Device and method incorporating an improved text input mechanism

• US 8,713,432 B2
• Filed: 06/10/2009
• Issued: 04/29/2014
• Est. Priority Date: 06/11/2008
• Status: Expired due to Fees

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Neuer Wall Treuhand GmbH
• Inventors: Assadollahi, Ramin O
• Primary Examiner(s): Patel, Manglesh M
• Application Number:
  US12/996,950
• Publication Number:
  US 20110197128A1
• Time in Patent Office: 1,784 Days
• Field of Search: 715/259, 715/257, 715/200
• US Class Current: 715/257
• CPC Class Codes: G06F 3/0237 using prediction or retrieval techniques
• CPC Class Codes: G06F 40/274 Converting codes to words; Guess-ahead of partial word inputs
• CPC Class Codes: H04M 2250/70 methods for entering alphabetical characters, e.g. multi-tap or dictionary disambiguation

Abstract

A device and method for its operation comprising a display and input device, a processor to receive character input maintain an input context of words and a dictionary comprising a plurality of word occurrence indicators for selection of candidate words that may follow context words. A word occurrence indicator is associated with a k_th order combination of a context word and a candidate word that indicates the frequency by which a respective candidate word follows the corresponding context word by k words in a text corpus. The processor is able to select a list of candidate words where the context word of at least one k_th order combination matches the kth last word of input context. A score is determined depending on an associated word occurrence indicator for at least one relevant k_th order combination.

Claims

1. An apparatus comprising at least one processor having a memory communicatively associated with said processor, the memory comprising computer executable instructions which, when executed by the processor, cause the apparatus to perform:

receiving character input from an input device;

maintaining an input context comprising K words directly preceding a desired input word, wherein K is greater than or equal to two;

providing a dictionary comprising a plurality of word occurrence indicators, wherein a word occurrence indicator is associated with a k_th order combination of a context word and a candidate word that indicates the frequency by which a respective candidate word follows the corresponding context word by k words in a text corpus without regard to any word in between the context word and the candidate word, wherein k takes on each of a value between 1 and K inclusively;

selecting a list of candidate words, wherein for each candidate word the context word of at least one k_th order combination matches the k^th last word of the input context;

determining a score depending on the at least one associated word occurrence indicator for the at least one relevant k_th order combination;

causing a number of candidate words from said list of candidate words having the highest score to be displayed on a display screen; and

prompting the user to select one of the displayed candidate words as the desired word or to enter at least one character for identifying the desired word using the input device.

2. The apparatus according to claim 1, wherein the score is determined as a combination of the matching word occurrence indicators.

3. The apparatus according to claim 1, wherein the input context comprises linguistic delimiters, such as sentence or punctuations marks.

4. The apparatus according to claim 1, wherein the dictionary is organized in K sub-dictionaries, wherein the k_th sub-dictionary comprises the k_th order combinations.

5. The apparatus according to claim 1, wherein the k_th order combinations are stored as pointers to a global word dictionary comprising the context and/or candidate words.

6. The apparatus according to claim 5, further comprising instructions that cause the apparatus to perform:

compiling a unigram dictionary comprising occurrence indicators associated to candidate words, indicating the frequencies of the respective candidate words in a text corpus.

7. The apparatus according to claim 6, wherein the unigram dictionary is the global dictionary.

8. The apparatus according to claim 1, wherein in response to the selection of the desired word, said processor is operable to update the input context by appending the desired word to the end of the input context and deleting the leading word;

select a new list of candidate words according to claim 1; and

cause the display to prompt the user to either select one of the displayed candidate words or to enter at least one character for identifying the desired word using the input device.

9. The apparatus according to claim 1, wherein in response to the entering of the at least one character for identifying the desired word using the input device, said processor is operable to cause only those candidate words from the list of candidate words to be displayed whose initial at least one character match the at least one character entered using the input device.

10. The apparatus according to claim 1, wherein the candidate words are displayed on the display screen in an order corresponding to their respective score.

11. The apparatus according to claim 1, wherein the score of a candidate word is determined by adding the occurrence indicators of matching k_th order combinations, each occurrence indicator being weighted by a weight multiplier.

12. The apparatus according to claim 11, wherein the weight multipliers are decreasing with increasing values of k.

13. The apparatus according to claim 1, wherein the occurrence indicators are normalized corresponding to the size of the text corpus.

14. The apparatus according to claim 1, wherein the occurrence indicators are represented by a logarithmic value.

15. The apparatus according to claim 1, wherein the processor is operable to cause the display screen to display only candidate words whose score exceeds a threshold value.

16. A method comprising:

maintaining an input context comprising K words directly preceding a desired word, wherein K is greater than or equal to two;

providing a dictionary comprising a plurality of word occurrence indicators, wherein a word occurrence indicator is associated with a k_th order combination of a context word and a candidate word that indicates the frequency by which a respective candidate word follows the corresponding context word by k words in a text corpus without regard to any word in between the context word and the candidate word, wherein k takes on each of a value between 1 and K inclusively;

selecting a list of candidate words, wherein for each candidate word the context word of at least one k^th order combination matches the k^th last word of the input context;

determining a score depending on the at least one associated word occurrence indicator for the at least one relevant k_th order combination;

causing a number of candidate words from said list of candidate words to be displayed on the display screen; and

prompting the user to select one of the displayed candidate words as the desired word or to enter at least one character for identifying the desired word.

17. The method of claim 16 further comprising:

the score is determined as a combination of the matching word occurrence indicators.

18. The method of claim 16 wherein:

the score of a candidate word is determined by adding the occurrence indicators of matching k_th order combinations, each occurrence indicator being weighted by a weight multiplier.

19. The method of claim 16 wherein:

the weight multipliers decrease with increasing values of k.

20. A computer program product comprising a non-transitory computer readable medium having stored therein computer executable instructions, said instructions when executed causing an apparatus to perform:

maintaining an input context comprising K words directly preceding a desired word, wherein K is greater than or equal to two;

providing a dictionary comprising a plurality of word occurrence indicators, wherein a word occurrence indicator is associated with a k_th order combination of a context word and a candidate word that indicates the frequency by which a respective candidate word follows the corresponding context word by k words in a text corpus without regard to any word in between the context word and the candidate word, wherein k takes on each of a value between 1 and K inclusively;

selecting a list of candidate words, wherein for each candidate word the context word of at least one k^th order combination matches the k^th last word of the input context;

determining a score depending on the at least one associated word occurrence indicator for the at least one relevant k_th order combination;

causing a number of candidate words from said list of candidate words to be displayed on the display screen; and

prompting the user to select one of the displayed candidate words as the desired word or to enter at least one character for identifying the desired word.