Handheld Electronic Device and Method for Disambiguation of Compound Text Input and That Employs N-Gram Data to Limit Generation of Low-Probability Compound Language Solutions

• US 20100153096A1
• Filed: 02/23/2010
• Published: 06/17/2010
• Est. Priority Date: 01/13/2006
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Elizarov, Michael G., Fux, Vadim
• Granted Patent: US 8,090,572 B2
• Time in Patent Office: Days
• US Class Current: 704/9
• CPC Class Codes: G06F 1/1626 with a single-body enclosure integrating a flat display, e.g. Personal Digital Assistants [PDAs]
• CPC Class Codes: G06F 1/1662 Details related to the integrated keyboard
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

A handheld electronic device includes a reduced QWERTY keyboard and is enabled with disambiguation software that is operable to disambiguate compound text input. The device is able to assemble language objects in the memory to generate compound language solutions. The device is able to analyze the combinations of language objects in light of N-gram data stored on the device to avoid proposing low-probability compound language solutions.

Claims

1. A method of enabling input into an electronic device having a plurality of input members, a display, and a memory having stored therein a number of language objects and a number of associated frequency objects, at least some of the language objects each comprising a number of characters, at least some of the input members each having a number of the characters assigned thereto, the method comprising:

detecting an ambiguous text input;

generating a number of compound language solutions by identifying a language object that corresponds with an initial portion of the ambiguous text input and identifying another language object that corresponds with another portion of the ambiguous text input;

for at least a first compound language solution, generating a junction object comprising a terminal character of the language object and an initial character of the another language object, and making a determination that at least one of;

the junction object corresponds with a language object associated with a frequency object having a frequency value below a predetermined threshold, and

no language object corresponds with the junction object; and

employing the determination in outputting with the display a representation of each of at least some of the compound language solutions.

2. The method of claim 1 wherein the employing of the determination in the outputting comprises at least one of

outputting a representation of the at least first compound language solution at a position of relatively lower priority than a representation of another compound language solution, and

suppressing from the output the at least first compound language solution.

3. The method of claim 1 wherein the number of language objects comprise a number of word objects and a number of n-gram objects, and further comprising making as the determination a determination that at least one of:

the junction object corresponds with an n-gram object associated with a frequency object having a frequency value below a predetermined threshold, and

no n-gram object corresponds with the junction object.

4. The method of claim 1, further comprising:

determining that an intermediate portion of the ambiguous text input following the initial portion is consistent with a suffix object in the memory;

employing as the another portion of the ambiguous text input the portion of the ambiguous text input following the intermediate portion; and

generating as the junction object an object comprising the terminal character of the language object, the suffix object, and the initial character of the another language object.

5. An electronic device comprising:

a processor apparatus comprising a processor and a memory having stored therein a number of language objects and a number of associated frequency objects, at least some of the language objects each comprising a number of characters;

a plurality of input members, at least some of the input members each having a number of the characters assigned thereto;

a display; and

the memory further having stored therein one or more routines which, when executed on the processor, cause the electronic device to perform operations comprising;

detecting an ambiguous text input;

generating a number of compound language solutions by identifying a language object that corresponds with an initial portion of the ambiguous text input and identifying another language object that corresponds with another portion of the ambiguous text input;

for at least a first compound language solution, generating a junction object comprising a terminal character of the language object and an initial character of the another language object, and making a determination that at least one of;

the junction object corresponds with a language object associated with a frequency object having a frequency value below a predetermined threshold, and

no language object corresponds with the junction object; and

employing the determination in outputting with the display a representation of each of at least some of the compound language solutions.

6. The electronic device of claim 5 wherein the employing of the determination in the outputting comprises at least one of:

outputting a representation of the at least first compound language solution at a position of relatively lower priority than a representation of another compound language solution, and

suppressing from the output the at least first compound language solution.

7. The electronic device of claim 5 wherein the number of language objects comprise a number of word objects and a number of n-gram objects, and wherein the operations further comprise making as the determination a determination that at least one of:

the junction object corresponds with an n-gram object associated with a frequency object having a frequency value below a predetermined threshold, and

no n-gram object corresponds with the junction object.

8. The electronic device of claim 5 wherein the operations further comprise:

determining that an intermediate portion of the ambiguous text input following the initial portion is consistent with a suffix object in the memory;

employing as the another portion of the ambiguous text input the portion of the ambiguous text input following the intermediate portion; and

generating as the junction object an object comprising the terminal character of the language object, the suffix object, and the initial character of the another language object.

9. A method of enabling input into an electronic device having a plurality of input members, a display, and a memory having a number of language objects stored therein, at least some of the language objects each comprising a number of characters, at least some of the input members each having a number of the characters assigned thereto, the method comprising:

detecting an ambiguous text input;

generating a number of compound language solutions by identifying a language object that corresponds with an initial portion of the ambiguous text input and identifying another language object that corresponds with another portion of the ambiguous text input;

for at least a first compound language solution, generating a junction object comprising a terminal character of the language object and an initial character of the another language object, and making a determination that no language object corresponds with the junction object; and

employing the determination in outputting with the display a representation of each of at least some of the compound language solutions.

10. The method of claim 9 wherein the employing of the determination in the outputting comprises at least one of:

outputting a representation of the at least first compound language solution at a position of relatively lower priority than a representation of another compound language solution, and

suppressing from the output the at least first compound language solution.

11. The method of claim 9 wherein the number of language objects comprise a number of word objects and a number of n-gram objects, and further comprising making as the determination a determination that no n-gram object corresponds with the junction object.

12. The method of claim 9, further comprising:

determining that an intermediate portion of the ambiguous text input following the initial portion is consistent with a suffix object in the memory;

employing as the another portion of the ambiguous text input the portion of the ambiguous text input following the intermediate portion; and

generating as the junction object an object comprising the terminal character of the language object, the suffix object, and the initial character of the another language object.

13. An electronic device on which is performed the method of claim 9.