Personalized studying path generating method in serious game

• US 20110136093A1
• Filed: 12/07/2009
• Published: 06/09/2011
• Est. Priority Date: 12/07/2009
• Status: Active Grant

• Current Assignee: Foundation of Soongsil University-Industry Cooperation
• Original Assignee: Foundation of Soongsil University-Industry Cooperation
• Inventors: Park, Junhyoung, Kwun, Jinman, Sung, Bokyung, Ko, Ilju, Kim, Jungsoo
• Granted Patent: US 9,443,443 B2
• Time in Patent Office: Days
• US Class Current: 434/362
• CPC Class Codes: G09B 3/00 Manually or mechanically operated teaching appliances working with questions and answers electrically-operated G09B7/00; e.g. G09B7/063 advertising or displaying in general G09F
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F
• CPC Class Codes: G09B 7/06 of the multiple-choice answer-type, i.e. where a given question is provided with a series of answers and a choice has to be made from the answers

Abstract

The present invention relates to a personalized studying path generating method in a serious game. The personalized studying path generating method in the serious game according to the present invention comprises (a) generating serious criteria on a learning ability based on study elements required for the serious game and a relation between the study elements; (b) projecting user information and target information onto the serious criteria; (c) simplifying first criteria which the user information is projected onto and second criteria which the target information is projected onto by reducing a dimension of the first criteria and the second criteria; (d) comparing the simplified first and second criteria; (e) generating a personalized optimum studying path from the first to the second criteria; and (f) studying according to the optimum studying path. Accordingly, the present invention sets a personalized studying path by evaluating user'"'"'s learning ability according to a standard and enables a user to play the game according to his/her ability to thereby improve study efficiency. Also, the present invention may minimize difference of study efficiency arising from different study inclination and circumstances between individuals.

Claims

1. A personalized studying path generating method in a serious game, the method comprising:

(a) generating serious criteria on a learning ability based on study elements required for the serious game and a relation between the study elements;

(b) projecting user information and target information onto the serious criteria;

(c) simplifying first criteria which the user information is projected onto and second criteria which the target information is projected onto by reducing a dimension of the first criteria and the second criteria;

(d) comparing the simplified first criteria and the simplified second criteria;

(e) generating a personalized optimum studying path from the simplified first criteria to the simplified second criteria; and

(f) studying according to the personalized optimum studying path.

2. The method according to claim 1, wherein the studying method of the serious game further comprises (g) updating the user information based on the study result data if the study result data are out of a critical value, projecting the updated user information onto the serious criteria, and then updating the personalized optimum studying path by re-performing the operations (c) to (f).

3. The method according to claim 1, wherein the serious criteria are discrete measurement criteria of the learning ability and are generated as an eigenspace through a machine learning process after a standardization of the study elements.

4. The method according to claim 1, wherein the user information comprises user physical ability information and user environmental information.

5. The method according to claim 1, wherein the operation (c) comprises transforming the first criteria and the second criteria from high dimensions to low dimensions by using a dimensionality reduction algorithm such as a principal component analysis (PCA) or curvilinear component analysis (CCA).

6. The method according to claim 1, wherein the serious criteria are generated through the machine learning by unsupervised boosting after normalizing the study elements included in the serious game by field independent clustering.

7. The method according to claim 1, wherein the user information initially is based on information input by a user and information acquired from a test game and then updated according to user'"'"'s study history information.

8. The method according to claim 1, wherein the operation (d) comprises determining a location of a characteristic point focusing on a big difference point between the simplified first criteria and the simplified second criteria;

and

matching similarity points between the two criteria by measuring a volume and a direction of changed energy from the location of the characteristic point.

9. The method according to claim 8, wherein the operation (e) comprises generating an intermediate path by applying a shape transformation process between the simplified first criteria and the simplified second criteria based on the similarity points;

and

collecting a study data which are appropriate for each step of the intermediate path.

10. The method according to claim 8, wherein the operation (e) comprises generating the personalized optimum studying path at multi steps by searching an intermediate transformation process between the simplified first criteria and the simplified second criteria based on the similarity points.

11. A personalized studying path generating method in a serious game, the method comprising:

(a) generating serious criteria on a learning ability based on study elements required for the serious game and a relation between the study elements;

(b) generating target criteria by projecting target information on target learning ability onto the serious criteria;

(c) generating user criteria by projecting user information onto the serious criteria;

(d) simplifying the target criteria and the user criteria to generate a target map and a user map;

(e) comparing the target map and the user map;

(f) generating a personalized optimum studying path from the user map to the target map; and

(g) studying according to the personalized optimum studying path.

12. The method according to claim 11, wherein the studying method of the serious game further comprises (h) updating the user information based on the study result data if the study result data are out of a critical value, projecting the updated user information onto the serious criteria, and then updating the optimum studying path by re-performing the operations (c) to (f).

13. The method according to claim 11, wherein the serious criteria are discrete measurement criteria of the learning ability and are generated as an eigenspace through a machine learning process after a standardization of the study elements.

14. The method according to claim 11, wherein the user information comprises user physical ability information and user environmental information.

15. The method according to claim 11, wherein the operation (d) comprises transforming the user criteria and the target criteria from high dimensions to low dimensions by using a dimensionality reduction algorithm such as a principal component analysis (PCA) or curvilinear component analysis (CCA).

16. The method according to claim 11, wherein the serious criteria are generated through the machine learning by unsupervised boosting after normalizing the study elements included in the serious game by field independent clustering.

17. The method according to claim 11, wherein the user information initially is based on information input by a user and information acquired from a test game and then updated according to user'"'"'s study history information.

18. The method according to claim 11, wherein the operation (e) comprises determining a location of a characteristic point focusing on a big difference point between the user map and the target map;

and

matching similarity points between the two criteria by measuring a volume and a direction of changed energy from the location of the characteristic point.

19. The method according to claim 18, wherein the operation (f) comprises generating an intermediate path by applying a shape transformation process between the user map and the target map based on the similarity points, and

collecting a study data which are appropriate for each step of the intermediate path.

20. The method according to claim 18, wherein the operation (f) comprises generating the optimum studying path at multi steps by searching an intermediate transformation process between the user map and the target map based on the similarity points.