METHOD OF LEARNING A CONTEXT OF A SEGMENT OF TEXT, AND ASSOCIATED HANDHELD ELECTRONIC DEVICE

• US 20080002885A1
• Filed: 06/30/2006
• Published: 01/03/2008
• Est. Priority Date: 06/30/2006
• Status: Active Grant

• Current Assignee: Malikie Innovations Limited (Key Patent Innovations Limited)
• Original Assignee: Blackberry Limited
• Inventors: Fux, Vadim, Kolomiets, Sergey
• Granted Patent: US 8,395,586 B2
• Time in Patent Office: Days
• US Class Current: 382/187
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 40/166 Editing, e.g. inserting or deleting
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/022 Knowledge engineering; Knowledge acquisition
• CPC Class Codes: G06V 30/10 Character recognition
• CPC Class Codes: G06V 30/246 using linguistic properties, e.g. specific for English or German language
• CPC Class Codes: G06V 30/262 using context analysis, e.g. lexical, syntactic or semantic context

Abstract

An improved method of learning a context of a segment of text input enables facilitated text input on an improved handheld electronic device. In response to a series of inputs, segments and other objects are analyzed to generate a proposed character interpretation of the series of inputs. Responsive to detecting a replacement of a segment of the character interpretation with another segment, a combination object comprising the another segment and a preceding object is stored. In response to another series of inputs, the combination object can be employed by a processing algorithm to ascertain a preference for the another segment in the context of the preceding object of the combination object.

Claims

1. A method of enabling input on a handheld electronic device comprising a memory having stored therein a plurality of characters, a plurality of segments, and a number of combination objects, each segment comprising a plurality of the characters, each combination object comprising at least a representation of a segment and at least a representation of one of a character and a segment, the method comprising:

receiving a sequence of inputs, at least some of the inputs each having a number of the characters corresponding therewith, for at least some of the inputs the number of characters comprising a plurality of the characters;

outputting a character interpretation of at least some of the inputs of the sequence, the character interpretation comprising, for each said input, a character that corresponds with the input;

detecting as an editing input a replacement of at least a portion of the character interpretation with a number of replacement characters that correspond with the inputs of the at least portion of the character interpretation, the number of replacement characters comprising at least one character different than the at least portion of the character interpretation; and

storing as a combination object;

at least a representation of the replacement characters, and

at least a representation of one of a character and a segment of the character interpretation other than the replacement characters.

2. The method of claim 1, further comprising storing as the combination object:

the at least representation of the replacement characters, and

at least a representation of one of a character and a segment of the character interpretation that precedes the replacement characters.

3. The method of claim 1, further comprising consulting at least some of the number of combination objects to determine whether or not a preference exists for at least one character in the context of at least one other character and, responsive thereto, generating the character interpretation.

4. The method of claim 1, further comprising storing as at least a portion of the combination object at least a representation of a segment.

5. The method of claim 1, further comprising storing as the at least a representation of the replacement characters at least a representation of a learned segment that comprises a plurality of characters.

6. The method of claim 5, further comprising storing the at least a representation of one of a character and a segment of the character interpretation other than the replacement characters as contextual data for the at least a representation of a learned segment.

7. The method of claim 1, further comprising, responsive to said detecting, initiating said storing.

8. A handheld electronic device comprising an input apparatus, a processor apparatus, and an output apparatus, the processor apparatus comprising a processor and a memory having stored therein a plurality of objects comprising a plurality of characters, a plurality of segments, and a number of combination objects, each segment comprising a plurality of the characters, each combination object comprising at least a representation of a segment and at least a representation of one of a character and a segment, the memory having stored therein a number of routines which, when executed by the processor, cause the handheld electronic device to be adapted to perform operations comprising:

receiving a sequence of inputs, at least some of the inputs each having a number of the characters corresponding therewith, for at least some of the inputs the number of characters comprising a plurality of the characters;

outputting a character interpretation of at least some of the inputs of the sequence, the character interpretation comprising, for each said input, a character that corresponds with the input;

detecting as an editing input a replacement of at least a portion of the character interpretation with a number of replacement characters that correspond with the inputs of the at least portion of the character interpretation, the number of replacement characters comprising at least one character different than the at least portion of the character interpretation; and

storing as a combination object;

at least a representation of the replacement characters, and

at least a representation of one of a character and a segment of the character interpretation other than the replacement characters.

9. The handheld electronic device of claim 8 wherein the operations further comprise storing as the combination object:

the at least representation of the replacement characters, and

at least a representation of one of a character and a segment of the character interpretation that precedes the replacement characters.

10. The handheld electronic device of claim 8 wherein the operations further comprise consulting at least some of the number of combination objects to determine whether or not a preference exists for at least one character in the context of at least one other character and, responsive thereto, generating the character interpretation.

11. The handheld electronic device of claim 8 wherein the operations further comprise storing as at least a portion of the combination object at least a representation of a segment.

12. The handheld electronic device of claim 8 wherein the operations further comprise storing as the at least a representation of the replacement characters at least a representation of a learned segment that comprises a plurality of characters.

13. The handheld electronic device of claim 12 wherein the operations further comprise storing the at least a representation of one of a character and a segment of the character interpretation other than the replacement characters as contextual data for the at least a representation of a learned segment.

14. The handheld electronic device of claim 8 wherein the operations further comprise, responsive to said detecting, initiating said storing.