WO2019045185A1 - Mobile device and method for correcting character string entered through virtual keyboard - Google Patents
Mobile device and method for correcting character string entered through virtual keyboard Download PDFInfo
- Publication number
- WO2019045185A1 WO2019045185A1 PCT/KR2017/014137 KR2017014137W WO2019045185A1 WO 2019045185 A1 WO2019045185 A1 WO 2019045185A1 KR 2017014137 W KR2017014137 W KR 2017014137W WO 2019045185 A1 WO2019045185 A1 WO 2019045185A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- candidate words
- correction candidate
- character string
- word
- mobile device
- Prior art date
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]
- G06F3/0487—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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0236—Character input methods using selection techniques to select from displayed items
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/02—Input arrangements using manually operated switches, e.g. using keyboards or dials
- G06F3/023—Arrangements for converting discrete items of information into a coded form, e.g. arrangements for interpreting keyboard generated codes as alphanumeric codes, operand codes or instruction codes
- G06F3/0233—Character input methods
- G06F3/0237—Character input methods using prediction or retrieval techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/20—Natural language analysis
- G06F40/232—Orthographic correction, e.g. spell checking or vowelisation
Definitions
- One or more embodiments relate to a mobile device and method for correcting a character string entered through a virtual keyboard.
- a typing error may occur while characters such as Korean alphabet letters, English alphabet letters, and numbers are entered into a mobile device.
- a user may delete a mistyped character by using a deletion key, such as a backspace key, and then enter a correct character or may place a cursor indicating a character input location to a position where the typing error has occurred, delete a mistyped character, and then enter a correct character.
- a mistyped character correction method is inconvenient in that when characters are continuously entered without immediately noticing an occurrence of a typing error, even correct characters entered after the typing error needs to be deleted or the cursor needs to be moved to a position where the typing error has occurred and then moved back to an original position.
- One or more embodiments include a mobile device and method for correcting a character string entered through a virtual keyboard.
- a method of correcting a character string entered through a virtual keyboard includes receiving a character string entered through a virtual keyboard displayed on a mobile device; creating a correction candidate word corresponding to an input word included in the entered character string; selecting an optimal word from the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with the correction candidate words, and also on the basis of weights based on at least one of positions of keys corresponding to the input word and the correction candidate words on the virtual key board, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words; and outputting a character string including the selected optimal word in place of the entered character string.
- a mobile device for correcting a character string entered through a virtual keyboard includes a user interface; a memory configured to store computer executable instructions; and a processor configured to the computer executable instructions to receive a character string entered through a virtual keyboard displayed on the user interface of the mobile device, create correction candidate words corresponding to an input word included in the entered character string, select an optimal word from among the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with the correction candidate words, and also on the basis of weights based on at least one of positions of keys on the virtual key board corresponding to the input word and the correction candidate words, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words, and output a character string including the selected optimal word in place of the entered character string.
- FIG. 1 is a block diagram showing a configuration of a mobile device for correcting a character string entered through a virtual keyboard according to an embodiment
- FIG. 2 is a diagram illustrating a process of correcting a character string entered through a virtual keyboard according to an embodiment
- FIG. 3 is a flowchart showing a method of correcting a character string entered through a virtual keyboard according to an embodiment
- FIG. 4 is a detailed flowchart showing a process of creating correction candidate words in the method of correcting a character string entered through a virtual keyboard according to an embodiment
- FIG. 5 is a detailed flowchart showing a process of selecting an optimal word in the method of correcting a character string entered through a virtual keyboard according to an embodiment.
- a method of correcting a character string entered through a virtual keyboard includes receiving a character string entered through a virtual keyboard displayed on a mobile device; creating a correction candidate word corresponding to an input word included in the entered character string; selecting an optimal word from the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with the correction candidate words, and also on the basis of weights based on at least one of positions of keys corresponding to the input word and the correction candidate words on the virtual key board, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words; and outputting a character string including the selected optimal word in place of the entered character string.
- FIG. 1 is a block diagram showing a configuration of a mobile device for correcting a character string entered through a virtual keyboard according to an embodiment.
- a mobile device 100 for correcting a character string entered through a virtual keyboard may include a memory 110, a processor 120, and a user interface 130. It will be appreciated by those skilled in the art that general-purpose elements other than the elements shown in FIG. 1 may be further included.
- the mobile device 100 is an electronic device equipped with an operating system (OS) and configured to execute an application installed on the mobile device 100 and display a processing result corresponding to a user input, and may include a smartphone, a tablet, a digital camera, etc.
- OS operating system
- the term "application” collectively refers to an application program or a mobile application.
- the memory 110 may store software and/or programs.
- the memory 110 may store programs, such as an application and an application programming interface (API), and various types of data.
- programs such as an application and an application programming interface (API), and various types of data.
- API application programming interface
- the processor 120 may access and use the data stored in the memory 110 or store new data in the memory 110. Also, the processor 120 may execute the programs installed in the memory 110. Also, the processor 120 may install an application received from the outside in the memory 110.
- the processor 120 may include at least one processor.
- the processor 120 may control the other elements included in the mobile device 100 to perform operations corresponding to a user input received through the user interface 130.
- the processor 120 may be a processor including at least one special-purpose processor corresponding to functions or a single integrated processor.
- the processor 120 may execute a program stored in the memory 110, read data or a file stored in the memory 110, and store a new file in the memory 110.
- the user interface 130 may receive a user input or the like from a user or may display information such as a result of the mobile device 100 executing an application, a result of the mobile device 100 performing an operation corresponding to a user unit, a state of the mobile device 100, or the like.
- the user interface 130 may include hardware units for receiving an input from a user or providing an output to the mobile device 100 and may include a dedicated software module for driving the hardware units.
- the user interface 130 may include an operation panel, such as a touch panel, for receiving a user input and a display panel for displaying a screen and may be a touchscreen, which is a combination of the operation panel and the display panel, but is not limited thereto.
- the memory 110 may store computer executable instructions.
- the processor 120 may execute a computer executable instruction stored in the memory 110.
- the processor 120 may receive a character string that is entered through a virtual keyboard displayed on the user interface 130 of the mobile device 100.
- the processor 120 may create correction candidate words corresponding to an input word included in the entered character string.
- the processor 120 may select an optimal word from among the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with the correction candidate words, and also on the basis of weights based on at least one of positions of keys on the virtual keyboard corresponding to the input word and the correction candidate words, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words.
- the processor 120 may output a character string including the selected optimal word in place of the entered character string. A process of correcting a character string entered through a virtual keyboard will be described in detail below.
- FIG. 2 is a diagram illustrating the process of correcting a character string entered through a virtual keyboard according to an embodiment.
- the mobile device 100 may receive a character string that is entered through a virtual keyboard displayed on a user interface of the mobile device 100. It can be seen from FIG. 2 that "son" was entered through the virtual keyboard.
- the entered character string may include at least one or more input words.
- the mobile device 100 may perform a process of correcting the entered character string.
- the mobile device 100 may utilize various kinds of databases (hereinafter referred to as a DB) to perform the process of correcting the entered character string.
- a DB databases
- FIG. 2 shows an adjacent key/non-adjacent key DB, a pronunciation distinction code DB, a word DB, a language model DB, etc.
- the mobile device 100 is not limited thereto and may additionally utilize another kind of DB.
- the mobile device 100 may utilize the adjacent key/non-adjacent key DB to create first correction candidate words on the basis of positions of keys on the virtual keyboard corresponding to letters constituting an input word included in the character string entered through the virtual keyboard. For example, as shown in FIG. 2, the mobile device 100 may generate first correction candidate words by combining adjacent keys of a "s" key, an "o” key, and a "n” key corresponding to an input word “son.”
- the adjacent keys of the key “s” may include an "e” key, a "d” key, a "x” key, a “z” key, a "a” key, and a “w” key, and the range of the adjacent keys may be enlarged or reduced depending on settings. Referring to FIG.
- the adjacent keys of the key “o” may include a “p” key, a “l” key, a “k” key, and an “i” key
- the adjacent keys of the key “n” may include a “b” key, a "h” key, a “j” key, a "k” key, and a “m” key.
- the mobile device 100 may create first correction candidate words by combining non-adjacent keys of the "s" key, the "o” key, and the "b” key. Each of the first correction candidate words may have a predetermined value corresponding to a similarity to the input word.
- the mobile device 100 may assign weights to the first correction candidate words in inverse proportion to the distance between a position of a key on the virtual keyboard corresponding to each of the letters constituting the input word and a position of each of the adjacent/non-adjacent keys on the virtual keyboard. In other words, the mobile device 100 may apply different weights to the similarities of the first correction candidate words on the basis of the positions of the keys on the virtual keyboard.
- the mobile device 100 may utilize the pronunciation distinction code DB to create first correction candidate words on the basis of pronunciations similar to that of the input word included in the character string entered through the virtual keyboard. For example, as shown in FIG. 2, the mobile device 100 may create first correction candidate words, such as "sun,” “sson,” “ssun,” and “sunn,” for an input word "son.” Each of the first correction candidate words may have a predetermined value corresponding to a similarity to the input word. The mobile device 100 may assign weights to the first correction candidate words on the basis of similar pronunciations. In other words, the mobile device 100 may apply different weights to the similarities of the first correction candidate words on the basis of the similar pronunciations.
- the mobile device 100 may determine whether the weighted similarities of the first correction candidate words created on the basis of the positions of the keys on the virtual keyboard and/or the similar pronunciations are greater than or equal to a predetermined threshold and may extract first correction candidate words having weighted similarities greater than or equal to the predetermined threshold. This is to remove first correction candidate words having similarities, which are based on the positions of the keys on the virtual keyboard and/or the similar pronunciations, less than the predetermined threshold from the created first correction candidate words.
- the mobile device 100 may match the first correction candidate words created on the basis of the positions of the keys on the virtual keyboard and/or the similar pronunciations with the word DB and may extract first correction candidate words that are validly matched. This is to remove invalid words, which are not present in the word DB, from the created first correction candidate words. As shown in FIG. 2, the mobile device 100 may match the first correction candidate words with the word DB and extract valid words such as "sun” and "sunn.”
- the mobile device 100 may create second correction candidate words on the basis of an editing distance.
- the editing distance is a criterion that indicates how many times any word needs to be corrected to become a target word, and second correction candidate words may be created according to an editing distance level.
- the mobile device 100 may create second correction candidate words according to an editing distance level that is determined by a user or according to a predetermined value. For example, when second correction candidate words are created according to editing distance level 3, the mobile device 100 may extract words corresponding to editing distance level 1, editing distance level 2, and editing distance level 3 from the word DB to create the second correction candidate words.
- the mobile device 100 may create correction candidate words corresponding to the input word included in the entered character string by combining the first correction candidate words and the second correction candidate words.
- correction candidate words may be created solely on the basis of the editing distance.
- the mobile device 100 may utilize the language model DB to select an optimal word from among the input word included in the entered character string and the created correction candidate words.
- the language model DB may have various types of language models. Each of the language models may be a language model that is learned on the basis of a predetermined condition or predetermined data.
- the mobile device 100 may select a language model most suitable for a situation or condition in which the character string is entered through the virtual keyboard and apply the selected language model to the entered character string and corrected character strings.
- the mobile device 100 may determine whether the input word is appropriate for the entered character string in context or whether the correction candidate words are appropriate for the corrected character strings, thereby acquiring a match probability of the input word. For example, as shown in FIG.
- the mobile device 100 may determine whether the input word "son” placed at the last part of the entered character string is appropriate for the entered character string in context and whether the correction candidate words "sun” and “sunn” are appropriate for corrected character strings obtained by replacing the input word "son” placed at the last part of the entered character string with the correction candidate words "sun” and “sunn” and may acquire match probabilities of the words. For example, when the entered character string is "I have a daughter and a son,” it can be seen that the input word "son,” which is actually entered, is more appropriate in context than the correction candidate words.
- the mobile device 100 may apply a language model to the entered character string and the corrected character strings to acquire match probabilities.
- the mobile device 100 may apply different weights to the match probabilities acquired by applying the language model to the entered character string and the corrected character strings on the basis of at least one of positions of keys on the virtual keyboard corresponding to the input word and the correction candidate words, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words.
- the mobile device 100 may select an optimal word having the highest match probability from among the input word and the correction candidate words on the basis of the weighted match probabilities.
- the mobile device 100 may correct a character string entered through the virtual keyboard by outputting a character string including the selected optimal word in place of the character string entered through the virtual keyword.
- FIG. 3 is a flowchart showing a method of correcting a character string entered through a virtual keyboard according to an embodiment.
- the mobile device 100 may receive a character string that is entered through a virtual keyboard displayed on the mobile device 100.
- the mobile device 100 may create correction candidates corresponding to an input word included in the entered character string.
- the input word included in the entered character string may include at least one or more input words, and one input word may include at least one correction candidate word.
- a process of creating correction candidate words will be described below in detail with reference to FIG. 4.
- FIG. 4 is a detailed flowchart showing the process of creating correction candidate words in the method of correcting a character string entered through a virtual keyboard according to an embodiment.
- the mobile device 100 may create first correction candidate words based on positions of keys on the virtual keyboard and/or similar pronunciations.
- the mobile device 100 may apply different weights to similarities of the created first correction candidate words on the basis of positions of keys on the virtual keyboard and/or similar pronunciations.
- the mobile device 100 may extract first correction candidate words having weighted similarities greater than or equal to a predetermined threshold. In other words, the mobile device 100 may remove first correction candidate words having weighted similarities less then the predetermined threshold from the created first correction candidate words.
- the mobile device 100 may match the created first correction candidate words with a word DB and extract first correction candidate words that are validly matched. In other words, the mobile device 100 may remove words that are not present in the word DB from the created first correction candidate words.
- the filtering of the weighted correction candidate words in operations 420 and 430 and the filtering of the correction candidate words by using the word DB in operation 450 may be performed in a different order, or any one of the operations may be omitted.
- the mobile device 100 may create second correction candidate words on the basis of an editing distance.
- the mobile device 100 may perform parallel processing on the operation of creating the first correction candidate words and the operation of creating the second correction candidate words.
- the mobile device 100 may combine the first correction candidate words and the second correction candidate words.
- at least one correction candidate word including a first correction candidate word and a second correction candidate word may be created for one input word.
- the mobile device 100 may select an optimal word from among the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with the correction candidate words, and also on the basis of weights based on at least one of positions of keys on the virtual keyboard corresponding to the input word and the correction candidate words, similar pronunciations between those of the input word and the correction candidate words, and/or similar spellings between those of the input word and the correction candidate words.
- a process of selecting an optimal word will be described below in detail with reference to FIG. 5.
- FIG. 5 is a detailed flowchart showing a process of selecting an optimal word in the method of correcting a character string entered through a virtual keyboard according to an embodiment.
- the mobile device 100 may apply a language model to an entered character string and corrected character strings, which are obtained by replacing an input word with a correction candidate words and thus acquire match probabilities of the words.
- the mobile device 100 may apply different weights to the acquired match probabilities on the basis of at least one of positions of keys on the virtual keyboard corresponding to the input word and the correction candidate words, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words.
- the mobile device 100 may select an optimal word having the highest match probability from among the input word and the correction candidate words on the basis of the weighted match probabilities.
- the mobile device 100 may output a character string including the selected optimal word in place of the entered character string.
- the mobile device 100 may output a corrected character string including the correction candidate word in place of the entered character string.
- the mobile device 100 may output the identical character string in place of the entered character string. Alternatively, the mobile device 100 may output the entered character string without change.
- the mobile device 100 may display the character string including the selected optimal word on the mobile device 100 and may output the character string including the selected optimal word instead according to a user's selection. In other words, the user confirms the character string to be output instead. When the user approves, the mobile device 100 may output the character string including the selected optimal word in place of the entered character string.
- the elements of the mobile device 100 may be changed in name. Also, the mobile device 100 according to this disclosure may include at least one of the aforementioned elements, and may exclude some elements or further include other additional elements.
- the disclosed embodiments may be implemented in the form of a computer-readable recording medium for storing instructions and data that are executable by a computer. At least one of the instructions and data may be stored in the form of program code, and may create a predetermined program module to perform a predetermined operation when executed by a processor.
- the computer-readable recording medium may include read-only memories (ROMs), random-access memories (RAMs), flash memories, CD-ROMs, CD-Rs, CD+Rs, CD-RWs, CD+RWs, DVD-ROMs, DVD-Rs, DVD+Rs, DVD-RWs, DVD+RWs, DVD-RAMs, BD-ROMs, BD-Rs, BD-R LTHs, BD-REs, magnetic tapes, floppy disks, magneto-optical data storage devices, optical data storage devices, hard disks, solid-state disks (SSDs), and any kind of devices capable of storing instructions or software, relevant data, data files, and data structures and providing the instructions or software, the relevant data, the data files, and the data structures to a processor or a computer so that the processor or computer may execute the instructions.
- ROMs read-only memories
- RAMs random-access memories
- flash memories CD-ROMs, CD-Rs, CD+Rs, CD-RWs, CD+
Abstract
Description
Claims (12)
- A method of correcting a character string entered through a virtual keyboard, the method comprising:receiving a character string entered through a virtual keyboard displayed on a mobile device;creating correction candidate words corresponding to an input word included in the entered character string;selecting an optimal word from among the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with correction candidate words, and also on the basis of weights based on at least one of positions of keys on the virtual key board corresponding to the input word and the correction candidate words, similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words; andoutputting a character string including the selected optimal word in place of the entered character string.
- The method of claim 1, wherein the creating of correction candidate words comprises:creating first correction candidate words on the basis of positions of keys on the virtual keyboard and/or similar pronunciations;creating second correction candidate words on the basis of an editing distance; andcombining the first correction candidate words and the second correction candidate words.
- The method of claim 2, wherein the creating of first correction candidate words comprises:applying different weights to similarities of the created first correction candidate words on the basis of the positions of keys on the virtual keyboard and/or similar pronunciations; andextracting first correction candidate words having weighted similarities greater than or equal to a predetermined threshold.
- The method of claim 2, wherein the creating of first correction candidate words comprises matching the created first correction candidate words with a word database and extracting first correction candidate words that are validly matched.
- The method of claim 1, wherein the selecting of an optimal word comprises:acquiring match probabilities obtained by applying a language model to the entered character string and the corrected character strings, which are obtained by replacing the input word with the correction candidate words;applying different weights to the acquired match probabilities on the basis of at least one of positions of keys on the virtual keyboard corresponding to the input word and the corrected candidate words similar pronunciations between those of the input word and the corrected candidate words, and similar spellings between those of the input word and the corrected candidate words; andselecting an optimal word having the highest match probability from among the input word and the correction candidate words on the basis of the weighted match probabilities.
- The method of claim 1, wherein the outputting of a character string including the selected optimal word comprises:displaying the character string including the selected optimal word on the mobile device; andoutputting the character string including the selected optimal word as a substitute according to a user's selection.
- A mobile device for correcting a character string entered through a virtual keyboard, the mobile device comprising:a user interface;a memory configured to store computer executable instructions; anda processor configured to the computer executable instructions to receive a character string entered through a virtual keyboard displayed on the user interface of the mobile device, create correction candidate words corresponding to an input word included in the entered character string, select an optimal word from among the input word and the correction candidate words on the basis of match probabilities obtained by applying a language model to the entered character string and corrected character strings, which are obtained by replacing the input word with the correction candidate words, and also on the basis of weighting based on at least one of positions of keys on the virtual key board, corresponding to the input word and the correction candidate words similar pronunciations between those of the input word and the correction candidate words, and similar spellings between those of the input word and the correction candidate words, and output a character string including the selected optimal word in place of the entered character string.
- The mobile device of claim 7, wherein the processor creates first correction candidate words on the basis of positions of keys on the virtual keyboard and/or similar pronunciations, creates second correction candidate words on the basis of an editing distance; and combines the first correction candidate words and the second correction candidate words.
- The mobile device of claim 8, wherein the processor applies different weights to similarities of the created first correction candidate words on the basis of positions of keys on the virtual keyboard and/or similar pronunciations and extracts first correction candidate words having weighted similarities greater than or equal to a predetermined threshold.
- The mobile device of claim 8, wherein the processor matches the created first correction candidate words with a word database and extract first correction candidate words that are validly matched.
- The mobile device of claim 7, wherein the processor acquires match probabilities obtained by applying a language model to the entered character string and the corrected character strings, which are obtained by replacing the input word with the correction candidate words, applies different weights to the acquired match probabilities on the basis of at least one of positions of keys on the virtual keyboard corresponding to the input word and the corrected candidate words, similar pronunciations between those of the input word and the corrected candidate words, and similar spellings between those of the input word and the corrected candidate words, and selects an optimal word having the highest match probability from among the input word and the correction candidate words.
- The mobile device of claim 7, wherein the processor displays the character string including the selected optimal word on the user interface of the mobile device and outputs the character string including the selected optimal word as a substitute according to a user's selection.
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
KR10-2017-0110662 | 2017-08-31 | ||
KR1020170110662A KR20190024072A (en) | 2017-08-31 | 2017-08-31 | Mobile apparatus and method for correcting character string inputted through virtual keyboard |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2019045185A1 true WO2019045185A1 (en) | 2019-03-07 |
Family
ID=65527616
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/KR2017/014137 WO2019045185A1 (en) | 2017-08-31 | 2017-12-05 | Mobile device and method for correcting character string entered through virtual keyboard |
Country Status (2)
Country | Link |
---|---|
KR (1) | KR20190024072A (en) |
WO (1) | WO2019045185A1 (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110764647A (en) * | 2019-10-21 | 2020-02-07 | 科大讯飞股份有限公司 | Input error correction method, input error correction device, electronic equipment and storage medium |
CN111078028A (en) * | 2019-12-09 | 2020-04-28 | 科大讯飞股份有限公司 | Input method, related device and readable storage medium |
CN114527927A (en) * | 2020-11-20 | 2022-05-24 | 阿波罗智联(北京)科技有限公司 | Method and device for inputting information, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060241944A1 (en) * | 2005-04-25 | 2006-10-26 | Microsoft Corporation | Method and system for generating spelling suggestions |
KR20130020418A (en) * | 2011-08-19 | 2013-02-27 | 주식회사 케이티 | A method for recomending character string |
US20130314352A1 (en) * | 2012-05-23 | 2013-11-28 | Google Inc. | Predictive virtual keyboard |
KR20130139447A (en) * | 2012-06-07 | 2013-12-23 | 네이버 주식회사 | Method of improving logic to propose query for mobile keyboard typo pattern and the device thereof |
KR20150131040A (en) * | 2013-03-14 | 2015-11-24 | 마이크로소프트 테크놀로지 라이센싱, 엘엘씨 | Text prediction based on multiple language models |
-
2017
- 2017-08-31 KR KR1020170110662A patent/KR20190024072A/en active IP Right Grant
- 2017-12-05 WO PCT/KR2017/014137 patent/WO2019045185A1/en active Application Filing
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20060241944A1 (en) * | 2005-04-25 | 2006-10-26 | Microsoft Corporation | Method and system for generating spelling suggestions |
KR20130020418A (en) * | 2011-08-19 | 2013-02-27 | 주식회사 케이티 | A method for recomending character string |
US20130314352A1 (en) * | 2012-05-23 | 2013-11-28 | Google Inc. | Predictive virtual keyboard |
KR20130139447A (en) * | 2012-06-07 | 2013-12-23 | 네이버 주식회사 | Method of improving logic to propose query for mobile keyboard typo pattern and the device thereof |
KR20150131040A (en) * | 2013-03-14 | 2015-11-24 | 마이크로소프트 테크놀로지 라이센싱, 엘엘씨 | Text prediction based on multiple language models |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110764647A (en) * | 2019-10-21 | 2020-02-07 | 科大讯飞股份有限公司 | Input error correction method, input error correction device, electronic equipment and storage medium |
CN110764647B (en) * | 2019-10-21 | 2023-10-31 | 科大讯飞股份有限公司 | Input error correction method, input error correction device, electronic equipment and storage medium |
CN111078028A (en) * | 2019-12-09 | 2020-04-28 | 科大讯飞股份有限公司 | Input method, related device and readable storage medium |
CN111078028B (en) * | 2019-12-09 | 2023-11-21 | 科大讯飞股份有限公司 | Input method, related device and readable storage medium |
CN114527927A (en) * | 2020-11-20 | 2022-05-24 | 阿波罗智联(北京)科技有限公司 | Method and device for inputting information, electronic equipment and storage medium |
Also Published As
Publication number | Publication date |
---|---|
KR20190024072A (en) | 2019-03-08 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US9218066B2 (en) | Method for character correction | |
US9824085B2 (en) | Personal language model for input method editor | |
US7721203B2 (en) | Method and system for character sequence checking according to a selected language | |
CN104008093A (en) | Method and system for chinese name transliteration | |
JPH08506444A (en) | Handwriting recognition method of likely character strings based on integrated dictionary | |
KR20090109585A (en) | Contextual input method | |
WO2019045185A1 (en) | Mobile device and method for correcting character string entered through virtual keyboard | |
CN105630763A (en) | Method and system for making mention of disambiguation in detection | |
CN106257452A (en) | Search Results is revised based on contextual feature | |
CN104008123A (en) | Native-script and cross-script Chinese name matching | |
WO2018030601A1 (en) | Typographical error character correction method | |
KR20090023417A (en) | Techniques for filtering handwriting recognition results | |
US20140189640A1 (en) | Native Language IDE Code Assistance | |
US9002772B2 (en) | Scalable rule-based processing system with trigger rules and rule evaluator | |
CN107784055A (en) | Transaction methods and device based on non-relational database | |
CN111581344A (en) | Interface information auditing method and device, computer equipment and storage medium | |
JP2018195272A (en) | Information extraction device | |
US20150199332A1 (en) | Browsing history language model for input method editor | |
JP4734400B2 (en) | Document search apparatus and program | |
CN111143374B (en) | Data auxiliary identification method, system, computing device and storage medium | |
JP2006309377A (en) | Document retrieval device, document retrieval method, its program, and recording medium | |
JP7211139B2 (en) | Review method, information processing device and review program | |
JP2017167882A (en) | Sentence boundary estimation device, method, and program | |
EP3376348A1 (en) | Character input device, character input method, and character input program | |
WO2019146837A1 (en) | Method and mobile apparatus for performing word prediction |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 17923502 Country of ref document: EP Kind code of ref document: A1 |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17923502 Country of ref document: EP Kind code of ref document: A1 |
|
32PN | Ep: public notification in the ep bulletin as address of the adressee cannot be established |
Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 25/01/2021). |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 17923502 Country of ref document: EP Kind code of ref document: A1 |