Self-learning method for keyword based human machine interaction and portable navigation device

• US 8,423,481 B2
• Filed: 10/06/2009
• Issued: 04/16/2013
• Est. Priority Date: 10/07/2008
• Status: Active Grant

• Current Assignee: MiTAC International Corporation (MiTAC Holdings Corp.)
• Original Assignee: MiTAC International Corporation (MiTAC Holdings Corp.)
• Inventors: Yang, Yin-pin, Chan, Ching-Chung, Lin, Xiao-Ming
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): Tran, Mai T
• Application Number:
  US12/574,394
• Publication Number:
  US 20100088254A1
• Time in Patent Office: 1,288 Days
• Field of Search: 706/11, 707/729, 704/9
• US Class Current: 706/11
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: H04L 9/0891 Revocation or update of secret information, e.g. encryption key update or rekeying
• CPC Class Codes: H04L 9/14 using a plurality of keys or algorithms

Abstract

A self-learning method for keyword based human machine interaction is disclosed. At least one of a plurality of keywords predetermined in a database is selected and a priority score of the selected keyword is updated and a weighted factor is generated for the selected keyword. A weighted score and the weighted factor of the selected keyword are transmitted to the keywords related to the selected keyword. The selected keyword is pushed to a keyword buffer and linkage strengths between the keywords in the keyword buffer are strengthened. When a keyword has been stored in the keyword buffer for over a predetermined reset time period, a reset operation is performed to remove the keyword from the keyword buffer.

Claims

1. A self-learning method for keyword based human machine interaction, comprising:

predetermining a set of keywords in a database of a portable navigation device;

performing an initialization operation to initialize the set of keywords;

sorting and displaying the set of keywords on a screen of the portable navigation device according to results of the initialization operation;

selecting at least one of the keywords;

assigning a weighted score to the selected keyword and performing a first calculation to refresh a priority score of the selected keyword;

generating a weighted factor for the selected keyword and transmitting the weighted score and the weighted factor of the selected keyword to the keywords related to the selected keyword;

refreshing, according to the weighted score and the weighted factor of the selected keyword, priority scores of the keywords related to the selected keyword and accordingly re-sorting all keywords;

displaying the keywords on the screen according to results of the re-sorting;

pushing the selected keyword to a keyword buffer of the portable navigation device;

performing a second calculation to strengthen linkage strengths between the keywords stored in the keyword buffer;

refreshing priority scores of all keywords according to the linkage strengths; and

performing a reset operation to remove the selected keyword out of the keyword buffer when the selected keyword stored in the keyword buffer has been stored over a predetermined time period.

2. The method as claimed in claim 1, wherein the keywords initially have no relationship or some relationship to each other and, for any pair of keywords having a relationship, there is a link representing the linkage strength therebetween.

3. The method as claimed in claim 1, wherein the higher the priority score is, the more frequent the corresponding keyword is used.

4. The method as claimed in claim 1, wherein the priority scores of the keywords are stored in a keyword table.

5. The method as claimed in claim 1, wherein the initialization operation comprises:

sorting the priority of the keywords according to the priority scores of the keywords and the linkage strengths between the keywords; and

setting the size and color of the keywords.

6. The method as claimed in claim 5, wherein the keywords having a relationship are displayed in similar colors.

7. The method as claimed in claim 1, wherein the priority score of the selected keyword is in positive correlation with the linkage strengths between the newly selected keywords and the weighted factor of the selected keyword.

8. The method as claimed in claim 1, wherein the linkage strengths between the newly selected keywords are in positive correlation with the priority score of the selected keyword.

9. The method as claimed in claim 1, wherein the step of keyword selection is implemented by speech recognition techniques or by user input via other interfaces.

10. The method as claimed in claim 1, wherein the keyword selection is triggered by an external event.

11. The method as claimed in claim 10, wherein the external event is a predetermined time period, weather condition, a position notification, a speed notification, or a navigation mode (for pedestrians or for cars) notification, or combinations thereof.

12. The method as claimed in claim 1, wherein the keyword selection is based on a detected result of a detector.

13. The method as claimed in claim 1, wherein the step of refreshing a priority score further comprises refreshing the linkage strengths between the keywords related to the selected keyword.

14. A portable navigation device, comprising:

a database, comprising a set of keywords and a keyword table, wherein the keyword table records priority scores of the keywords and linkage strengths between the keywords;

a speech recognition device, receiving voice commands;

a screen, displaying the keywords and receiving user input triggered by a stylus or user'"'"'s finger;

a keyword buffer, storing the keyword selected by the voice commands or the user input triggered by a stylus or user'"'"'s finger;

a microprocessor, performing an initialization operation to initialize the set of keywords, sorting priority of the set of keywords according to results of the initialization operation and displaying the set of keywords on the screen according to results of the sorting, selecting at least one of the keywords according to the voice commands or the user input triggered by a stylus or user'"'"'s finger, assigning a weighted score to the selected keyword, refreshing the keyword table wherein the priory score of the selected keyword is refreshed according to the weighted score of the selected keyword, generating a weighted factor for the selected keyword, transmitting the weighted score and the weighted factor of the selected keyword to the keywords related to the selected keyword, refreshing the priority scores of the keywords related to the selected keyword according to the weighted score and the weighted factor of the selected keyword and re-sorting the priority of the keywords accordingly, displaying the keywords on the screen according to results of the re-sorting, pushing the selected keyword to the keyword buffer, strengthening linkage strengths between the keywords stored in the keyword buffer and refreshing the priority scores of all keywords accordingly, and performing a reset operation to remove the selected keyword out of the keyword buffer while the selected keyword has been stored in the keyword buffer over a predetermined time period.

15. The portable navigation device as claimed in claim 14, wherein the keywords initially have no relationship or some relationship to each other, and for any pair of keywords having a relationship, there is a link representing the linkage strength therebetween.

16. The portable navigation device as claimed in claim 14, wherein the higher the priority score is, the more frequent the corresponding keyword is used.

17. The portable navigation device as claimed in claim 14, wherein when performing the initialization operation, the microprocessor sorts the priority of the keywords according to the priority scores of the keywords and the linkage strengths between the keywords, and sets the size and color of the keywords.

18. The portable navigation device as claimed in claim 17, wherein the keywords having a relationship are displayed in similar colors.

19. The portable navigation device as claimed in claim 14, wherein the priority score of the selected keyword is in positive correlation with the linkage strengths, between the newly selected keywords and the weighted factor of the selected keyword.

20. The portable navigation device as claimed in claim 14, wherein the linkage strengths between the newly selected keyword are in positive correlation with the priority score of the selected keyword.

21. The portable navigation device as claimed in claim 14, wherein the microprocessor selects at least one of the set of keywords based on the voice commands received by the speech recognition device or user input via other interfaces.

22. The portable navigation device as claimed in claim 14, wherein the microprocessor selects at least one of the set of keywords based on an external event.

23. The portable navigation device as claimed in claim 22, wherein the external event is a predetermined time period, weather condition, a position notification, a speed notification, or a navigation mode (for pedestrians or for cars) notification, or combinations thereof.

24. The portable navigation device as claimed in claim 14, wherein the microprocessor selects at least one of the set of keywords based on a detected result of a detector.

25. The portable navigation device as claimed in claim 14, wherein when refreshing the priority scores of the keywords, the microprocessor further refreshes linkage strengths between the keywords.