from preset database according to the character features, obtains the word that the user is write.
2. character input method according to claim 1, which is characterized in that it is described according to preset processing model to described
Attitude data carries out analyzing processing, before obtaining character features, further includes:
Denoising is carried out to the attitude data.
3. character input method according to claim 1, which is characterized in that it is described when user using pen when being write, it obtains
Before the attitude data for taking the pen movement, further include:
The jitter amplitude for judging the pen obtains the user and exists when the jitter amplitude of the pen is more than default jitter amplitude
It is write using the pen.
4. character input method according to any one of claim 1 to 3, which is characterized in that described when user is using
When pen writes, before the attitude data for obtaining the pen movement, further include:
Multiple users are obtained to carry out repeatedly writing obtained lteral data respectively;
Machine learning algorithm training is carried out to the processing model according to the lteral data.
5. character input method according to claim 4, which is characterized in that it is described according to the lteral data to the place
It manages model and carries out machine learning algorithm training, specifically include:
When the lteral data is first kind word, using the first kind word as sample, to the processing model
Carry out machine learning algorithm training;
When the lteral data is Second Type word, using the stroke of the Second Type word as sample, to the place
It manages model and carries out machine learning algorithm training, then by the combination of strokes after training at word;
Wherein, the first kind word is the word not being made of stroke, and the Second Type word is made of stroke
Word.
6. a kind of character input system, which is characterized in that including:Pen, attitude transducer and receiving terminal, the attitude transducer are set
It sets on the pen, the receiving terminal is used to when user using the pen when writing, obtain the attitude transducer and collect
The pen movement attitude data, and according to preset processing model to the attitude data progress analyzing processing, obtain text
Word feature, and corresponding word is matched from preset database according to the character features, obtain the text that the user is write
Word.
7. character input system according to claim 6, which is characterized in that the receiving terminal is additionally operable to the posture number
According to progress denoising.
8. character input system according to claim 6, which is characterized in that further include:Processing on the pen is set
Device, the jitter amplitude for judging the pen obtain the user when the jitter amplitude of the pen is more than default jitter amplitude
It writes using the pen.
9. the character input system according to any one of claim 6 to 8, which is characterized in that the receiving terminal is additionally operable to
Multiple users are obtained to carry out repeatedly writing obtained lteral data respectively, and according to the lteral data to the processing model into
Row machine learning algorithm is trained.
10. character input system according to claim 9, which is characterized in that the receiving terminal is specifically used for working as the text
When digital data is first kind word, using the first kind word as sample, machine learning is carried out to the processing model
Algorithm is trained, when the lteral data is Second Type word, using the stroke of the Second Type word as sample, to institute
It states processing model and carries out machine learning algorithm training, then by the combination of strokes after training at word, wherein the first kind
Type word is the word not being made of stroke, and the Second Type word is the word being made of stroke.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810102902.4A CN108469912A (en) | 2018-02-01 | 2018-02-01 | A kind of character input method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810102902.4A CN108469912A (en) | 2018-02-01 | 2018-02-01 | A kind of character input method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108469912A true CN108469912A (en) | 2018-08-31 |
Family
ID=63266035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810102902.4A Pending CN108469912A (en) | 2018-02-01 | 2018-02-01 | A kind of character input method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108469912A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111338811A (en) * | 2019-02-13 | 2020-06-26 | 鸿合科技股份有限公司 | User writing behavior analysis method, server, terminal, system and electronic equipment |
CN116048242A (en) * | 2022-06-17 | 2023-05-02 | 荣耀终端有限公司 | Active pen and gesture recognition method thereof |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101872259A (en) * | 2010-06-03 | 2010-10-27 | 中国人民解放军第二炮兵工程学院 | Natural interaction pen capable of automatically inputting written contents and handwriting detection method |
CN102135823A (en) * | 2011-04-28 | 2011-07-27 | 华南理工大学 | Intelligent electronic handwriting pen |
CN102999185A (en) * | 2012-12-04 | 2013-03-27 | 昆山冠强软件科技有限公司 | Stylus device with smart learning and memory function |
CN106339104A (en) * | 2016-08-24 | 2017-01-18 | 广州市香港科大霍英东研究院 | Text input method and device for smart watch |
-
2018
- 2018-02-01 CN CN201810102902.4A patent/CN108469912A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101872259A (en) * | 2010-06-03 | 2010-10-27 | 中国人民解放军第二炮兵工程学院 | Natural interaction pen capable of automatically inputting written contents and handwriting detection method |
CN102135823A (en) * | 2011-04-28 | 2011-07-27 | 华南理工大学 | Intelligent electronic handwriting pen |
CN102999185A (en) * | 2012-12-04 | 2013-03-27 | 昆山冠强软件科技有限公司 | Stylus device with smart learning and memory function |
CN106339104A (en) * | 2016-08-24 | 2017-01-18 | 广州市香港科大霍英东研究院 | Text input method and device for smart watch |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111338811A (en) * | 2019-02-13 | 2020-06-26 | 鸿合科技股份有限公司 | User writing behavior analysis method, server, terminal, system and electronic equipment |
CN116048242A (en) * | 2022-06-17 | 2023-05-02 | 荣耀终端有限公司 | Active pen and gesture recognition method thereof |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108171257B (en) | Fine granularity image recognition model training and recognition methods, device and storage medium | |
CN107609489B (en) | Handwriting writing path evaluation device and method and electronic equipment | |
US9672418B2 (en) | Arabic sign language recognition using multi-sensor data fusion | |
CN107633227A (en) | A kind of fine granularity gesture identification method and system based on CSI | |
CN112507806B (en) | Intelligent classroom information interaction method and device and electronic equipment | |
CN100410965C (en) | System and method for detecting a list in ink input | |
CN103926997A (en) | Method for determining emotional information based on user input and terminal | |
JP6489005B2 (en) | Information processing system, information processing method, and program | |
CN109902541B (en) | Image recognition method and system | |
CN102867190B (en) | A kind of method utilizing mobile device built-in sensors to carry out Activity recognition | |
CN111768760B (en) | Multi-mode voice endpoint detection method and device | |
CN102073870A (en) | Method for recognizing Chinese character handwriting on touch screen | |
CN101685497B (en) | Method and device for processing hand-written information | |
CN107077243A (en) | Output intent, output device and the program of ink file | |
CN107330009B (en) | Method and apparatus for creating topic word classification model, and storage medium | |
JP2022501713A (en) | Motion recognition methods and devices, electronic devices, and storage media | |
Xu et al. | Air-writing characters modelling and recognition on modified CHMM | |
CN108469912A (en) | A kind of character input method and system | |
Popli et al. | Classification and recognition of online hand-written alphabets using machine learning methods | |
CN108416249A (en) | A kind of written handwriting identification system and method | |
CN112487883A (en) | Intelligent pen writing behavior characteristic analysis method and device and electronic equipment | |
CN103176651B (en) | A kind of hand-written information Quick Acquisition method | |
CN104951811B (en) | Row style line recognition methods and device applied to brush writing | |
CN107015647A (en) | User's gender identification method based on smart mobile phone posture behavior big data | |
CN106648149B (en) | A kind of aerial hand-written character recognition method based on accelerometer and gyroscope |
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 | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180831 |