Multiple predictions in a reduced keyboard disambiguating system

• US 9,086,736 B2
• Filed: 02/18/2014
• Issued: 07/21/2015
• Est. Priority Date: 05/22/2007
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Longe, Michael R.
• Primary Examiner(s): Phan, Hai
• Assistant Examiner(s): BALSECA, FRANKLIN D
• Application Number:
  US14/183,451
• Publication Number:
  US 20140176351A1
• Time in Patent Office: 518 Days
• Field of Search: 341/20, 341/22, 345/168, 710/67, 710/73
• US Class Current: 1/1
• 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

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 method for text-entry interpretation, comprising:

receiving, via a keypad associated with a digital device, user entry of a sequence of keypresses representing a series of symbols indicative of a textual object intended by a user;

for each keypress received,

generating an interpretation of the sequence of keypresses by using multiple keypress interpretation strategies, the interpretation including at least one vocabulary entry predictive of a potential textual object intended by the user;

providing, via a display associated with the digital device, a human-readable presentation of the interpretation, the providing including changing a symbol associated with the at least one vocabulary entry based on a subsequent keypress received from the user subsequent to an initial presentation, wherein changing the symbol results in an updated human-readable presentation of the interpretation provided via the display, wherein providing the human-readable presentation further includes maintaining the human-readable presentation to include a greater number of vocabulary entries arising from a first keypress interpretation strategy than a number of vocabulary entries arising from a second keypress interpretation strategy until vocabulary entries arising from the first keypress interpretation strategy fall below a prescribed quantity.

2. The computer-implemented method of claim 1, wherein providing the human-readable presentation further includes:

varying a display proportion between associated vocabulary entries arising from the multiple keypress interpretation strategies.

3. The computer-implemented method of claim 1, wherein providing the human-readable presentation further includes:

varying relative numbers of vocabulary entries arising from the multiple keypress interpretation strategies to be presented according to a user submitted ratio.

4. The computer-implemented method of claim 1, wherein the multiple keypress interpretation strategies include a one-keypress-per-letter interpretation strategy and a multi-tap interpretation strategy.

5. The computer-implemented method of claim 1, further comprising identifying a user preference associated with a particular keypress interpretation strategy by monitoring at least one of:

a user selection of a displayed vocabulary entry and an associated keypress interpretation strategy that has identified the displayed vocabulary entry,

an occurrence of repeated keypresses in the sequence of keypresses;

a user submission of predefined entries, the predefined entries being specific to the particular keypress interpretation strategy, or

cadence employed by the user while entering keypresses.

6. The computer-implemented method of claim 5, wherein providing the human-readable presentation of the interpretation further comprises:

varying a display proportion between presented vocabulary entries arising from the multiple keypress interpretation strategies according to the user preference identified.

7. A method executed by a data processing system coupled to a digital device of a user, the method comprising:

receiving a sequence of keypresses indicative of a user-intended textual object;

for each keypress received,

generating a combination of vocabulary entries based on multiple keypress interpretation strategies, each vocabulary entry predictive of a potential user-intended textual object as interpreted by an associated keypress interpretation strategy, wherein the multiple keypress interpretation strategies include a one-keypress-per-letter interpretation strategy and a multi-tap interpretation strategy; and

presenting the combination of vocabulary entries, the presenting including updating at least one vocabulary entry of the combination of vocabulary entries based on any subsequent keypress received subsequent to an initial presentation of the combination, wherein the presenting further includes varying associated numbers of presented vocabulary entries arising from the one-keypress-per-letter interpretation strategy and the multi-tap interpretation strategy according to a user submitted ratio.

8. The method of claim 7, wherein the at least one vocabulary entry comprises a series of symbols indicative of the potential user-intended textual object, wherein updating the at least one vocabulary entry comprises changing a symbol of the series of symbols based on the subsequent keypress.

9. The method of claim 7, wherein the combination of vocabulary entries is selected from vocabulary entries arising from the multiple keypress interpretation strategies based on at least one of:

frequency, recency of use, or context.

10. The method of claim 7, where a particular vocabulary entry of the combination of vocabulary entries is omitted based on at least one of the following conditions:

a number of keypresses in the sequence of keypresses is less than a predetermined number, or

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

11. The method of claim 7, where the user-intended textual object comprises at least one of:

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

12. An apparatus comprising:

an input device to receive user inputs;

a display device to present outputs associated with the user inputs received;

a processor coupled to the input device and the display device; and

a memory coupled to the processor, the memory storing computer-executable instructions comprising;

instructions for receiving a sequence of keypresses via the input device;

instructions for, for each keypress received,

generating alternative interpretations of the sequence of keypresses according to a one-keypress-per-letter interpretation strategy and a multi-tap interpretation strategy, the alternative interpretations including associated vocabulary entries arising from the one-keypress-per-letter interpretation strategy and the multi-tap interpretation strategy; and

presenting a combination of vocabulary entries selected from the associated vocabulary entries via the display device, the instructions for presenting including;

instructions for updating at least one vocabulary entry of the combination of vocabulary entries based on a subsequent keypress received subsequent to an initial presentation of the combination; and

instructions for varying relative numbers of the associated vocabulary entries arising from the one-keypress-per-letter interpretation strategy and the multi-tap interpretation strategy according to a user submitted ratio.

13. The apparatus of claim 12, wherein each vocabulary entry comprises a series of symbols indicative of a potential user-intended textual object associated with the sequence of keypresses received, wherein the instructions for updating the at least one vocabulary entry comprises instructions for changing a symbol of the series of symbols based on the subsequent keypress.

14. The apparatus of claim 12, wherein the combination of vocabulary entries is selected based on at least one of:

frequency, recency of use, or context.

15. The apparatus of claim 12, wherein the user submitted ratio is submitted by adjustments made via a graphical user interface (GUI) slider associated with the display device.

16. The apparatus of claim 12, wherein the instructions further comprise:

instructions for presenting via the display device a search prompt that enables a user to submit a particular sequence of keypresses indicative of a search textual object;

instructions for generating a particular combination of vocabulary entries that correspond to the search textual object by using the one-keypress-per-letter interpretation strategy and the multi-tap interpretation strategy;

instructions for presenting a set of search results that include the particular combination of vocabulary entries, wherein the particular combination of vocabulary entries is presented in situ within the set of search results.