METHOD FOR INPUTTING AND IDENTIFYING A CHARACTER STRING

• US 20150324011A1
• Filed: 12/03/2013
• Published: 11/12/2015
• Est. Priority Date: 12/28/2012
• Status: Active Grant

• Current Assignee: Volkswagen AG
• Original Assignee: Volkswagen AG
• Inventors: CZELNIK, Mark Peter, BENDEWALD, Lennart, WALLER, Christoph
• Granted Patent: US 9,703,393 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• 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 3/04886 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

Abstract

A method for inputting and identifying a character string, in which several successively inputted user inputs for forming the character string are identified and a confidence analysis is carried out, in which each user input is compared to a number of characters and each of the compared characters is allocated a value of a confidence measure which evaluates the correlation of the user input to the characters. Character combinations are formed from the characters associated with the user inputs. Global confidence measures are determined for the character combinations from the confidence measures associated with the characters. Finally, a partial amount of the character combinations is emitted in accordance with the global confidence measures. Also disclosed is a device for carrying out the method and a vehicle having the disclosed device.

Claims

1. A method for inputting and identifying a character string, the method comprising:

detecting multiple user inputs which are input in succession to form a character string;

carrying out a confidence analysis, in which each user input is compared with multiple characters stored in a database, and assigning a value of a confidence measure to relevant characters which assesses the correspondence of the user input to these relevant characters;

forming character combinations from the characters assigned to the user inputs, wherein overall confidence measures for the character combinations are ascertained from the confidence measures assigned to the relevant characters; and

outputting a subset of the character combinations as a function of the overall confidence measures.

2. The method of claim 1, wherein

only those character combinations are output whose overall confidence measures lie above a certain threshold value.

3. The method of claim 2, wherein the threshold value is selected as a function of the number of multiple user inputs.

4. The method of claim 1,

wherein the overall confidence measures of the character combinations are ascertained by multiplication of the confidence measures assigned to the relevant characters.

5. The method of claim 1,

wherein the overall confidence measures of the character combinations are ascertained by averaging over the confidence measures assigned to the relevant characters.

6. The method of claim 1, further comprising:

arranging the subset of the character combinations in descending order according to the level of the overall confidence measures; and

outputting the character combination having the highest overall confidence measure is output first.

7. The method of claim 6, wherein

the subset of the character combinations is compared with database entries;

and

if no database entry is present for the character combination having the highest overall confidence measure, this character combination is not output, and the character combination having the next-highest overall confidence measure, for which a database entry is present, is output first.

8. The method of claim 1, wherein

the input characters are detected by handwriting detection, speech detection, or keyboard input detection.

9. A device for inputting and identifying a character string, the device comprising:

an input device for inputting and detecting user inputs;

a control device for carrying out a confidence analysis, wherein comparisons are carried out between user inputs with multiple characters stored in a database;

wherein a value of a confidence measure is assigned to relevant characters which assesses the correspondence of the user input to these relevant characters, wherein the control device forms character combinations from the relevant characters;

a computing device by which overall confidence measures for the character combinations are ascertained from the confidence measures assigned to the relevant characters; and

an output device, by which a subset of the character combinations are output as a function of the overall confidence measures.

10. A vehicle including a device for inputting and identifying a character string, the device including:

an input device for inputting and detecting user inputs;

a control device for carrying out a confidence analysis, wherein comparisons are carried out between user inputs with multiple characters stored in a database, wherein a value of a confidence measure is assigned to relevant characters which assesses the correspondence of the user input to these relevant characters, wherein the control device forms character combinations from the relevant characters;

a computing device by which overall confidence measures for the character combinations are ascertained from the confidence measures assigned to the relevant characters; and

an output device, by which a subset of the character combinations are output as a function of the overall confidence measures.