EXPLICIT CHARACTER FILTERING OF AMBIGUOUS TEXT ENTRY

• US 20140292664A1
• Filed: 06/13/2014
• Published: 10/02/2014
• Est. Priority Date: 12/03/1999
• Status: Active Grant

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Bradford, Ethan Robert, Hullfish, Keith Charles, Kay, David, Van Meurs, Pim, Long, Michael R.
• Granted Patent: US 8,990,738 B2
• Time in Patent Office: Days
• US Class Current: 345/169
• CPC Class Codes: G06F 16/3344 using natural language analysis
• CPC Class Codes: G06F 16/338 Presentation of query results
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 3/02 Input arrangements using manually operated switches, e.g. using keyboards or dials
• CPC Class Codes: G06F 3/0233 Character input methods
• CPC Class Codes: G06F 3/0235 using chord techniques G06F3/0234 takes precedence
• CPC Class Codes: G06F 3/0236 using selection techniques to select from displayed items
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/04842 Selection of displayed objects or displayed text elements G06F3/0482 takes precedence
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination

Abstract

The present invention relates to a method and apparatus for explicit filtering in ambiguous text entry. The invention provides embodiments including various explicit text entry methodologies, such as 2-key and long pressing. The invention also provides means for matching words in a database using build around methodology, stem locking methodology, word completion methodology, and n-gram searches.

Claims

1. An apparatus for key input comprising:

a keyboard configured to accept a plurality of key inputs, wherein at least one key input is received by any combination of;

long pressing a key to display and cycle through a character sequence; and

long pressing a key to enter a number/digit explicitly;

wherein responsive to receiving a key input, a single, character is received.

2. The apparatus of claim 1, further comprising:

a processor executing instructions, based on a sequence of key inputs, for generating a first set of character sequences, wherein each character of each character sequence in the first set of character sequences corresponds to either an intended key input or a potentially intended key input and in which each character is selected from the plurality of intended or potentially intended characters associated with the corresponding respective key input; and

based on the first set of character sequences, said processor searching a database for objects to identify a first set of potential desired objects and receiving a selection of a first desired object from the first set of potential desired objects.

3. The apparatus of claim 2, wherein a desired object further comprises the one or more characters received by a long pressing key input.

4. The apparatus of claim 3, wherein the processor generates the desired object by concatenating characters in the following order:

the characters of the first desired object, the one or more characters received by a long pressing key input, and the characters of the second desired object.

5. The apparatus of claim 1, wherein said plurality of key inputs comprise any of letters, digits, punctuation marks, Japanese kana, Korean jamos, and icons.

6. The apparatus of claim 1, wherein objects comprise words, part of words, word stems, icons, phone numbers, inventory records, and sequences of characters.

7. The apparatus of claim 1, further comprising speech synthesis software and a speaker as a communication aid.

8. The apparatus of claim 1, wherein a key input is further received by any combination of:

2-key explicit entry comprising two keys entered in sequence, wherein the combination of the two keys entered in sequence identifies a single character;

changing to a numbers mode and pressing a key to enter a number/digit;

changing to a multi-tap mode and pressing a key repeatedly to enter a character;

interpreting key presses as an intended character, either by grouping each pair of key presses as a 2-key entry, or by grouping repeated presses of the same key as a multi-tap entry;

using multi-switch keys, thereby permitting a potentially intended entry on a simple press and an intended character entry on a different kind of press;

chording by pressing more than one key simultaneously, with a primary key indicating a potentially intended set of characters and a secondary key indicating which character in the set to select; and

using a softkey as a secondary means for offering any character assigned to a key based on analysis of most likely character associated with a preceding keystroke or based on words in a current word candidate list.

9. The apparatus of claim 8, wherein an intended key input by 2-key entry comprises use of at least one of:

a matrix display;

a label including a subset of predetermined sets of associated characters; and

a scrolling list.

10. The apparatus of claim 1, wherein long pressing a key to display and cycle through a character sequence further comprises, after a character sequence is displayed, either of:

a next character in said character sequence is highlighted each additional time said key is pressed, ending after a sufficient time elapses between one key press and the next or when a different key is pressed;

or

a next character in said character sequence is highlighted each time a navigation key is pressed.

11. The apparatus of claim 1, wherein a selection of a desired object from a set of potential desired objects found in a database is received subsequent to displaying the set of potential desired objects in a pre-determined order.

12. A method for key input comprising:

providing a keyboard configured to accept a plurality of key inputs, wherein at least one key input is received by any combination of;

long pressing a key to display and cycle through a character sequence; and

long pressing a key to enter a number/digit explicitly;

wherein responsive to receiving a key input, a single, character is received.

13. The method of claim 12, further comprising:

providing a processor executing instructions, based on a sequence of key inputs, for generating a first set of character sequences, wherein each character of each character sequence in the first set of character sequences corresponds to either an intended key input or a potentially intended key input and in which each character is selected from the plurality of intended or potentially intended characters associated with the corresponding respective key input; and

based on the first set of character sequences, said processor searching a database for objects to identify a first set of potential desired objects and receiving a selection of a first desired object from the first set of potential desired objects.

14. The method of claim 13, wherein a desired object further comprises the one or more characters received by a long pressing key input.

15. The method of claim 14, further comprising;

said processor generating the desired object by concatenating characters in the following order;

the characters of the first desired object, the one or more characters received by a long pressing key input, and the characters of the second desired object.

16. The method of claim 12, wherein said plurality of key inputs comprise any of letters, digits, punctuation marks, Japanese kana, Korean jamos, and icons.

17. The method of claim 12, wherein objects comprise words, part of words, word stems, icons, phone numbers, inventory records, and sequences of characters.

18. The method of claim 12, further comprising:

providing speech synthesis software and a speaker as a communication aid.

19. The method of claim 12, further comprising:

receiving a key input by any combination of;

2-key explicit entry comprising two keys entered in sequence, wherein the combination of the two keys entered in sequence identifies a single character;

changing to a numbers mode and pressing a key to enter a number/digit;

changing to a multi-tap mode and pressing a key repeatedly to enter a character;

interpreting key presses as an intended character, either by grouping each pair of key presses as a 2-key entry, or by grouping repeated presses of the same key as a multi-tap entry;

using multi-switch keys, thereby permitting a potentially intended entry on a simple press and an intended character entry on a different kind of press;

chording by pressing more than one key simultaneously, with a primary key indicating a potentially intended set of characters and a secondary key indicating which character in the set to select; and

using a softkey as a secondary means for offering any character assigned to a key based on analysis of most likely character associated with a preceding keystroke or based on words in a current word candidate list.

20. The method of claim 19, further comprising:

for an intended key input by 2-key entry, using of at least one of;

a matrix display;

a label including a subset of predetermined sets of associated characters; and

a scrolling list.

21. The method of claim 12, further comprising:

long pressing a key to display and cycle through a character sequence, after a character sequence is displayed, wherein either of;

a next character in said character sequence is highlighted each additional time said key is pressed, ending after a sufficient time elapses between one key press and the next or when a different key is pressed;

or

a next character in said character sequence is highlighted each time a navigation key is pressed.

22. The method of claim 12, further comprising:

receiving a selection of a desired object from a set of potential desired objects found in a database subsequent to displaying the set of potential desired objects in a pre-determined order.