Reduced keyboard with prediction solutions when input is a partial sliding trajectory

• US 9,405,466 B2
• Filed: 12/22/2014
• Issued: 08/02/2016
• Est. Priority Date: 07/28/2010
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Suraqui, Daniel
• Primary Examiner(s): BAUTISTA, XIOMARA L
• Application Number:
  US14/579,501
• Publication Number:
  US 20150242119A1
• Time in Patent Office: 589 Days
• US Class Current: 1/1
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06F 3/04886 by partitioning the display area of the touch-screen or the surface of the digitising tablet into independently controllable areas, e.g. virtual keyboards or menus
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs

Abstract

A reduced virtual keyboard system for text input on electronic devices is disclosed. Text input is performed by creating a tracing trajectory. Dynamic prediction solutions are created during the tracing process, thus avoiding the need for a user to complete the entire word trajectory. The system also allows a mixture of tapping actions and sliding motions for the same word. The system may comprise a Long Words Dictionary database having first letters corresponding to predetermined keys of the keyboard. Alternatively, the system uses a Dictionary and a database management tool to find long words.

Claims

1. A method for predicting a full word solution corresponding to a partial trajectory pattern, comprising:

receiving a partial word trajectory pattern input by a user via a keyboard that has a plurality of virtual keys displayed on an electronic device, the partial word trajectory pattern resulting from movement of a pointing device by the user from one virtual key to other virtual keys on the displayed keyboard, while the pointing device is maintained in contact with the keyboard;

evaluating the partial word trajectory pattern to generate a partial word solution that comprises two or more letters of a longer word; and

utilizing the partial word solution to extract, from a dictionary that includes a set of words and respective frequencies of usage, a predicted full word solution having a highest frequency of use,

wherein the dictionary is derived from a dictionary database, stored in a memory of the electronic device, that includes a set of words and respective frequencies of usage, and

wherein the dictionary is smaller in size than the dictionary database, and includes words satisfying a minimum character threshold value.

2. The method of claim 1, wherein generating a partial word solution further comprises using a preceeding tapped entry of one or more virtual keys by the user to generate the partial word solution.

3. The method of claim 1, wherein the pointing device comprises a finger, a mouse, a remote control, or a pen.

4. The method of claim 1, wherein the dictionary includes words having a minimum character threshold value of eight characters, and is configured according to an arrangement of the plurality of virtual keys on the keyboard.

5. The method of claim 1, wherein the dictionary further comprises a length parameter reflecting a minimum length of each word in the dictionary and a frequency parameter reflecting a minimum frequency of use of each word in the dictionary.

6. The method of claim 5, wherein the dictionary is derived from the dictionary database by scanning the dictionary database and selecting all words having a length that is at least equal to the length parameter and a frequency of use that is greater than or equal to the frequency parameter associated with the dictionary.

7. The method of claim 1, wherein evaluating further comprises selecting the partial word solution from the dictionary using filters.

8. The method of claim 7, wherein the filters include:

a first filter that identifies partial word solution candidates from the dictionary based on candidate first characters corresponding to the partial word trajectory pattern, wherein the candidate first characters comprise the first character of the partial word trajectory pattern and at least one character neighboring the first character;

a second filter that eliminates partial word solution candidates that do not include as an intermediate character candidate last characters corresponding to the partial word trajectory pattern, wherein the candidate last characters comprise the last character of the partial word trajectory pattern and at least one character neighboring the last character; and

a third filter that eliminates partial word solution candidates that do not include as intermediate characters corresponding to inflection points of the partial word trajectory pattern.

9. The method of claim 8, wherein the last character of the partial word trajectory pattern is denoted by a long press by the user during input of the partial word trajectory pattern.

10. The method of claim 1, wherein the set of words in the dictionary are grouped in classes, each class including full words starting with the same character sorted according to an arrangement of characters on the keyboard.

11. An electronic device implementing a method for predicting a long word solution corresponding to a partial word trajectory pattern, comprising:

a memory storing computer-executable instructions; and

a processor for executing the computer-executable instructions stored in the memory, the computer-executable instructions including;

instructions for receiving an input via a virtual keypad on an electronic device, the input representing a partial word trajectory pattern, the partial word trajectory pattern resulting from movement of a pointing device by the user from one virtual key to other virtual keys on the displayed keyboard, while the pointing device is maintained in contact with the keyboard;

instructions for accessing a long word dictionary to generate a partial word solution corresponding to the partial word trajectory pattern, wherein the long word dictionary includes a subset of words derived from a dictionary database and that have a number of characters that meet or exceed a minimum character threshold value; and

instructions for utilizing the long word dictionary in conjunction with the partial word solution to generate a predicted long word solution.

12. The electronic device of claim 11, further comprising:

instructions for generating the long word dictionary from the dictionary database, wherein the long word dictionary comprises long words and respective frequencies of usage.

13. The electronic device of claim 12, wherein the instructions for generating the long word dictionary further comprises:

instructions for scanning the dictionary database to select long words having a number of characters at least equal to a length parameter and a frequency of usage greater than or equal to a frequency parameter.

14. The electronic device of claim 13, wherein a size of the long word dictionary is determined by at least the length and frequency parameters.

15. The electronic device of claim 12, wherein the long words in the long word dictionary are grouped in classes, each class including long words starting with the same character sorted according to an arrangement of characters on the virtual keypad.

16. The electronic device of claim 15, wherein the instructions for utilizing the long word dictionary in conjunction with the partial word solution to generate the predicted long word solution further comprises:

instructions for detecting long word solution candidates matching the partial word solution by scanning a class of the long word dictionary including a sorted list of long words that start with the same character as the partial word solution; and

instructions for selecting a long word from the long word solution candidates that has the highest frequency of usage as the predicted long word solution.

17. The electronic device of claim 16, further comprising:

instructions for detecting candidate first characters in the partial word trajectory pattern and scanning each class corresponding to the candidate first characters for partial word solution candidates, wherein the candidate first characters correspond to a key on the virtual keypad detected as being tapped or traced using a pointing device and one or more neighboring keys thereof.

18. The electronic device of claim 17, further comprising:

instructions for selecting the partial word solution from the partial word solution candidates by;

eliminating partial word solution candidates that do not include as an intermediate character candidate last characters of the partial word trajectory pattern; and

eliminating partial word solution candidates that do not include as intermediate characters inflection points in the partial word trajectory pattern.

19. A method for predicting a full word solution corresponding to a partial word trajectory pattern, comprising:

receiving text input from a virtual keyboard displayed on an electronic device, the text input corresponding to a partial word trajectory pattern created by moving a pointing device from one key to the next on the virtual keyboard;

generating from the partial word trajectory pattern a partial word solution; and

utilizing the partial word solution to extract, from a dictionary, associated with the virtual keyboard, which includes words having a number of characters that meet or exceed a minimum character threshold value and their associated frequencies of use, full word solutions and respective frequencies of usage;

selecting, from the full word solutions, a full word solution having the highest frequency of usage as a predicted full word solution.

20. The method of claim 19, wherein the dictionary is derived in real-time from a dictionary database that comprises words and respective frequencies of usage, and wherein the extracting is performed by issuing a command using a database management tool that includes SQLITE.