Directional Input System with Automatic Correction

• US 20080126073A1
• Filed: 10/12/2007
• Published: 05/29/2008
• Est. Priority Date: 05/26/2000
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Longe, Michael R., Palmer, Brian, Hullfish, Keith Charles, Brams, Doug
• Granted Patent: US 8,976,115 B2
• Time in Patent Office: Days
• US Class Current: 704/1
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 3/02 Input arrangements using manually operated switches, e.g. using keyboards or dials
• 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 3/0354 with detection of 2D relative movements between the device, or an operating part thereof, and a plane or surface, e.g. 2D mice, trackballs, pens or pucks
• CPC Class Codes: G06F 3/0482 Interaction with lists of selectable items, e.g. menus
• 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 3/04897 Special input arrangements or commands for improving display capability
• CPC Class Codes: G06F 40/232 Orthographic correction, e.g. spell checking or vowelisation
• CPC Class Codes: G06F 40/253 Grammatical analysis; Style critique
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: G06V 30/1423 the instrument generating sequences of position coordinates corresponding to handwriting preprocessing or recognising digital ink G06V30/32

Abstract

A system associated with a text entry application, such as email or instant messaging, comprises an optional onscreen representation of a circular keyboard, a list of potential linguistic object matches, and a message area where the selected words are entered. The circular keyboard is manipulated via a hardware joystick or game-pad with analog joystick or omni-directional rocker switch built therein. The user points the joystick in the general direction of the desired letter, and then continues pointing roughly to each letter in the desired word. Once all letters have been roughly selected, buttons are used to select a specific word from the list of potential matches and send the selected word to the message area.

Claims

1. A text entry system, comprising:

a direction selector to individually point in a direction of letters to collectively form an intended linguistic object, where each letter comprises a linguistic object subcomponent;

a collection of linguistic objects;

an output device with a text display area;

a processor, comprising;

a difference calculation module configured to output, for each act of pointing, various letters based upon factors including at least the difference between an actual direction indicated by the directional selector and pre-assigned directions of said letters;

an object search engine configured to identify at least one linguistic object based on the output letters; and

a selection component to facilitate user selection of a desired linguistic object.

2. The system of claim 1, further comprising an on-screen keyboard representation of an array of letters in each writing system.

3. The system of claim 2, wherein said on-screen keyboard is of any shape selected from a group comprising circle, square, oval, and polygon.

4. The system of claim 1, wherein each of said output letters comprises any subcomponent or combination of one or more of the following forming an incomplete part of one of the linguistic objects:

an alphabetic letter, accented letter, numeric digit, punctuation symbol;

a sub-word component from a non-alphabetic language including one or more strokes, radicals, jamos, kana.

5. The system of claim 1, where said linguistic model includes one or more of:

frequency of occurrence of a linguistic object in formal or conversational written text;

frequency of occurrence of a linguistic object when following a preceding linguistic object or linguistic objects;

proper or common grammar of the surrounding sentence;

application context of current linguistic object entry; and

recency of use or repeated use of the linguistic object by the user or within an application program.

6. The system of claim 1, wherein identified linguistic objects are ordered by a combination value of a calculated weighted difference value and a linguistic model, wherein said linguistic model comprises one or more of:

frequency of occurrence of a linguistic object in formal or conversational written text;

frequency of occurrence of a linguistic object when following a preceding linguistic object or linguistic objects;

proper or common grammar of the surrounding sentence;

application context of current linguistic object entry; and

recency of use or repeated use of the linguistic object by the user or within an application program.

7. The system of claim 1, further comprising a means for extending a selected linguistic object with completions.

8. The system of claim 1, further comprising a means for precisely selecting said letters of said linguistic object wherein said means for precisely selecting detects, during an act of pointing, the amount that a direction of a selector is above a threshold distance, degree of tilt, or period of time.

9. The system of claim 8, wherein either an exact spelling sequence is displayed in said text display area, or the last entered letter is indicated in an exact spelling sequence, or the last entered letter is indicated in said on-screen keyboard.

10. The method of claim 1, further comprising a smart symbol, said smart symbol when indicated is automatically interpreted as a punctuation symbol, diacritic mark or tonal indication at the place in the input sequence where a matching punctuation symbol, diacritic mark or tonal indication occurs in identified linguistic objects.

11. A text input method using a directional input device, wherein each direction entered corresponds, directly or indirectly, to one or more linguistic object subcomponents according to a current mapping, said method comprising the steps of:

for each user act of pointing the directional input device, preparing an output of candidate linguistic object subcomponents based upon factors including at least the difference between directions indicated by the directional input device and pre-assigned directions of said linguistic object subcomponents according to the current mapping;

using the output to predict at least one linguistic object;

facilitating user selection of a desired linguistic object.

12. The method of claim 11, wherein the candidate linguistic object subcomponents can be one of any number of letters or symbols near the direction entered.

13. The method of claim 12, further comprising utilizing a linguistic model to order said predicted linguistic objects according to likelihood of intended selection by the user wherein the order of said predicted linguistic objects is based either on a combination of weightings and the linguistic model, or the linguistic model comprises one or more of:

frequency of occurrence of a linguistic object in formal or conversational written text;

frequency of occurrence of a linguistic object when following a preceding linguistic object or linguistic objects;

proper or common grammar of the surrounding sentence;

application context of current linguistic object entry; and

recency of use or repeated use of the linguistic object by the user or within an application program.

14. The method of claim 11, wherein said directional input device is associated with an on-screen keyboard.

15. The method of claim 11, wherein the user selects a partial linguistic object and continues with more directional inputs, and wherein said predicted linguistic objects includes only linguistic objects that begin with said selected partial linguistic object.

16. The method of claim 11, wherein a set of buttons or a second directional input device can be used alone or with said directional input device, separately or simultaneously, to switch or choose input modes, to change from input to linguistic object selection, or to invoke other functions.

17. The method of claim 11, further comprising the steps of:

in response to a user invoking an undo means after selecting a linguistic object,

facilitating user selection of an alternate linguistic object.

18. The method of claim 11, wherein linguistic object subcomponents presented on said on-screen keyboard are limited to, or highlighted as, the linguistic object subcomponents in certain positions, in a collection of linguistic objects.

19. A computer readable storage medium tangibly embodying a program of instructions executable by a digital data processing machine to perform text input operations comprising the steps of:

receiving machine-readable signals representing a series of user-submitted directional inputs entered via a directional input tool, the series having an order;

where directional inputs of the directional input tool correspond to different linguistic object subcomponents according to a current mapping;

for each user-submitted directional input, based upon that directional input alone, estimating multiple corresponding subcomponents that the user might have intended by such directional input;

assembling the different ones of the estimated subcomponents to construct multiple different proposed linguistic objects that the user might have intended by the series of directional inputs, where each proposed object includes one estimated subcomponent for each user-submitted directional input, the subcomponents occurring in the proposed object in the same order as the series of user-submitted directional inputs;

facilitating selection of a desired one of the proposed objects.

20. The medium of claim 19, where each linguistic object subcomponent comprises at least one of the following:

an alphabetic letter, accented letter, numeric digit, punctuation symbol;

a sub-word component from a non-alphabetic language including one or more strokes, radicals, jamos, kana;

a subcomponent or combination of one or more of the foregoing.

21. The medium of claim 19, where the assembling operation further comprises ordering the proposed linguistic objects according to one or more of the following:

word length, ordinal ranking, weighting value of proposed linguistic object subcomponents, frequency of general usage, recency of use, appearance in a user-defined list.

22. A text input system, comprising:

a direction selector operable in a coordinate system to point in an approximate direction toward one or more linguistic object subcomponents;

a predetermined or dynamic mapping between directions and linguistic object subcomponents;

a collection of linguistic objects;

an output device with a text display area;

a processor, comprising an object evaluation component configured to identify at least one linguistic object based on a sequence of approximate directions; and

a selection component to facilitate user selection of a desired linguistic object wherein said object evaluation component matches said sequence of approximate directions against said sequences of directional values associated with each linguistic object and identifies at least one linguistic object whose associated directional values minimize the differences with said sequence of approximate directions.

23. The system of claim 22, wherein said identification of at least one linguistic object is further based on a linguistic model wherein the linguistic model comprises one or more of:

frequency of occurrence of a linguistic object in formal or conversational written text;

frequency of occurrence of a linguistic object when following a preceding linguistic object or linguistic objects;

proper or common grammar of the surrounding sentence;

application context of current linguistic object entry; and

recency of use or repeated use of the linguistic object by the user or within an application program.

24. The system of claim 22, wherein at least one of the mapped directions corresponds to a plurality of linguistic object subcomponents, one or a plurality of which include a diacritic mark, wherein the plurality of linguistic object subcomponents comprise variant forms of a single base linguistic object subcomponent, and wherein said collection of linguistic objects include linguistic object subcomponents with diacritic marks.

25. The system of claim 22, wherein said direction selector comprises any of:

an omni-directional joystick or sliding switch, a radial gesture with a mouse, a data glove or, on a touch-sensitive surface, a touch-sensitive ring, a wheel, an accelerometer-based tilt device, or an eye-tracking device wherein selection of a direction using a ring or wheel is determined by detecting a difference in speed of selection, a threshold time delay within a range of direction, or a change in acceleration, and wherein selection of a direction using an accelerometer-based tilt device is determined by detecting a change in acceleration or by a confirming button press.