MULTIPLE PREDICTIONS IN A REDUCED KEYBOARD DISAMBIGUATING SYSTEM

• US 20080291059A1
• Filed: 05/01/2008
• Published: 11/27/2008
• Est. Priority Date: 05/22/2007
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Tegic Communications, Inc. (Microsoft Corporation)
• Inventors: Longe, Michael R.
• Granted Patent: US 8,299,943 B2
• Time in Patent Office: Days
• US Class Current: 341/22
• CPC Class Codes: G06F 3/0233 Character input methods
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: H04M 2250/70 methods for entering alphabetical characters, e.g. multi-tap or dictionary disambiguation methods for entering alphabetical characters per se G06F3/0237

Abstract

A computer receives user entry of a sequence of keypresses, representing an intended series of letters collectively spelling-out some or all of a desired textual object. Resolution of the intended series of letters and the desired textual object is ambiguous, however, because some or all of the key presses individually represent multiple letters. The computer interprets the keypresses utilizing concurrent, competing strategies, including one-keypress-per-letter and multi-tap interpretations. The computer displays a combined output of proposed interpretations and completions from both strategies.

Claims

1. A computer-implemented text entry method employing a display and a multi-key keypad, comprising operations of:

via the keypad, receiving user entry of a sequence of keypresses in an order, the sequence of keypresses representing an intended series of letters collectively spelling-out some or all of a desired textual object, where resolution of the intended series of letters and the desired textual object is ambiguous because some or all of the keypresses individually represent multiple letters;

after each new keypress, automatically and substantially concurrently preparing alternative interpretations of the sequence of keypresses according to multiple inconsistent keypress interpretation strategies, comprising;

employing a one-keypress-per-letter interpretation of keypress sequence to identify each entry in the vocabulary matching the keypress sequence, and each entry in the vocabulary with a stem matching the keypress sequence;

employing a multi-tap interpretation of keypress sequence to identify each entry in the vocabulary matching the keypress sequence, and each entry in the vocabulary with a stem matching the keypress sequence;

utilizing the display to provide a human-readable presentation including a selected combination of vocabulary entries identified by one-keypress-per-letter interpretation and vocabulary entries identified by multi-tap interpretation.

2. The method of claim 1, where the operation of preparing alternative interpretations is terminated upon identifying sufficient identified vocabulary entries to substantially occupy the display or a predetermined region of the display, and the operations further include after displaying the sufficient identified vocabulary entries reactivating the operation of preparing alternative interpretations in response to prescribed user input requesting to view further vocabulary entries.

3. The method of claim 1, the operation of utilizing the display comprising maintaining the presentation to include a greater number of vocabulary entries arising from the one-keypress-per-letter interpretation than a number of presented vocabulary entries arising from the multi-tap interpretation until vocabulary entries arising from the one-keypress-per-letter interpretation fall below a prescribed quantity.

4. The method of claim 1, where the operation of utilizing the display comprises varying relative numbers of presented vocabulary entries arising from the one-keypress-per-letter and multi-tap interpretations according to a user submitted ratio.

5. The method of claim 1, where the operation of utilizing the display comprises presenting the vocabulary entries identified by one-keypress-per-letter interpretation and multi-tap interpretations in separate panes, and further varying relative sizes of the panes according to a user submitted ratio.

6. The method of claim 5, further comprising, choosing a default word from the displayed vocabulary entries and displaying the chosen word at a displayed cursor position, where the choice of default word as between the one-keypress-per-letter and multi-tap interpretations is conducted in accordance with which of the one-keypress-per-letter and multi-tap interpretations is favored by the user submitted ratio.

7. The method of claim 1,

the operations further comprising monitoring at least one of the following in order to identify any user preference as between single-keypress-per-letter and multi-tap entry schemes:

user selection of presented vocabulary entries presented and which of the single-keypress-per-letter and multi-tap interpretations gave rise to the selection;

occurrence of repeated keypresses in the keypress sequence;

user submittal of predefined entries via the keypad or another data entry tool, where the predefined entries are specific to a particular one single-keypress-per-letter and multi-tap entry schemes;

cadence employed by the user while entering keypresses;

where the operation of utilizing the display further comprises automatically adjusting a relative proportion of vocabulary entries arising from the single-keypress-per-letter and multi-tap entry interpretation in response to said identifying of a user preference.

8. The method of claim 1, where the operation of utilizing the display comprises, in response to user submission of the keypresses having occurred within one or more predetermined application contexts, varying a display proportion as between presented entries arising from the multi-tap interpretations and presented entries arising from the single-keypress-per-letter interpretations.

9. The method of claim 1, where any or all of the employing operations and the operation of utilizing the display omits vocabulary entries under one or more of the following conditions:

number of the keypresses in the sequence is less than a predetermined number;

length of the vocabulary entry minus the number of keypresses in the sequence is less than a predetermined number.

10. The method of claim 1, where the letters are embodied by one or more of the following:

letters of one or more alphabets, symbols, punctuation marks, emoticons, numerals, elements of a script, components of a phonetic system.

11. The method of claim 1, further comprising utilizing the display to present a numerical interpretation of the sequence of keypresses.

12. The method of claim 1,where the operations further comprise making human readable presentation of a search prompt, and where the user entry of the sequence of keypresses occurs in response to the search prompt, and where the vocabulary comprises one or more bodies of search data, and where the operation of utilizing the display comprises displaying entries from the combined list in situ within the bodies of search data or excerpts from the bodies of search data.