Text/character input system, such as for use with touch screens on mobile phones

• US 9,026,428 B2
• Filed: 10/15/2012
• Issued: 05/05/2015
• Est. Priority Date: 10/15/2012
• Status: Active Grant

• Current Assignee: Cerence Operating Company (Cerence Inc.)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Sternby, Jakob, Morwing, Lars Jonas, Andersson, Jonas, Friberg, Christer
• Primary Examiner(s): SPOONER, LAMONT M
• Application Number:
  US13/652,222
• Publication Number:
  US 20140108004A1
• Time in Patent Office: 932 Days
• Field of Search: 704/1, 704/9, 704/10, 707706-708, 382/186, 382/187
• US Class Current: 704/9
• CPC Class Codes: G06F 3/018 Input/output arrangements for oriental characters
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 3/04883 for inputting data by handwriting, e.g. gesture or text
• CPC Class Codes: G06F 40/171 by use of digital ink
• CPC Class Codes: G06F 40/30 Semantic analysis

Abstract

A system and method for receiving character input from a user includes a programmed processor that receives inputs from the user and disambiguates the inputs to present character sequence choices corresponding to the input characters. In one embodiment, a first character input is received and a corresponding first recognized character is stored in a temporary storage buffer and displayed to the user for editing. After a predetermined number of subsequent input characters and/or predetermined amount of time without being edited, the system determines that the first recognized character is the intended character input by the user and removes the first recognized character from the buffer, thereby inhibiting future editing.

Claims

1. A method for data input on a touchscreen of a mobile device, the method comprising:

receiving a first user input,

wherein the first user input is handwritten input received on the touchscreen of the mobile device;

determining a first recognized sequence based on the first user input;

wherein the first recognized sequence is a best match of the first user input;

writing the first recognized sequence to a memory storage buffer of the mobile device;

generating a first candidate sequence,

wherein the first candidate sequence is a best match of one or more recognized sequences;

presenting the first candidate sequence to the user,

wherein the presenting includes displaying the first candidate sequence to the user and allowing the user to edit the first candidate sequence;

identifying at least a first sequence portion of the first candidate sequence

wherein the identifying is at least partially based on one or more rules or dictionaries of words accessible to the mobile device;

removing the first sequence portion from the memory storage buffer,

wherein the removing is performed in the absence of receiving user input editing the first candidate sequence, representing a space character, or selecting a word; and

sending the first sequence portion to an application running on the mobile device.

2. The method of claim 1, further comprising:

receiving at least a second user input;

determining a second recognized sequence based on the second user input; and

revising the first candidate sequence, wherein the revised first candidate sequence is based on the first recognized sequence and the second recognized sequence.

3. The method of claim 1, further comprising:

determining at least a second candidate sequence based on the first user input; and

presenting at least the second candidate sequence to the user.

4. The method of claim 1 wherein the identifying is based on linguistic properties of the first user input and the first candidate sequence, and a probability of future editing of the first sequence portion by the user.

5. The method of claim 4, wherein the removing is performed when the probability is less than a predetermined amount.

6. The method of claim 1, wherein the first sequence portion is removed from the memory storage buffer a predetermined time after second user input is received.

7. The method of claim 1, wherein the dictionaries of words include words in Chinese, Japanese, or Korean languages.

8. The method of claim 1, wherein the first user input includes at least one of a Chinese character, a Japanese character, or a Korean character.

9. At least one non-transitory computer-readable storage medium storing instructions for data input, wherein the data input is performed at a wireless device having a processor and a memory, comprising:

receiving a first user input and at least a second user input;

wherein the first and second user input are handwritten input received on a handwriting input area of the wireless device;

determining a first sequence based on a best match of the first and second user inputs,

wherein the first sequence includes at least the first input;

storing the first sequence to a memory of the mobile device;

automatically determining that at least a portion of the sequence matches a word or phrase in a database of acceptable words and/or phrases without the user inputting a space or selecting a word; and

sending the first sequence to an application or service running on, or accessible by, the wireless device,

wherein the sending comprises removing the first sequence from the memory storage buffer, and

wherein the sending is performed in the absence of user editing of the first sequence.

10. The computer readable medium of claim 9, further comprising:

determining at least a second sequence based on the first user input and the second user input;

presenting the second sequence to the user.

11. The computer readable medium of claim 9, wherein the first sequence is sent to the application or service a predetermined time after the first user input is received in the absence of user editing of the first sequence.

12. The computer readable medium of claim 9, further comprising:

presenting the first sequence to the user,

wherein the presenting includes displaying the first sequence to the user and allowing the user to edit the first sequence.

13. The computer readable medium of claim 9, wherein the first user input and the second user input include at least one of a Chinese character, a Japanese character, or a Korean character.

14. A data processing apparatus, comprising:

at least one processor;

at least one memory coupled to the processor;

data input and data output components coupled to the processor,

wherein the data output component includes a visual display device; and

wherein the data input component includes at least an area for receiving hand written character input;

wherein the data processing apparatus is configured to;

receive first character data representing a first handwritten character input to the data input component;

determine a likely first displayable character associated with the first character data;

store the likely first character data in the memory;

receive second character data representing a second handwritten character input to the data input component;

determine a likely second displayable character associated with the second character data;

store the likely second character data in the memory;

receive third character data representing a third handwritten character input to the data input component;

determine a likely third displayable character associated with the third character data;

store the likely third character data in the memory;

determine a final value for at least the likely first character based on the likely first, likely second and likely third character data stored in the memory,

wherein determining the final value is performed without the user inputting a space gesture or selecting a button to accept the likely first character, and

wherein determining the final value is performed by comparing the likely first, second and third characters to a linguistic database; and

,

remove the likely first data character from the memory after determining the final value for at least the first character.

15. The apparatus of claim 14, wherein the input and output components are a touch-sensitive display,

wherein the first character data is received on a select area of the touch-sensitive display, and

wherein the second and third character data are sequentially received on the same area of the touch-sensitive display.

16. The apparatus of claim 14, wherein the likely first, second and third characters are Asian characters, and wherein the likely first character can be edited until it is removed from the memory.

17. The apparatus of claim 14, wherein the likely first and second characters are displayed on the display component before receiving the third character data, and wherein the determining comprises determining whether the received third character data represents punctuation.

18. The apparatus of claim 14, wherein the memory stores first and second words for comparison with the linguistic database, and wherein a determined final first word is removed from the memory when the first and second words acceptably match a phrase in the linguistic database.

19. The apparatus of claim 14, further comprising a recognition engine, wherein the recognition engine and the linguistic database are stored in the memory, and wherein the recognition engine is a software module configured to perform at least the determining of a likely displayable character based on a received handwritten character.

20. The apparatus of claim 14, further comprising:

a portable power source;

a wireless transceiver; and

a touch-sensitive display.