WO2017175900A1 - Dispositif d'entrée en langue chinoise à base d'alphabet coréen et procédé utilisant la transcription phonétique en caractères romains en tant que support - Google Patents

Dispositif d'entrée en langue chinoise à base d'alphabet coréen et procédé utilisant la transcription phonétique en caractères romains en tant que support Download PDF

Info

Publication number
WO2017175900A1
WO2017175900A1 PCT/KR2016/003684 KR2016003684W WO2017175900A1 WO 2017175900 A1 WO2017175900 A1 WO 2017175900A1 KR 2016003684 W KR2016003684 W KR 2016003684W WO 2017175900 A1 WO2017175900 A1 WO 2017175900A1
Authority
WO
WIPO (PCT)
Prior art keywords
pronunciation
chinese
roman
notation
chinese word
Prior art date
Application number
PCT/KR2016/003684
Other languages
English (en)
Korean (ko)
Inventor
이문호
강두원
Original Assignee
(주)신명시스템즈
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 (주)신명시스템즈 filed Critical (주)신명시스템즈
Publication of WO2017175900A1 publication Critical patent/WO2017175900A1/fr

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
    • 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

Definitions

  • the present invention relates to a Hangul-based Chinese input technique that supports the user to automatically input a Chinese word corresponding to the pronunciation on the electronic document when the user inputs a pronunciation for a specific Chinese word on the electronic document.
  • a desktop PC, a mobile phone, a notebook, a tablet PC, etc. provide a user with an Hangul input interface and an English input interface at the same time, so that the user can select the desired interface and input Korean or English.
  • the Chinese-Hangul is arranged by mapping all the pronunciations of the Chinese words into Korean.
  • the conversion table needs to be stored in the terminal device.
  • Chinese uses a pronunciation table that formally forms the pronunciation of Chinese characters in Roman pronunciation.
  • the pronunciation table is an officially constructed and used table in China, when a user inputs a pronunciation of a specific Chinese word in an electronic document in Korean using a roman pronunciation notation for a Chinese word that is already built, There is a need for research on a technique for automatically converting corresponding Chinese words and inputting them into electronic documents.
  • the Hangul-based Chinese input device and method using the roman pronunciation notation according to the present invention correspond to and store a roman pronunciation notation set for a plurality of Chinese words on the basis of the roman pronunciation notation information for Chinese which has already been constructed.
  • a user After building a Chinese pronunciation database, if a user inputs a Hangul pronunciation for a predetermined Chinese word on an electronic document by maintaining a Hangul character pronunciation database stored in correspondence with Roman phonetic notation for each of a plurality of Hangul characters, the Hangul After extracting the roman pronunciation notations corresponding to the Hangul characters inputted into the electronic document from the character pronunciation database, extracting a Chinese word having the extracted roman pronunciation notations as the Roman pronunciation notation set from the Chinese pronunciation database and inputting them on the electronic document. by doing, Even if you create a table recording the Korean Hangul pronunciation of words and respond to it easily allows the user to separately to enable you to enter the Chinese word on the electronic document based on Hangul.
  • a Hangul-based Chinese input device using a roman phonetic transcription is stored in which a plurality of Chinese words and a set of Roman phonetic transcriptions for each of the plurality of Chinese words are stored in correspondence with each other.
  • a Chinese pronunciation database, a plurality of Korean characters and a Hangul character pronunciation database in which the Roman phonetic transcriptions of the pronunciation of each of the plurality of Korean characters are stored in correspondence with each other, and the Chinese of any one of the plurality of Chinese words by the user Roman letters for extracting at least one first roman pronunciation notation corresponding to each of the at least one first Hangul characters from the Hangul character pronunciation database when at least one first Hangul character for pronunciation of a word is input on the electronic document Extraction unit, the written word from the Chinese pronunciation database Chinese word determination unit for determining whether there is a first Chinese word having a roman pronunciation notation as a roman pronunciation notation set that matches all of the first roman pronunciation notation, the first Chinese word on the Chinese pronunciation database If it is determined to exist, the Chinese word extracting unit
  • the Hangul-based Chinese input method using the roman pronunciation notation stores a plurality of Chinese words and a set of roman pronunciation notations for the pronunciation of each of the plurality of Chinese words. Maintaining the Chinese pronunciation database, maintaining a Hangul character pronunciation database in which a plurality of Hangul characters and Roman phonetic transcriptions of the pronunciation of each of the Hangul characters are stored in correspondence with each other.
  • At least one first Hangul character for pronunciation of a Chinese word of a plurality of Chinese words is input on an electronic document, at least one corresponding to each of the at least one first Hangul characters from the Hangul character pronunciation database Extracting the first roman pronunciation notation of the Chinese pronunciation Determining whether a first Chinese word having a roman pronunciation notation as a roman pronunciation notation set that matches all of the at least one first roman pronunciation notation exists from a database, wherein the first Chinese word is displayed on the Chinese pronunciation database; If it is determined to exist, extracting the first Chinese word from the Chinese pronunciation database and inputting the extracted first Chinese word on the electronic document as a Chinese word corresponding to the at least one first Korean character; It includes a step.
  • the Hangul-based Chinese input device and method using the roman pronunciation notation according to the present invention correspond to and store a roman pronunciation notation set for a plurality of Chinese words on the basis of the roman pronunciation notation information for Chinese which has already been constructed.
  • a user After building a Chinese pronunciation database, if a user inputs a Hangul pronunciation for a predetermined Chinese word on an electronic document by maintaining a Hangul character pronunciation database stored in correspondence with Roman phonetic notation for each of a plurality of Hangul characters, the Hangul After extracting the roman pronunciation notations corresponding to the Hangul characters inputted into the electronic document from the character pronunciation database, extracting a Chinese word having the extracted roman pronunciation notations as the Roman pronunciation notation set from the Chinese pronunciation database and inputting them on the electronic document. by doing, Even if you create a table recording the Korean Hangul pronunciation of words and respond to it easily allows the user to separately can assist you to enter the Chinese word on the electronic document based on Hangul.
  • FIG. 1 is a diagram illustrating a structure of a Hangul-based Chinese input device using a roman phonetic transcription according to an embodiment of the present invention.
  • FIG. 2 is a view for explaining the operation of the Hangul-based Chinese input device via the roman phonetic transcription according to an embodiment of the present invention.
  • FIG. 3 is a flowchart illustrating a Hangul-based Chinese input method using a roman phonetic transcription according to an embodiment of the present invention.
  • FIG. 1 is a diagram illustrating a structure of a Hangul-based Chinese input device using a roman phonetic transcription according to an embodiment of the present invention.
  • a Hangul-based Chinese input device 110 using a roman pronunciation notation may include a Chinese pronunciation database 111, a Korean character pronunciation database 112, and a roman extractor ( 113, the Chinese word determination unit 114, the Chinese word extraction unit 115 and the Chinese word input unit 116.
  • the Hangul-based Chinese input device 110 which is based on the roman pronunciation pronunciation according to an embodiment of the present invention, drives an application program for electronic document creation such as a desktop PC, a mobile terminal, a PDA, a notebook computer, and a tablet PC. It can be implemented based on various kinds of microprocessor-based devices for supporting electronic document creation.
  • Hangul is a concept that includes not only modern Hangul but also all old Hangul such as Hunminjeongeum.
  • the Chinese pronunciation database 111 stores a plurality of Chinese words and a set of Roman phonetic transcriptions for the pronunciation of each of the Chinese words.
  • the Chinese pronunciation database 111 may store information as shown in Table 1 below.
  • the roman pronunciation notation set is " Using the Chinese word “for example,” The word “Chinese” is pronounced in three syllables, and the corresponding pronunciation is the Roman pronunciation “han”, the Roman pronunciation “guo” and the Roman pronunciation “ren”. As it constitutes a pronunciation for the Chinese word ",” the Roman pronunciation notation set refers to a set consisting of one or more Roman pronunciation notations "[han, guo, ren]" as shown in Table 1 above.
  • the Hangul character pronunciation database 112 stores a plurality of Hangul characters and Roman phonetic transcriptions of the pronunciation of each of the Hangul characters.
  • information may be stored in the Hangul character pronunciation database 112 as shown in Table 2 below.
  • the Hangul character extraction database 112 displays the message from the Hangul character pronunciation database 112. Extract at least one first roman phonetic transcription corresponding to each of the at least one first Korean character.
  • the Chinese word determination unit 114 determines whether a first Chinese word having a roman pronunciation notation that matches all of the at least one first roman pronunciation notation from the Chinese pronunciation database 111 exists as a Roman pronunciation notation set.
  • the Chinese word extractor 115 extracts the first Chinese word from the Chinese pronunciation database 111.
  • the Chinese word input unit 116 inputs the extracted first Chinese word on the electronic document as a Chinese word corresponding to the at least one first Korean character.
  • the Chinese word input unit 116 deletes the at least one first Korean character input on the electronic document, and the at least one The first Chinese word may be input at a position on the electronic document in which the first Hangul character of is input.
  • the Roman alphabet extracting unit 113 may perform "Han", “Gu”, “Run” from the Hangul character pronunciation database 112, respectively.
  • the roman pronunciation notation “han”, “guo”, and “ren” can be extracted as three roman pronunciation notations.
  • the Chinese word determining unit 114 has a roman pronunciation notation set corresponding to all three roman pronunciation notations "han”, “guo”, and "ren” from the Chinese pronunciation database 111 as a Roman pronunciation notation set. 1 Can determine whether or not Chinese words exist.
  • the Chinese pronunciation database 111 has the first Chinese word having a Roman pronunciation notation as a Roman pronunciation notation set that matches all three Roman phonetic notations "han”, “guo”, and "ren". Since the Chinese word "is present", the Chinese word determining unit 114 is displayed on the Chinese pronunciation database 111. It can be determined that the first Chinese word "" exists.
  • the Chinese word extracting unit 115 determines that the first Chinese word is “1” from the Chinese pronunciation database 111. "Can be extracted.
  • the Chinese word input unit 116 is the extracted " "" Can be entered on the electronic document as a Chinese word corresponding to a three-character Hangul character "Han Gurun”.
  • the Chinese word input unit 116 deletes the three-letter Hangul characters "Hangoran” input on the electronic document, and the three-letter Hangul word “Hangurun". The first Chinese word "" "Can be entered.
  • the Hangul-based Chinese input device 110 using the roman pronunciation notation is based on the roman pronunciation notation information for Chinese, which is already established, the roman pronunciation of a plurality of Chinese words.
  • the user can designate a user on the electronic document by maintaining the Hangul character pronunciation database 112 corresponding to and storing Roman phonetic notation for each of a plurality of Korean characters. If the Hangul pronunciation of a Chinese word is inputted, the phonetic alphabet is extracted from the Hangul character pronunciation database 112 and the roman pronunciation notations corresponding to the Hangul characters entered in the electronic document are extracted from the Chinese pronunciation database 111.
  • the Chinese word extracted from the Roman phonetic transcription set is extracted from the electronic document.
  • the Hangul-based Chinese input device 110 through the roman phonetic notation is a user's Hangul for the Chinese word, such as "Kan Gurun", rather than "Han Gurun” on the electronic document.
  • the system may further include a configuration for implementing an automatic error correction function for automatically selecting the most suitable Chinese word based on the wrong Korean phonetic phonetic letters and inputting the same on the electronic document.
  • the Chinese word extractor 115 may include a candidate group extractor 117, a pronunciation similarity calculator 118, and a Chinese word selector 119.
  • the candidate group extracting unit 117 determines that the first Chinese word does not exist in the Chinese pronunciation database 111 by the Chinese word determining unit 114, from the Chinese pronunciation database 111. At least one second Chinese word including a roman pronunciation notation that matches a predetermined number or more of the roman pronunciation notations in the roman pronunciation notation set is extracted as a candidate group.
  • the pronunciation similarity calculator 118 may include a set of roman pronunciation notations corresponding to each of the at least one first and second Chinese words and the at least one second Chinese word for each of the at least one second Chinese word extracted as the candidate group. Compute phonetic similarities between Roman phonetic notations that do not match each other.
  • the Chinese word selector 119 selects a third Chinese word having the maximum phonetic similarity among the at least one second Chinese word extracted as the candidate group.
  • the Chinese word input unit 116 may input the selected third Chinese word on the electronic document as a Chinese word corresponding to the at least one first Korean character.
  • the Roman alphabet extracting unit 113 may input “Kan”, “Guo” and “Run” from the Hangul Character Pronunciation Database 112, respectively.
  • the roman pronunciation notation “kan”, “guo”, and “ren” can be extracted from the three roman pronunciation notations corresponding to.
  • the Chinese word determination unit 114 has a roman pronunciation notation set that matches all three roman pronunciation notations "kan”, “guo”, and "ren” from the Chinese pronunciation database 111 as a Roman pronunciation notation set. 1 Can determine whether or not Chinese words exist.
  • the Chinese word determination unit 114 may determine that the first Chinese word does not exist in the Chinese pronunciation database 111.
  • the candidate group extracting unit 117 selects a roman pronunciation notation corresponding to at least a selected number of Roman pronunciation notations from the Chinese pronunciation database 111 including "kan”, “guo", and "ren". At least one second Chinese word included in the phonetic transcription set may be extracted as a candidate group.
  • the candidate group extracting unit 117 uses "kan”, “guo”, “ren” from the Chinese pronunciation database 111.
  • the pronunciation similarity calculating unit 118 is extracted with the candidate group ". ",” “And” “For each, three Roman phonetic notations” kan “,” guo “,” ren “and” “,” “And” “Between the corresponding roman pronunciation notation” [han, guo, ren] “,” [zhong, guo, ren] “and” [mei, guo, ren] " The phonetic similarity can be calculated.
  • the pronunciation similarity calculator 118 is " You can calculate phonetic similarity between “kan” and “han”, which are non-matching roman pronunciations for “,” You can calculate phonetic similarity between “kan” and “zhong”, which are non-matching roman pronunciations for “,” You can calculate the phonetic similarity between “kan” and “mei”, which are Roman phonetic notations for “.”
  • the Chinese word extractor 115 may include at least one different roman pronunciation, which is previously designated as a similar pronunciation for each of the plurality of roman pronunciation notations.
  • the apparatus may further include a similar pronunciation table holding unit 120 which stores and maintains a similar pronunciation table in which the notation is recorded.
  • the pronunciation similarity calculating unit 118 for each of the at least one second Chinese word extracted as the candidate group, the roman pronunciation corresponding to each of the at least one first roman pronunciation notation and the at least one second Chinese word.
  • a selected first score is given to the roman pronunciation notation pairs that are stored in correspondence with each other on the similar pronunciation table.
  • the selected second score lower than the selected first score with respect to the roman pronunciation notation pair not correspondingly stored in the similar pronunciation table on the similar pronunciation table, and then the selected first score and the selected first score.
  • the sum of the two scores can be calculated with the pronunciation similarity.
  • the pronunciation similarity calculator 118 is " When calculating the pronunciation similarity between "kan” and “han”, which are not the same as the Roman pronunciation notation for ",” kan “and” han “correspond to each other with similar pronunciation on the table of similar pronunciation as shown in Table 3 above. 10 points which are the selected first scores are given as the Roman pronunciation pronunciation pairs which are stored. It can be calculated with the phonetic similarity for ".
  • the pronunciation similarity calculating unit 118 is " When calculating the phonetic similarity between "kan” and “zhong", the Roman pronunciation notation for "to match each other,"”kan” and “zhong” correspond to each other in a similar pronunciation table as shown in Table 3 above. Since the pair is not stored in the Roman pronunciation pronunciation pair is given the 5 points which is the selected second score to the "5 points” It can be calculated with the phonetic similarity for ".
  • the pronunciation similarity calculator 118 is " When calculating the pronunciation similarity between "kan” and “mei", the Roman pronunciation notation for "to match each other,"”kan” and “mei” correspond to each other with similar pronunciations on the similar pronunciation table as shown in Table 3 above. Since the pair is not stored in the Roman pronunciation pronunciation pair is given the 5 points which is the selected second score to the "5 points” It can be calculated with the phonetic similarity for ".
  • the Chinese word selector 119 is extracted as the candidate group" "," "," A third Chinese word having the maximum pronunciation similarity may be selected from the Chinese word ".”
  • the Chinese word selector 119 selects” May be selected as the third Chinese word.
  • the Chinese word input unit 116 is the selected third Chinese word " May be input on the electronic document as a Chinese word corresponding to a Hangul character such as "Kan Guo Run”.
  • the Chinese word input unit 116 is " When " is selected as the third Chinese word, the Hangul character " Kangurunan " input on the electronic document is deleted, and the third word is located at the position on the electronic document where the Hangul letter " Kanguoran " The Chinese word " "Can be entered.
  • the Hangul-based Chinese input device 110 through the roman phonetic notation according to the present invention automatically extracts the most appropriate Chinese word corresponding to the user even if the user inputs the wrong pronunciation of Hangul characters on the electronic document.
  • the user's convenience can be aimed at.
  • the Hangul-based Chinese input device 110 via the roman phonetic transcription is a phonetic notation set extractor 121, a Hangul character extractor 122, and a correction pronunciation guide displayer ( 123 may be further included.
  • the pronunciation notation set extracting unit 121 selects the selected third Chinese word from the Chinese pronunciation database 111. Extract the first set of phonetic pronunciations stored corresponding to the word.
  • the Hangul character extraction unit 122 may include at least one second Hangul corresponding to each of the Roman phonetic transcriptions included in the first Roman phonetic transcription set from the Korean alphabet phonetic pronunciation database. Extract the character.
  • the corrective pronunciation guide display unit 123 may select the at least one second Hangul character based on a position where the third Chinese word is input on the electronic document. The message is displayed along with a message informing that the correct Hangul pronunciation of the third Chinese word.
  • the pronunciation notation set extraction unit 121 is the third Chinese word selected from the Chinese pronunciation database 111. "[Han, guo, ren]” may be extracted as the first set of phonetic transcriptions stored corresponding to ".”
  • the Hangul character extracting unit 122 is the Hangul character notation database “han”, “guo” that is included in the first roman pronunciation notation set “[han, guo, ren]” from the Hangul character pronunciation database 112 "Han”, “Guo", and “run” may be extracted as at least one second Hangul character corresponding to each of "and” ren ".
  • the corrected pronunciation guide display unit 123 may display a Hangul character “Han Gurun” in the third Chinese language on the electronic document.
  • the word “ “At this location, the Hangul character” Han Gurun” is displayed on the selected separation point and at the same time”
  • a message indicating that the correct Korean pronunciation of the Chinese word "" can be displayed.
  • the corrected pronunciation guide display unit 123 may output a Hangul character “Hango Run” to the electronic document.
  • the third Chinese word on 210 is " "Hangul” is displayed on the selected separation point 212 centered on the input position 211, and at the same time the Hangul characters " A message indicating that the correct Korean pronunciation of the Chinese word "" can be displayed.
  • FIG. 3 is a flowchart illustrating a Hangul-based Chinese input method using a roman phonetic transcription according to an embodiment of the present invention.
  • a Chinese pronunciation database in which a plurality of Chinese words and a set of Roman phonetic transcriptions for each of the plurality of Chinese words are stored in correspondence with each other is stored.
  • a Hangul character pronunciation database in which a plurality of Hangul characters and Roman phonetic transcriptions of the pronunciation of each of the Hangul characters are stored in correspondence with each other is stored.
  • the at least one first Korean character when at least one first Korean character for pronunciation of a Chinese word of the plurality of Chinese words is input on an electronic document by the user, the at least one first Korean character may be input from the Korean character pronunciation database. 1 At least one first roman pronunciation notation corresponding to each Hangul character is extracted.
  • step S340 it is determined from the Chinese pronunciation database whether there is a first Chinese word having a roman pronunciation notation that matches all of the at least one first roman pronunciation notation as a Roman pronunciation notation set.
  • the extracted first Chinese word is input on the electronic document as a Chinese word corresponding to the at least one first Korean character.
  • the at least one first Korean character input on the electronic document is deleted and the at least one first word is deleted.
  • the first Chinese word may be input at a location on the electronic document in which Korean characters are input.
  • the step S340 it is determined that the first Chinese word does not exist on the Chinese pronunciation database.
  • at least one second Chinese word having a roman pronunciation notation that matches a selected number of roman pronunciation notations among the at least one first roman pronunciation notation in a roman pronunciation notation set as a candidate group.
  • each of the at least one second Chinese word extracted as the candidate group does not coincide with each other between the set of the at least one first roman pronunciation and the at least one set of roman pronunciation corresponding to each of the at least one second Chinese word.
  • the method may further include inputting the Chinese word on the electronic document.
  • the Hangul-based Chinese input method using the roman pronunciation notation corresponds to at least one different roman pronunciation notation that is previously designated as a similar pronunciation for each of the plurality of Roman pronunciation notations.
  • the method may further include storing and maintaining a similar pronunciation table that is recorded.
  • the calculating of the phonetic similarity may include calculating each of the at least one second Chinese word extracted as the candidate group, and at least one roman alphabet corresponding to each of the at least one second Chinese word and the at least one second Chinese word.
  • a selected first score is given to the roman pronunciation notation pairs that are stored in correspondence with one another on the similar pronunciation table.
  • the selected second score lower than the selected first score for the roman pronunciation notation pair not correspondingly stored in the similar pronunciation table on the similar pronunciation table, and then the selected first score and the selected first score.
  • the sum of the second scores is calculated with the pronunciation similarity.
  • the Hangul-based Chinese input method using the roman phonetic transcription is the electronic document in which the selected third Chinese word is a Chinese word corresponding to the at least one first Korean character. Extracting a first roman pronunciation notation set stored in correspondence with the selected third Chinese word from the Chinese pronunciation database when the first roman pronunciation notation set is extracted; Extracting at least one second Hangul character corresponding to each of the roman pronunciation notations included in the first roman pronunciation notation set; and if the at least one second Hangul character is extracted, the at least one second Hangul character Character around the position where the third Chinese word is entered on the electronic document
  • the method may further include displaying on the selected separation point together with a message indicating that the correct Hangul pronunciation of the third Chinese word.
  • the Korean-based Chinese input method using the roman pronunciation notation according to an embodiment of the present invention has been described.
  • the Hangul-based Chinese input method using the roman phonetic notation according to an embodiment of the present invention is a Korean-based Chinese input device 110 via the Roman phonetic notation described using FIGS. 1 and 2. Since the configuration may correspond to an operation, a detailed description thereof will be omitted.
  • the Hangul-based Chinese input method using the roman pronunciation notation may be implemented as a computer program stored in a storage medium for execution by combining with a computer.
  • the Hangul-based Chinese input method using the roman phonetic notation may be implemented in the form of program instructions that can be executed by various computer means and recorded in a computer readable medium.
  • the computer readable medium may include program instructions, data files, data structures, etc. alone or in combination.
  • Program instructions recorded on the media may be those specially designed and constructed for the purposes of the present invention, or they may be of the kind well-known and available to those having skill in the computer software arts.
  • Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tape, optical media such as CD-ROMs, DVDs, and magnetic disks, such as floppy disks.
  • Magneto-optical media and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like.
  • program instructions include not only machine code generated by a compiler, but also high-level language code that can be executed by a computer using an interpreter or the like.
  • the hardware device described above may be configured to operate as one or more software modules to perform the operations of the present invention, and vice versa.

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)
  • Document Processing Apparatus (AREA)

Abstract

La présente invention concerne une technique pour construire une base de données phonétique de langue chinoise dans laquelle des ensembles de transcriptions phonétiques en caractères romains sont stockés en correspondance avec une pluralité de mots en langue chinoise sur la base d'informations de transcription phonétique en caractères romains déjà construite pour la langue chinoise, puis pour maintenir une base de données phonétique coréenne dans laquelle une transcription phonétique en caractères romains est stockée en correspondance avec chacun d'une pluralité de caractères de l'alphabet coréen, de telle sorte que lorsqu'un utilisateur entre la prononciation en alphabet coréen d'un mot de langue chinoise prédéterminé dans un document électronique, des transcriptions phonétiques en caractères romains correspondant à un caractère de l'alphabet coréen entré dans le document électronique depuis la base de données phonétique coréenne sont extraites, puis un mot en langue chinoise ayant les transcriptions phonétiques en caractères romains extraites en tant qu'ensemble de transcriptions phonétiques en caractères romains est extrait de la base de données phonétique en langue chinoise, et le mot de langue chinoise extrait est entré dans le document électronique.
PCT/KR2016/003684 2016-04-05 2016-04-08 Dispositif d'entrée en langue chinoise à base d'alphabet coréen et procédé utilisant la transcription phonétique en caractères romains en tant que support WO2017175900A1 (fr)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
KR1020160041788A KR101658598B1 (ko) 2016-04-05 2016-04-05 로마자 발음 표기를 매개로 하는 한글 기반의 중국어 입력 장치 및 방법
KR10-2016-0041788 2016-04-05

Publications (1)

Publication Number Publication Date
WO2017175900A1 true WO2017175900A1 (fr) 2017-10-12

Family

ID=57080218

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/KR2016/003684 WO2017175900A1 (fr) 2016-04-05 2016-04-08 Dispositif d'entrée en langue chinoise à base d'alphabet coréen et procédé utilisant la transcription phonétique en caractères romains en tant que support

Country Status (2)

Country Link
KR (1) KR101658598B1 (fr)
WO (1) WO2017175900A1 (fr)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR102375575B1 (ko) * 2020-12-23 2022-03-17 주식회사 한글과컴퓨터 음성 특성을 이용하여 사용자 인증을 수행할 수 있는 전자 장치 및 그 동작 방법

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20010100112A (ko) * 2001-10-04 2001-11-14 서정수 국제 한글 음성 기호 입/출력법
KR20080047677A (ko) * 2006-11-27 2008-05-30 정원수 중국어 표기문자로서의 한글 입력장치 및 그 입력방법
KR20120000822A (ko) * 2010-06-28 2012-01-04 에스케이플래닛 주식회사 중국 병음의 한글 입력을 이용하여 검색할 수 있는 중국어 검색 장치 및 방법
JP5514760B2 (ja) * 2011-03-28 2014-06-04 Ｋｄｄｉ株式会社 中国語入力装置
KR20150085982A (ko) * 2014-01-17 2015-07-27 한국전자통신연구원 번역 장치 및 방법

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
KR20010100112A (ko) * 2001-10-04 2001-11-14 서정수 국제 한글 음성 기호 입/출력법
KR20080047677A (ko) * 2006-11-27 2008-05-30 정원수 중국어 표기문자로서의 한글 입력장치 및 그 입력방법
KR20120000822A (ko) * 2010-06-28 2012-01-04 에스케이플래닛 주식회사 중국 병음의 한글 입력을 이용하여 검색할 수 있는 중국어 검색 장치 및 방법
JP5514760B2 (ja) * 2011-03-28 2014-06-04 Ｋｄｄｉ株式会社 中国語入力装置
KR20150085982A (ko) * 2014-01-17 2015-07-27 한국전자통신연구원 번역 장치 및 방법

Also Published As

Publication number Publication date
KR101658598B1 (ko) 2016-09-21

Similar Documents

Publication Publication Date Title
WO2020164281A1 (fr) Procédé d'analyse de formulaire basé sur l'emplacement et la reconnaissance de caractères, ainsi que support et dispositif informatique
WO2016112558A1 (fr) Procédé et système de mise en correspondance de questions dans un système d'interaction intelligent
WO2015050321A1 (fr) Appareil pour générer un corpus d'alignement basé sur un alignement d'auto-apprentissage, procédé associé, appareil pour analyser un morphème d'expression destructrice par utilisation d'un corpus d'alignement et procédé d'analyse de morphème associé
WO2014003276A1 (fr) Dispositif et procédé permettant de saisir des mots chinois
WO2016208941A1 (fr) Procédé de prétraitement de texte et système de prétraitement permettant de mettre en œuvre ledit procédé
WO2017175900A1 (fr) Dispositif d'entrée en langue chinoise à base d'alphabet coréen et procédé utilisant la transcription phonétique en caractères romains en tant que support
WO2012165920A2 (fr) Procédé permettant d'entrer des caractères chinois au moyen d'un écran tactile comprenant une fonction de sélection d'intonation
JP2000298667A (ja) 構文情報による漢字変換装置
WO2019045185A1 (fr) Dispositif mobile, et procédé de correction de chaîne de caractères saisie via un clavier virtuel
WO2023075565A1 (fr) Outil de saisie de caractères japonais et procédé de saisie
US10133920B2 (en) OCR through voice recognition
WO2018074710A1 (fr) Dispositif électronique à écran tactile prenant en charge une entrée facile de caractères par le biais d'un clavier virtuel, et son procédé de fonctionnement
WO2009148224A2 (fr) Dispositif de saisie de caractères latins et terminal portable l'utilisant
KR101697237B1 (ko) 중국어 단어에 대한 한글 발음 학습 보조 장치 및 방법
WO2016085156A1 (fr) Procédé et appareil destinés à la saisie d'un caractère chinois
WO2015108229A1 (fr) Procédé de fonctionnement d'un terminal permettant de corriger un document électronique
CN103678276B (zh) 中国语显示装置、中国语显示方法
WO2019132480A1 (fr) Dispositif d'entrée de caractères chinois et procédé d'entrée de caractères chinois l'utilisant
WO2017047929A1 (fr) Dispositif à écran tactile apte à exécuter un événement basé sur une combinaison de gestes et son procédé de fonctionnement
WO2021118037A1 (fr) Dispositif électronique destiné à prendre en charge une pratique de dactylographie efficace par présentation de mots pour chaque niveau selon une classification de graphèmes, et son procédé de fonctionnement
CN111179645A (zh) 汉语拼音拼读方法、装置、设备和计算机可读存储介质
WO2014017840A1 (fr) Clavier utilisant un procédé de combinaison de touches et procédé de saisie de caractères l'utilisant
KR102243933B1 (ko) 번역된 문장에 포함된 단위의 자동 변환을 지원하는 번역 처리 장치 및 그 동작 방법
WO2016047853A1 (fr) Procédé de saisie d'alphabet coréen/d'alphabet anglais/de nombres grâce à un clavier logiciel
WO2024147461A1 (fr) Dispositif électronique fournissant une assistance pour permettre de réaliser une évaluation de prononciation sur la base d'une phrase d'évaluation de prononciation, et son procédé de fonctionnement

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16898004

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16898004

Country of ref document: EP

Kind code of ref document: A1