Component-based, adaptive stroke-order system

• US 20040239534A1
• Filed: 02/27/2004
• Published: 12/02/2004
• Est. Priority Date: 08/30/2001
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Tegic Communications, Inc. (Microsoft Corporation)
• Inventors: Chong Wong, Keng, Kushler, Clifford A., Longe, Michael R., Meurs, Pim Van
• Granted Patent: US 7,164,367 B2
• Time in Patent Office: Days
• US Class Current: 341/28
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06V 30/268 Lexical context
• CPC Class Codes: G06V 30/287 of Kanji, Hiragana or Katakana characters
• CPC Class Codes: G06V 30/387 using human interaction, e.g. selection of the best displayed recognition candidate

Abstract

An efficient and simple approach to encoding ideographic characters as sequences of input strokes or stroke categories is disclosed, wherein: each character is represented by one or more sequences of one or more components; each component corresponds to a plurality of alternative stroke sequences, each of which is associated with a probability that it will be the sequence which the user enters to specify the given component or character; and the probability associated with the user'"'"'s preferred stroke sequence is automatically increased by the system when the character is selected, thus automatically adapting to a user'"'"'s preferences.

Claims

1. A method of entering characters in an ideographic language, comprising the steps of:

maintaining a record for each one of one or more characters, which comprises one or more sequences of one or more components;

further maintaining a record for each of one or more components which comprises one or more sequences of entered strokes or stroke categories;

entering strokes or stroke categories;

comparing strokes or stroke categories and component sequences and matching one or more characters; and

optionally displaying one or more matched characters;

wherein each time a character is selected, input sequences for components that comprise said character are reprioritized.

2. The method of claim 1, further comprising the step of:

prioritizing characters that match a stroke entry sequence according to a linguistic model

3. The method of claim 2, where the linguistic model may include one or more of:

frequency of occurrence of a character in formal or conversational written text;

frequency of occurrence of a character when following a preceding character or characters;

proper or common grammar of the surrounding sentence;

application context of current character entry; and

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

4. The method of claim 1, further comprising the step of:

prioritizing a character according to the probability that a component with a matching stroke sequence occurs in said character at that point in an entered stroke sequence.

5. The method of claim 1, further comprising the step of:

prioritizing each alternate stroke sequence of a component according to the probability that said stroke sequence will be entered by the user to specify said component.

6. The method of claim 1, further comprising the step of:

for each component identified by matching all or a part of the stroke entry sequence with one of the stroke sequences associated with said component, using a priority associated with said stroke sequence to adjust the priority of the character or characters containing said component.

7. The method of claim 6, further comprising the step of:

once a character is selected, changing the associated priority of each matching stroke sequence of each component of said character, and optionally changing an associated priority of each non-matching stroke sequence of each component of said character.

8. The method of claim 1, further comprising the step of:

recording that a stroke entry sequence that a user enters for a particular component via a first selection mechanism is an appropriate stoke entry sequence for said component.

9. The method of claim 8, further comprising the step of:

either of creating a new association between a stroke entry sequence and a component, and creating a new association between a component sequence and a character.

10. The method of claim 9, wherein a desired component or character is specified through a second selection mechanism.

11. The method of claim 1, further comprising the step of:

displaying possible components, in addition to displaying one or more matched characters, wherein said components are optionally indicated with an underbar.

12. The method of claim 11, further comprising the step of:

showing only those characters that contain a component selected by a user.

13. The method of claim 1, wherein gestures are used for stroke entry.

14. The method of claim 13, further comprising the step of:

recognizing and mapping said gestures to predefined stroke categories.

15. The method of claim 13, further comprising the step of:

assigning a recognition score to each said gesture that is considered in a component-matching algorithm.

16. The method of claim 1, wherein an ideographic character description database is provided for describing the appearance of characters and component objects.

17. The method of claim 16, further comprising the step of:

defining a character set of components and component positions within a grid.

18. The method of claim 17, further comprising the step of:

defining a character as a set of components and component positions within a grid.

19. The method of claim 18, further comprising the step of:

creating a new association between a character, a set of components, and a set of component positions.

20. The method of claim 18, further comprising the step of:

allowing the user to select from one or more predefined grid arrangements to identify the kind of character.

21. The method of claim 18, further comprising the step of:

allowing the user to select the position of each component and the component for said position.

22. The method of claim 1, wherein input sequences identifying a multi-part component are represented by at least one of a set of linked records or by separate component records.

23. The method of claim 1, wherein an object is added to a memory if an object does not exist for an input sequence.

24. The method of claim 1, wherein one of the plurality of inputs is associated with a special wildcard input that is associated with any or all stroke or stroke category.

25. The method of claim 18, further comprising the step of:

displaying each displayable character as a set of objects positioned within a character grid.

26. The method of claim 1, wherein components are displayed as character interpretations of identified objects;

and wherein after a component is selected only characters containing said selected components are further displayed or reprioritized.

27. A system for selecting strokes to select characters in an ideographic language, comprising:

a user input device having a plurality of inputs, each of said plurality of inputs being associated with a plurality of user strokes that make up a character or its component parts, an input sequence being generated each time an input is selected by manipulating the user input device, wherein a generated sequence corresponds to a sequence of inputs that have been selected;

a memory containing a plurality of objects, comprising character objects that are ideographic characters and component objects that comprise components corresponding to the components of a character, each of the component objects being associated with one or more input sequences, wherein each of the one or more input sequences associated with a component object is optionally associated with a dynamic priority;

an output device to provide system output to the user; and

a processor coupled to the user input device, memory, and output device, the processor identifying from the plurality of objects contained in the memory any object associated with each generated input sequence, and optionally generating output signals causing the output device to provide the user any object or objects as character interpretations of the entered input sequence.

28. The system of claim 27, wherein order of said priorities is initially based on an appropriate linguistic model.

29. The system of claim 27, wherein an object having a highest priority is automatically selected.

30. An ideographic language text input system comprising:

a user input device comprising;

a plurality of inputs, each of the plurality of inputs associated with a stroke or stroke category, an input sequence being generated each time an input is selected by manipulating the user input device, wherein a generated input sequence corresponds to a sequence of inputs that have been selected; and

at least one selection input for generating an object output, wherein

a stoke input sequence is terminated when the user manipulates the user input device to a selection input;

a memory containing a plurality of objects, wherein each of the plurality of objects is associated with an input sequence;

a display to depict system output to the user; and

a processor coupled to the user input device, memory, and display, said processor comprising;

an identifying means for identifying form the plurality of objects in the memory any object associated with each generated input sequence;

an output means for displaying on the display the character interpretation of any identified objects associated with each generated input sequence; and

a selection means for selecting the desired character for entry into a text entry display location upon detecting the manipulation of the user input device to a selection input;

wherein each time a character is selected, input sequences for components that comprise said character are reprioritized.

31. The system of claim 30, wherein said selection means selects a desired character based upon identification of objects having a highest priority based on a linguistic model.

32. The system of claim 30, wherein input sequences identifying a multi-part component are represented by at least one of a set of linked records or by separate component records.

33. The system of claim 30, wherein an object is added to a memory if an object does not exist for an input sequence.

34. The system of claim 30, wherein one of the inputs is associated with a special wildcard input that is associated with any or all strokes or categories.

35. The system of claim 30, wherein an ideographic character description database is provided for describing the appearance of characters and component objects.

36. The system of claim 35, wherein each displayable character is represented as a set of objects positioned within a character grid.

37. The system of claim 30, wherein components are displayed as character interpretations of identified objects;

and wherein after a component is selected only characters containing said selected component are further displayed or reprioritized.