Situation-aware recommendation using correlation

• US 8,171,035 B2
• Filed: 06/11/2008
• Issued: 05/01/2012
• Est. Priority Date: 10/22/2007
• Status: Active Grant

• Current Assignee: Huawei Technologies Co., Ltd. (Huawei Investment & Holding Co., Ltd.)
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Song, Yu, Jeong, Sangoh, Cheng, Doreen, Kalasapur, Swaroop
• Primary Examiner(s): Casanova, Jorge A
• Application Number:
  US12/137,417
• Publication Number:
  US 20090106314A1
• Time in Patent Office: 1,420 Days
• Field of Search: 707/737, 707/739, 707/751
• US Class Current: 707/751
• CPC Class Codes: G06F 18/2321 using statistics or function optimisation, e.g. modelling of probability density functions
• CPC Class Codes: G06F 18/24137 Distances to cluster centroïds

Abstract

In one embodiment, data relating to usage patterns of the user is stored, wherein the data includes information as to items which were used and the context in which they were used. A correlation table is constructed. Correlation values between each item and each context are then stored in then correlation table, wherein the correlations are used to recommend one or more of the items.

Claims

1. A method for making recommendations to a user, the method comprising:

storing data relating to usage patterns of the user, wherein the data includes information as to items which were used and the context in which they were used, wherein context includes a situation in which the user and device were operating when the items were used;

constructing a correlation table, wherein each axis of the correlation table has both items that can be recommended and contexts, both extracted from the usage patterns and wherein the constructing is performed without performing clustering of usage patterns;

determining a probability that an item in the correlation table will be useful to a user given a particular context; and

storing a correlation value between each item and each context in the correlation table, wherein the correlations are used to recommend one or more of the items.

2. The method of claim 1, wherein the correlation values are relationships between items and contexts.

3. The method of claim 1, wherein the items comprise software applications, computing services, or data.

4. The method of claim 1, wherein the correlation table contains each of the one or more items and each of the contexts described by data points on each of the correlation table'"'"'s axes.

5. The method of claim 1, wherein the computing includes using Pearson'"'"'s correlation.

6. The method of claim 1, wherein the computing includes using cosine-based correlation.

7. The method of claim 1, further comprising recomputing one or more of the correlation values to capture real values in a usage log.

8. An apparatus comprising:

an interface; and

one or more processors configured to;

store data relating to usage patterns of the user, wherein the data includes information as to items which were used and the context in which they were used, wherein context includes a situation in which the user and device were operating when the items were used, without performing clustering of the usage patterns;

construct a correlation table, wherein each axis of the correlation table has both items that can be recommended and contexts, both extracted from the usage patterns;

determine a probability that an item in the correlation table will be useful to a user given a particular context; and

store a value correlation between each item and each context in the correlation table, wherein the correlations are used to recommend one or more of the items.

9. The apparatus of claim 8, wherein the apparatus is a mobile device.

10. A system for making recommendations to a user without performing clustering of usage patterns, the system comprising:

means for storing data relating to usage patterns of the user, wherein the data includes information as to items which were used and the context in which they were used, wherein context includes a situation in which the user and device were operating when the items were used;

means for constructing a correlation table, wherein each axis of the correlation table has both items that can be recommended and contexts, both extracted from the usage patterns;

means for determining a probability that an item in the correlation table will be useful to a user given a particular context; and

means for storing a correlation value between each item and each in the correlation table, wherein the correlations are used to recommend one or more of the items; and

a computer processor configured to interact with the means for storing, means for constructing and means for storing and to perform calculations based on input therefrom, providing results.

11. The system of claim 10, wherein the correlation values are relationships between items and contexts.

12. The system of claim 10, wherein the items comprise software applications, computing services, or data.

13. The system of claim 10, wherein the correlation table contains each of the one or more items and each of the contexts described by data points on each of the correlation table'"'"'s axes.

14. The system of claim 10, further comprising means for using Pearson'"'"'s correlation.

15. The system of claim 10, wherein the means for computing includes means for using cosine-based correlation.

16. The system of claim 10, wherein the means for recommending includes means for recomputing one or more of the correlation values to capture real values in a usage log.

17. A non-transitory program storage device readable by a machine tangibly embodying a program of instructions executable by the machine to perform a method for making recommendations to a user, the method comprising:

storing data relating to usage patterns of the user, wherein the data includes information as to items which were used and the context in which they were used, wherein context includes a situation in which the user and device were operating when the items were used;

constructing a correlation table, wherein each axis of the correlation table has both items that can be recommended and contexts, both extracted from the usage patterns and wherein the constructing is performed without performing clustering of usage patterns;

determining a probability that an item in the correlation table will be useful to a user given a particular context; and

storing a correlation value between each item and each context in the correlation table, wherein the correlations are used to recommend one or more of the items.