GENERATION OF CONCEPT RELATIONS

• US 20100198604A1
• Filed: 01/30/2009
• Published: 08/05/2010
• Est. Priority Date: 01/30/2009
• Status: Abandoned Application

• Current Assignee: Samsung Electronics Co. Ltd.
• Original Assignee: Samsung Electronics Co. Ltd.
• Inventors: Cheng, Doreen, Song, Yu, Kalasapur, Swaroop, Jeong, Sangoh
• Application Number:
  US12/363,662
• Publication Number:
  US 20100198604A1
• Time in Patent Office: Days
• US Class Current: 705/1.1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Given a situation, an interest in a first object of interest can be determined. In the given situation, interest in a first object of interest is initially unknown and interest in a second object of interest is known. Data is obtained. The obtained data can, for example, include documents from the Internet or other forms of information from a network and/or database. The number of joint occurrences of the first object of interest and the second object of interest in the data is determined. Based on this number, at least one correlation value is determined. Based on the at least one correlation value, an interest value is determined. The interest value indicates the interest in the first object of interest in the given situation.

Claims

1. A computer-implemented method of determining interest in a first object of interest in a given situation of a plurality of situations, wherein interest in said first object of interest is unknown in said given situation and wherein interest in a second object of interest is known in said given situation, said computer-implemented method comprising:

obtaining data that includes a plurality of joint occurrences of said first object of interest and said second object of interest;

(a) determining a first number of joint occurrences of said first object of interest and said second object of interest in said data;

(b) determining, based on said first number of joint occurrences, at least one correlation value indicative of a first correlation between said first object of interest and said second object of interest; and

(c) determining an interest value indicative of said interest in said first object of interest based on said at least one correlation value.

2. The computer-implemented method of claim 1, wherein each one of said plurality of situations includes a plurality of context variables, each one of said plurality of context variables having a plurality of possible context values.

3. The computer-implemented method of claim 2, wherein said plurality of situations includes set of all possible combinations of said pluralities of context variables and context values and wherein interest in said first object of interest is unknown for said set of all possible combinations.

4. The computer-implemented method of claim 1, wherein:

interest in a third object of interest is known in said given situation;

said data includes joint occurrences of said first object of interest and said third object of interest;

the method further comprises;

(d) determining a second number of joint occurrences of said first object of interest and said third object of interest;

said at least one correlation value is based on said first number of joint occurrences and said second number of joint occurrences; and

said at least one correlation value is indicative of said first correlation and a second correlation between said first object of interest and said third object of interest.

5. The computer-implemented method of claim 4, wherein:

determining (c) includes calculating a weighted sum that is based on said at least one correlation value, said interest in said second object of interest and said interest in said third object of interest.

6. The computer-implemented method of claim 1, wherein there is a plurality of objects of interest including said first and second objects of interest and said interest value is not based on predetermined rules that are applied differently to different ones of said objects of interest.

7. The computer-implemented method of claim 1, wherein the at least one correlation value is based on at least one of a group consisting of:

conditional probability, cosine correlation and Pearson'"'"'s correlation.

9. The computer-implemented method of claim 7, wherein each one of said plurality of situations includes a plurality of context variables, each one of said plurality of context variables having a plurality of possible context values.

11. The computer-implemented method of claim 7, wherein said estimated interest value includes calculating a weighted sum that is based on said first correlation value, said second correlation value, said known second interest value for said given situation and said known third interest value for said given situation.

21. The computer-implemented method of claim 1, wherein the first object of interest and the second object of interest are not part of the same domain.

22. The computer-implemented method of claim 1, wherein the determining (c) of the interest value is not based on relative positions of the first and second objects of interest within a tree-like structure.

8. A computer-implemented method of determining interest in a keyword in a given situation of a plurality of situations, comprising:

(a) obtaining a plurality of situation-based interest rating components for said plurality of situations, wherein each one of said plurality of situation-based interest rating components includes a first interest value, a second interest value, a third interest value and one of said plurality of situations, said first, second and third interest values indicative of interests in first, second and third keywords respectively in said one of said plurality of situations, wherein said first interest values are unknown for said plurality of situations and wherein said second and third interest values are known at least for said given situation;

(b) obtaining a first plurality of text-based data items and a second plurality of text-based data items from a multiplicity of text-based data items, said first and second pluralities of text-based data items selected from said multiplicity of text-based data items based on said second and third keywords respectively, each one of said first plurality of text-based data items including at least one occurrence of said second keyword, each one of said second plurality of text-based data items including at least one occurrence of said third keyword, said first and second pluralities of text-based data items including at least one occurrence of said first keyword;

(a) determining a first correlation value based on comparing the number of occurrences of said first keyword in said first plurality of text-based data items and the number of occurrences of said second keyword in said first plurality of text-based data items;

(b) determining a second correlation value based on comparing the number of occurrences of said first keyword in said second plurality of text-based data items and the number of occurrences of said second keyword in said second plurality of text-based data items;

predicting, based on said first correlation value, said second correlation value, and said known second and third interest values, an estimated interest value indicative of interest in said first keyword in said given situation.

10. The computer-implemented method of claim 8, wherein said plurality of situations includes set of all possible combinations of said pluralities of context variables and context values and wherein said first interest values are unknown for said set of all possible combinations.

12. The computer-implemented method of claim 8, wherein said text-based data items include web documents and said obtaining (b) is performed by an Internet search engine.

13. A computing system for determining an interest in a first object of interest in a given situation of a plurality of situations, wherein interest in said first object of interest is unknown in said given situation and wherein interest in a second object of interest is known in said given situation and wherein said computing system is operable to:

obtain data that includes a plurality of joint occurrences of said first object of interest and said second object of interest;

(a) determine a first number of joint occurrences of said first object of interest and said second object of interest in said data;

(b) determine, based on said first number of joint occurrences, at least one correlation value indicative of a first correlation between said first object of interest and said second object of interest; and

(c) determine an interest value indicative of said interest in said first object of interest based on said at least one correlation value.

14. The computing system of claim 13, wherein the computing system includes at least one server and at least one client.

15. The computing system of claim 13, wherein each one of said plurality of situations includes a plurality of context variables, each one of said plurality of context variables having a plurality of possible context values.

16. The computing system of claim 15, wherein at least one of the context variables is based on one or more of the following:

a) an environmental factor and/or element;

b) an environmental factor and/or element associated with one or more humans interacting with one or more applications on the computing system;

c) environmental context of use associated with an environment of one or more humans as they interact with one or more active applications on the computing system;

d) a geographical and/or physical factor and/or element;

e) time, date, location, mode, mode of operation, condition, event, temperature, speed and/or acceleration of movement, power and/or force;

f) presence of one or more external components and/or devices;

g) presence of one or more active components operating on one or more external devices in a determined proximity of said device; and

h) one or more physiological and/or biological conditions associated with one or more persons interacting with the computing system.

17. The computing system of claim 13, wherein:

interest in a third object of interest is known in said given situation;

said data includes joint occurrences of said first object of interest and said third object of interest;

the method further comprises;

(d) determining a second number of joint occurrences of said first object of interest and said third object of interest;

said at least one correlation value is based on said first number of joint occurrences and said second number of joint occurrences; and

said at least one correlation value is indicative of said first correlation and a second correlation between said first object of interest and said third object of interest.

18. The computing system of claim 17, wherein:

determining (c) includes calculating a weighted sum that is based on said at least one correlation value, said interest in said second object of interest and said interest in said third object of interest.

19. The computer-implemented method of claim 13, wherein the at least one correlation value is based on at least one of a group consisting of:

conditional probability, cosine correlation and Pearson'"'"'s correlation.

20. A computer readable storage medium that includes executable computer code embodied in a tangible form operable to determine an interest in a first object of interest in a given situation of a plurality of situations, wherein interest in said first object of interest is unknown in said given situation and wherein interest in a second object of interest is known in said given situation and wherein said computer readable medium comprises:

executable computer code operable to obtain data that includes a plurality of joint occurrences of said first object of interest and said second object of interest;

executable computer code operable to (a) determine a first number of joint occurrences of said first object of interest and said second object of interest in said data;

executable computer code operable to (b) determine, based on said first number of joint occurrences, at least one correlation value indicative of a first correlation between said first object of interest and said second object of interest; and

executable computer code operable to (c) determine an interest value indicative of said interest in said first object of interest based on said at least one correlation value.

23. A computer-implemented method of determining interest in a first object of interest, wherein a first interest value indicative of an interest in said first object of interest is unknown and wherein a second interest value indicative of an interest in a second object of interest is known, said computer-implemented method comprising:

obtaining a first search term representing said first object of interest and a second search term representing said second object of interest;

transmitting the first and second search terms to a search engine configured to search a multiplicity of text-based data items stored on a network;

receiving data from said search engine indicating a plurality of joint occurrences of said first search term and said second search term in each of a plurality of said text-based data items;

determining at least one correlation value based on the received data, the correlation value indicative of a frequency that said first search term appears together with said second search term in one of the multiplicity of text-based data items; and

computing said first interest value indicative of said interest in said first object of interest based on said at least one correlation value and said second interest value.

24. The computer-implemented method of claim 23, wherein:

said multiplicity of text documents include a multiplicity of words, each text-based data item including a plurality of words;

the first and second search terms each include at least one word of the multiplicity of words; and

each of the plurality of joint occurrences involves a joint appearance of the at least one word of the first search term and the at least one word of second search term among the plurality of words of one of the multiplicity of text-based data items.