WO2008025123A1 - Procédé d'identification du langage de texte dans un dispositif électronique à tenue manuelle et dispositif électronique à tenue manuelle correspondant - Google Patents

Procédé d'identification du langage de texte dans un dispositif électronique à tenue manuelle et dispositif électronique à tenue manuelle correspondant Download PDF

Info

Publication number
WO2008025123A1
WO2008025123A1 PCT/CA2006/001448 CA2006001448W WO2008025123A1 WO 2008025123 A1 WO2008025123 A1 WO 2008025123A1 CA 2006001448 W CA2006001448 W CA 2006001448W WO 2008025123 A1 WO2008025123 A1 WO 2008025123A1
Authority
WO
WIPO (PCT)
Prior art keywords
text
electronic device
language
linguistic objects
handheld electronic
Prior art date
Application number
PCT/CA2006/001448
Other languages
English (en)
Inventor
Vadim Fux
Sergey Kolomiets
Original Assignee
Research In Motion Limited
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 Research In Motion Limited filed Critical Research In Motion Limited
Priority to CA2661559A priority Critical patent/CA2661559C/fr
Priority to DE112006004015T priority patent/DE112006004015T5/de
Priority to PCT/CA2006/001448 priority patent/WO2008025123A1/fr
Priority to GB0903317.6A priority patent/GB2454147B/en
Publication of WO2008025123A1 publication Critical patent/WO2008025123A1/fr

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F40/00—Handling natural language data
    • G06F40/20—Natural language analysis
    • G06F40/263—Language identification

Definitions

  • aspects of the disclosure relate to identifying language of text in a handheld electronic device.
  • Generating text in a handheld electronic device examples of which include, for instance, personal data assistants (PDA's), handheld computers, two-way pagers, cellular telephones, text messaging devices, and the like, has become a complex process. This is due at least partially to the trend to make these handheld electronic devices smaller and lighter in weight. A limitation in making them smaller has been the physical size of the keypad if the keys are to be actuated directly by human fingers. Generally, there have been two approaches to solving this problem. One is to adapt the ten digit keypad indigenous to mobile phones for text input. This requires each key to support input of multiple characters. The second approach seeks to shrink the traditional full keypad, such as the QWERTY keyboard by doubling up characters to reduce the number of keys.
  • FIG. 1 is a front view of an exemplary handheld electronic device incorporating aspects of the disclosed and claimed concepts
  • FIG. 2 is a front view of an alternate exemplary handheld electronic device incorporating aspects of the disclosed and claimed concepts
  • FIG. 3 is a functional diagram in block form illustrating aspects of the disclosed and claimed concepts.
  • FIG. 4 is a flow chart illustrating operation of aspects of the disclosed and claimed concepts.
  • An aspect of the disclosed and claimed concepts is to identify the language of text and to verify the encoding of the text to minimize processing errors in a handheld electronic device.
  • An exemplary external source of text is e-mail messaging. Additional non-limiting examples include SMS (Short Message Service), MMS (Multi-Media
  • aspects of the disclosed and claimed concepts are directed to a method of identifying language of text in a handheld electronic device.
  • the handheld electronic device has at least one application for receiving text from a source external to the handheld electronic device.
  • the handheld electronic device also has available thereto a plurality of indicator lists with each indicator list comprising a number of linguistic objects which are indicative of a preselected language and which are in a different language from the linguistic objects of the other indicator lists.
  • the general method of the disclosed and claimed concepts includes analyzing the text to at least preliminarily determine an encoding of the text, and comparing linguistic objects of the text to at least some of the linguistic objects of at least some of the indicator lists to identify the language of the text and to verify the encoding of the text.
  • the processing apparatus has a processor and a memory.
  • Stored within the memory is at least one application for receiving text from a source external to the handheld electronic device.
  • Stored within the memory also is a plurality of indicator lists with each indicator list comprising a number of linguistic objects which are indicative of a preselected language and which are in a different language from the linguistic objects of the other indicator lists.
  • the memory has stored therein a number of routines which, when executed by the processor, cause the handheld electronic device to perform operations.
  • the general nature of the operations can be stated as analyzing the text to at least preliminarily determine an encoding of the text, and comparing linguistic objects of the text to at least some of the linguistic objects of at least some of the indicator lists to identify the language of the text and to verify the encoding of the text.
  • FIG. 1 illustrates a wireless handheld electronic device 1 , which is but an example of a type of a handheld electronic device to which aspects of the disclosed and claimed concepts can be applied.
  • the exemplary handheld electronic device 1 includes an input device 3 in the form of a keypad 5 and a thumbwheel 7 that are used to control the functions of the handheld electronic device 1 and to generate text and other inputs.
  • the keypad 5 constitutes a reduced QWERTY keyboard in which most of the keys 9 are used to input two letters of the alphabet. It is noted, however, that the keypad 5 may be of other configurations, such as an AZERTY keyboard, a QWERTZ keyboard, or other keyboard arrangement, whether presently known or unknown, and either reduced or not reduced.
  • the input generated by depressing one of these keys is ambiguous in that it is undetermined as to which letter was intended.
  • Various schemes have been devised for disambiguating the inputs generated by these keys 9 assigned multiple letters for input.
  • the input provided through the keypad 5 and thumbwheel 7 are displayed on a display 1 1 as is well known.
  • FIG. 2 illustrates an alternate wireless handheld electronic device 1, which is but another example of a type of a handheld electronic device to which aspects of the disclosed and claimed concepts can be applied. Elements that are presented in FIG. 2 which are similar to the elements found in FIG. 1 are labeled with the same element number in FIG. 2.
  • the exemplary handheld electronic device 1 includes an input device 3 in the form of a keypad 5 and a navigational tool 8 that is used to control the functions of the handheld electronic device 1 and to generate text and other inputs.
  • the keypad 5 constitutes a reduced QWERTY keyboard in which most of the keys 9 are used to input two letters of the alphabet.
  • the keypad 5 may be of other configurations, such as an AZERTY keyboard, a QWERTZ keyboard, or other keyboard arrangement, whether presently known or unknown, and either reduced or not reduced.
  • the input generated by depressing one of these keys is ambiguous in that it is undetermined as to which letter was intended.
  • Various schemes have been devised for disambiguating the inputs generated by these keys 9 assigned multiple letters for input.
  • the handheld electronic device 1 also includes the navigational tool 8.
  • the navigational tool 8 is a trackball 10 that can be rotated thereby allowing for the navigation of a cursor which is displayed on a display 11 in various directions including up, down, left, right, and any combination thereof.
  • the trackball 10 can also be depressed. When the trackball 10 is depressed, a selection is made based upon the current location of the cursor. For example, if the cursor is located over a given program icon, that program will be launched when the trackball 10 is depressed. The input provided through the keypad 5 and trackball 10 is displayed on the display 11.
  • FIG. 2 depicting the navigational tool 8 as being disposed on the front face of the handheld electronic device 1 the navigational tool 8 can also be disposed on a side of the handheld electronic device 1 in the form of the thumbwheel 7 as shown in FIG. 1.
  • the thumbwheel 7 of FIG. 1 which is capable of being rotated and depressed, may be disposed on the side of the handheld electronic device 1 of FIG. 1 in lieu of the trackball 10. Rotation of the thumbwheel 7 can provide a navigation input, while depression of the thumbwheel 7 can provide a selection input. Accordingly, rotation of the thumbwheel 7 can navigate the cursor over a particular program icon, while depression of the thumbwheel 7 with the cursor located over a given program icon can launch the program.
  • the input device 3 provides keystroke inputs to a processing apparatus 13 which may include, by way of example and not limitation, a memory, an operating system, a processor, a Java virtual machine, a run time environment or the like.
  • the handheld electronic devices 1 of FIGS. 1-2 each implement a plurality of applications 17. These applications may include, by way of example and not limitation, an address book 19, e-mail 21, a calendar 23, a memo 25, and additional applications, such as, for example, spell check and a phone application.
  • these applications 17 require text input that is implemented by a text input process 27, which forms part of an input system 15.
  • Various types of text input processes 27 can be used that employ lists 29 to facilitate the generation of text.
  • the text input process 27 utilizes software to progressively narrow the possible combination of letters that could be intended by a specified sequence of keystrokes.
  • Such "disambiguation" software is known.
  • Such systems employ a plurality of lists 29 of linguistic objects.
  • linguistic objects it is meant words and in some languages ideograms.
  • the keystrokes input linguistic elements which in the case of words, are characters or letters in the alphabet, and in the case of ideograms, strokes that make up the ideogram.
  • the lists 29 of language objects can also include abbreviations, and text shortcuts, which are becoming common with the growing use of various kinds of text messaging.
  • Lists 29 that can be used by the exemplary disambiguation text input process 27 can include a generic list 31 and a new list 33. Additional lists 35 can include learned words and special word lists such as technical terms.
  • Other types of text input processes 27 could include, by way of example and not limitation, prediction programs that anticipate a word intended by a user as it is typed in and thereby complete it, could also use word lists. Such a prediction program might be used with a full keypad.
  • Known disambiguation programs can assign frequencies of use to the linguistic objects, such as words or ideograms, in the lists 29 it uses to determine the linguistic object intended by the user.
  • Frequencies of use can be initially assigned based on statistics of common usage and can then be modified through actual usage. It is known for disambiguation programs to incorporate "learned" linguistic objects such as words that were not in the initial lists 29, but were inserted by the user to drive the output 37 to the intended new word. It is known to assign such learned words an initial frequency of use that is near the high end of the range of frequencies of use. This initial frequency of use is then modified through actual use as with the initially inserted words.
  • e-mail 21 One source for additional linguistic objects is by e-mail 21. Not only is it likely that new language objects contained in incoming e-mail 21 would be used by the user to generate a reply or other e-mail responses, such new linguistic objects could also be linguistic objects that the user might want to use in generating other text inputs.
  • a problem associated with using new linguistic objects received by e-mail 21 is that processing errors occur in the handheld electronic devices 1 of FIGS. 1-2 in identifying language of the text that is received.
  • quantities of text in various languages are transmitted by e-mail with a preselected encoding which is then translated by the handheld electronic device 1 into the text that is shown on display 11 of the handheld electronic device 1.
  • Encoding refers to the coding employed to transmit e-mail to the handheld electronic device 1. Encoding examples include, by way of example and not limitation, Unicode, ASCII and the like.
  • certain languages share the same encoding among characters, words or ideograms and the potential for processing errors exists in the handheld electronic device 1 in determining the identity of the language of the e-mail 21.
  • FIG. 4 illustrates a flow chart of a routine 39 for identifying language of text in the handheld electronic device 1.
  • the processor apparatus 13 of the handheld electronic device 1 has a processor and a memory.
  • Stored within the memory is at least one application for receiving text from a source external to the handheld electronic device 1.
  • Stored within the memory also is a plurality of indicator lists 41 with each indicator list 41 comprising a number of linguistic objects which are indicative of a preselected language and which are in a different language from the linguistic objects of the other indicator lists 41.
  • Each indicator list 41 may contain a set of most frequently found linguistic objects of the preselected language of the indicator list 41.
  • the indicator list 41 may have 20 or more linguistic objects stored within the memory.
  • the linguistic objects may be, by way of example and not limitation, words or ideograms.
  • the different languages may consist of different dialects of a same language used in one or more countries.
  • the incoming e-mails 43 are placed in a queue 45 for processing as permitted by the processing burden on the handheld electronic device 1.
  • Processing begins with scanning the e-mail to parse 47 the message into text.
  • the parsed message is then filtered at 49 to remove unwanted components, such as numbers, dates, and the like.
  • At least a portion of the message is then analyzed 51 for the frequency of use of characters in the text to at least preliminarily determine an encoding of the text.
  • Encoding examples include, by way of example and not limitation, Unicode, ASCII and the like.
  • the encoding of the text may dictate the language of the text but, in other circumstances, a plurality of languages will share the same encoding for various characters, words or ideograms which leads to processing problems in the handheld electronic device 1.
  • linguistic objects of the text are then compared 53 to at least some of the linguistic objects of indicator lists 41 to identify the language of the text and to verify the encoding of the text.
  • the linguistic objects of the text may be compared 53 with at least some of the linguistic objects of all of the indicator lists 41.
  • the handheld electronic device 1 determines 55 if a proportion of the quantity of linguistic objects of the text that are also found in a given indicator list 41 to the total quantity of linguistic objects of text reaches a preselected threshold.
  • the routine 39 determines 55 that the language of the text is the preselected language of a particular indicator list 41. The identification of a language would verify that the encoding of the text was correctly analyzed at 51. If, for example, the linguistic objects of the text are in a particular indicator list 41 at a proportion of less than 10%, the routine 39 determines that the language of the text has not yet been identified. If no language can be identified for the text, the routine 39 concludes that the encoding of the text has not been determined accurately so the linguistic objects of the text are routed to be analyzed 51 or compared 53 again.
  • routine 39 may end.
  • the linguistic objects of the text may be added to lists 29 that facilitate the generation of text in various disambiguation schemes.
  • the linguistic objects of the text may be shown on display 11. For example, in certain languages, the encoding of certain letters or ideograms are the same. A user of the handheld electronic device 1 in Japan may not enjoy viewing Chinese characters appearing on display 11 because the processor did not have the ability to differentiate between the encoding of a Japanese and Chinese ideogram.
  • the above method identifies the language in a received e-mail.
  • other text received from sources outside the handheld electronic device 1 can also be scanned for new words. This can include identifying the language used in instant messages, SMS (short message service), MMS (multimedia service), and the like.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Computational Linguistics (AREA)
  • General Health & Medical Sciences (AREA)
  • Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Telephone Function (AREA)

Abstract

Cette invention concerne un dispositif électronique à tenue manuelle possédant au moins une application pour la réception d'un texte provenant d'une source extérieure audit dispositif. Le dispositif de l'invention dispose également d'une pluralité de listes d'indicateurs comprenant un certain nombre d'objets linguistiques renseignant sur un langage présélectionné et qui sont présentés dans une langue différente de celles des objets linguistiques des autres listes d'indicateurs. Le dispositif à tenue manuelle analyse le texte afin de déterminer au moins à titre préliminaire un codage pour le texte, puis compare les objets linguistiques du texte à au moins certains des listes d'indicateurs afin d'identifier le langage du texte et de vérifier le codage de ce texte.
PCT/CA2006/001448 2006-09-01 2006-09-01 Procédé d'identification du langage de texte dans un dispositif électronique à tenue manuelle et dispositif électronique à tenue manuelle correspondant WO2008025123A1 (fr)

Priority Applications (4)

Application Number Priority Date Filing Date Title
CA2661559A CA2661559C (fr) 2006-09-01 2006-09-01 Procede d'identification du langage de texte dans un dispositif electronique a tenue manuelle et dispositif electronique a tenue manuelle correspondant
DE112006004015T DE112006004015T5 (de) 2006-09-01 2006-09-01 Verfahren zum Identifizieren der Sprache von Text in einer handgehaltenen bzw. tragbaren elektronischen Vorrichtung und eine tragbare elektronische Vorrichtung, die dies aufweist
PCT/CA2006/001448 WO2008025123A1 (fr) 2006-09-01 2006-09-01 Procédé d'identification du langage de texte dans un dispositif électronique à tenue manuelle et dispositif électronique à tenue manuelle correspondant
GB0903317.6A GB2454147B (en) 2006-09-01 2006-09-01 Method for identifying language of text in a handheld electronic device and a handheld electronic device incorporating the same

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CA2006/001448 WO2008025123A1 (fr) 2006-09-01 2006-09-01 Procédé d'identification du langage de texte dans un dispositif électronique à tenue manuelle et dispositif électronique à tenue manuelle correspondant

Publications (1)

Publication Number Publication Date
WO2008025123A1 true WO2008025123A1 (fr) 2008-03-06

Family

ID=39135451

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CA2006/001448 WO2008025123A1 (fr) 2006-09-01 2006-09-01 Procédé d'identification du langage de texte dans un dispositif électronique à tenue manuelle et dispositif électronique à tenue manuelle correspondant

Country Status (4)

Country Link
CA (1) CA2661559C (fr)
DE (1) DE112006004015T5 (fr)
GB (1) GB2454147B (fr)
WO (1) WO2008025123A1 (fr)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111160015A (zh) * 2019-12-24 2020-05-15 北京明略软件系统有限公司 一种实现文本分析的方法、装置、计算机存储介质及终端

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9672209B2 (en) 2012-06-21 2017-06-06 International Business Machines Corporation Dynamic translation substitution

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030078982A1 (en) * 2001-10-19 2003-04-24 Matsushita Graphic Communication Systems, Inc. Electronic mail transmission apparatus and method
US20060025988A1 (en) * 2004-07-30 2006-02-02 Ming Xu Fast text character set recognition
US20060074628A1 (en) * 2004-09-30 2006-04-06 Elbaz Gilad I Methods and systems for selecting a language for text segmentation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030078982A1 (en) * 2001-10-19 2003-04-24 Matsushita Graphic Communication Systems, Inc. Electronic mail transmission apparatus and method
US20060025988A1 (en) * 2004-07-30 2006-02-02 Ming Xu Fast text character set recognition
US20060074628A1 (en) * 2004-09-30 2006-04-06 Elbaz Gilad I Methods and systems for selecting a language for text segmentation

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111160015A (zh) * 2019-12-24 2020-05-15 北京明略软件系统有限公司 一种实现文本分析的方法、装置、计算机存储介质及终端
CN111160015B (zh) * 2019-12-24 2024-03-05 北京明略软件系统有限公司 一种实现文本分析的方法、装置、计算机存储介质及终端

Also Published As

Publication number Publication date
GB2454147A (en) 2009-04-29
DE112006004015T5 (de) 2009-07-02
GB2454147B (en) 2014-03-12
CA2661559A1 (fr) 2008-03-06
CA2661559C (fr) 2013-07-16
GB0903317D0 (en) 2009-04-08

Similar Documents

Publication Publication Date Title
US8423908B2 (en) Method for identifying language of text in a handheld electronic device and a handheld electronic device incorporating the same
US7548849B2 (en) Method for generating text that meets specified characteristics in a handheld electronic device and a handheld electronic device incorporating the same
US7620540B2 (en) Method for generating text in a handheld electronic device and a handheld electronic device incorporating the same
US8539350B2 (en) Automatic language selection for improving text accuracy
US7656317B2 (en) Reduced keypad for multi-tap input
US20160085726A1 (en) Converting text strings into number strings, such as via a touchscreen input
US9009624B2 (en) Keyboard gestures for character string replacement
US20090058688A1 (en) Disambiguation of keypad text entry
EP1722294B1 (fr) Dispositif portatif comprenant un procédé de génération de texte
CA2563233C (fr) Selection de langue automatique permettant d'ameliorer la precision du texte
CA2606328C (fr) Procede pour generer du texte qui correspond a des criteres preetablies dans un dispositif electronique de poche et dispositif electronique de poche utilisant ce procede
CA2661559C (fr) Procede d'identification du langage de texte dans un dispositif electronique a tenue manuelle et dispositif electronique a tenue manuelle correspondant
EP2256643B1 (fr) Dispositif électronique portable et procédé associé pour améliorer l'efficacité de frappe sur le dispositif
CN112925469A (zh) 内容显示方法、装置、存储介质及电子设备

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: 06790625

Country of ref document: EP

Kind code of ref document: A1

DPE1 Request for preliminary examination filed after expiration of 19th month from priority date (pct application filed from 20040101)
WWE Wipo information: entry into national phase

Ref document number: 2661559

Country of ref document: CA

ENP Entry into the national phase

Ref document number: 0903317

Country of ref document: GB

Kind code of ref document: A

Free format text: PCT FILING DATE = 20060901

WWE Wipo information: entry into national phase

Ref document number: 0903317.6

Country of ref document: GB

WWE Wipo information: entry into national phase

Ref document number: 1120060040154

Country of ref document: DE

RET De translation (de og part 6b)

Ref document number: 112006004015

Country of ref document: DE

Date of ref document: 20090702

Kind code of ref document: P

122 Ep: pct application non-entry in european phase

Ref document number: 06790625

Country of ref document: EP

Kind code of ref document: A1

REG Reference to national code

Ref country code: DE

Ref legal event code: 8607