ELECTRONIC COMPUTING DEVICE, PERSONALIZED DATA RECOMMENDING METHOD THEREOF, AND NON-TRANSITORY MACHINE-READABLE MEDIUM THEREOF

• US 20150100575A1
• Filed: 12/02/2013
• Published: 04/09/2015
• Est. Priority Date: 10/07/2013
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: SHAE, Zonyin, WANG, Ko-Yang, SHIH, Meng-Jung, TU, Ting-Chieh, CHAN, Ya-Hui, CHEN, Ping-I, WANG, Tai-Chun
• Granted Patent: US 9,208,501 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

An electronic computing device, a personalized information providing method thereof, and a non-transitory machine-readable medium thereof are provided. The electronic computing device establishes a first and a second tree structure data according to a first data of a first user and a second data of a second user arranged in a period respectively by using an ontology construction algorithm, and calculates a similarity between the first and the second tree structure data by using a similarity evaluating algorithm, and then analyzes the similarity to subsume the first and the second tree structure data into a group by using a clustering algorithm. The electronic computing device determines difference between the first and the second tree structure data according to the group and generates recommending information corresponding to the first user which is arranged in the period according to the difference, and then enables a monitor to display the recommending information.

Claims

1. An electronic computing device for providing a personalized information recommendation, comprising:

an input/output interface, being configured to receive a first behavior data of a first user and a second behavior data of a second user, wherein the first behavior data and the second behavior data are arranged in a first period;

a storage electrically connected to the input/output interface, being configured to store the first behavior data and the second behavior data; and

a processor electrically connected to the storage, being configured to execute the following operations;

retrieving the first behavior data and the second behavior data from the storage;

establishing a first tree structure data and a second tree structure data according to the first behavior data and the second behavior data respectively by using an ontology construction algorithm;

calculating a first similarity between the first tree structure data and the second tree structure data by using a similarity evaluation algorithm;

analyzing the first similarity to subsume the first tree structure data and the second tree structure data into a first group by using a clustering algorithm;

determining a piece of first difference information between the first tree structure data and the second tree structure data according to the first group; and

generating a piece of first recommending information corresponding to the first user which is arranged in the first period according to the piece of first difference information so that a first monitor displays the piece of first recommending information.

2. The electronic computing device as claimed in claim 1, wherein the input/output interface is further configured to receive a third behavior data of a third user, the third behavior data is arranged in the first period, the storage is further configured to store the third behavior data, and the processor is further configured to execute the following operations:

retrieving the third behavior data from the storage;

establishing a third tree structure data according to the third behavior data by using the ontology construction algorithm;

calculating a second similarity between the first tree structure data and the third tree structure data, and a third similarity between the second tree structure data and the third tree structure data by using the similarity evaluation algorithm; and

wherein the first group further comprises the third tree structure data that is obtained by the processor by further using the clustering algorithm to analyze the first similarity, the second similarity and the third similarity;

wherein the piece of first difference information is further obtained by the processor by determining a difference between the first tree structure data and the second and the third tree structure data according to the first group.

3. The electronic computing device as claimed in claim 2, wherein the piece of first difference information comprises a plurality of difference words, and the processor further accumulates a number of appearances of each of the difference words and generates the piece of first recommending data according to an optimum difference word of which the accumulated number of appearances is the largest.

4. The electronic computing device as claimed in claim 2, wherein the piece of first difference information comprises a plurality of difference words, and the processor further generates the piece of first recommending information according to when an appearance ratio of at least one of the plurality of difference words is higher than a threshold.

5. The electronic computing device as claimed in claim 1, wherein the input/output interface is further configured to receive a fourth behavior data of a fourth user, a fifth behavior data of the first user and a sixth behavior data of the second user, the fourth behavior data, the fifth behavior data and the sixth behavior data are arranged in a second period, the storage is further configured to store the fourth behavior data, the fifth behavior data and the sixth behavior data, and the processor is further configured to execute the following operations:

retrieving the fourth behavior data, the fifth behavior data and the sixth behavior data from the storage;

establishing a fourth tree structure data, a fifth tree structure data and a sixth tree structure data according to the fourth behavior data, the fifth behavior data and the sixth behavior data respectively by using the ontology construction algorithm;

calculating a fourth similarity between the fourth tree structure data and the fifth tree structure data, a fifth similarity between the fifth tree structure data and the sixth tree structure data and a sixth similarity between the sixth tree structure data and the fourth tree structure data respectively by using the similarity evaluation algorithm;

analyzing the fourth similarity, the fifth similarity and the sixth similarity to subsume the fourth tree structure data and the fifth tree structure data into a second group and subsume the fourth tree structure data, the fifth tree structure data and the sixth tree structure data into a third group by using the clustering algorithm, wherein an internal data correlation of the second group is higher than an internal data correlation of the third group;

determining a piece of second difference information between the fifth tree structure data and the fourth tree structure data according to the second group; and

generating a piece of second recommending information corresponding to the first user which is arranged in a second period according to the piece of second difference information so that the first monitor displays the piece of second recommending information.

6. A personalized information recommending method for use in an electronic computing device, the electronic computing device comprising an input/output interface, a storage and a processor, the personalized information recommending method comprising the steps of:

(a) enabling the input/output interface to receive a first behavior data of a first user and a second behavior data of a second user, wherein the first behavior data and the second behavior data are arranged in a first period;

(b) enabling the storage to store the first behavior data and the second behavior data;

(c) enabling the processor to retrieve the first behavior data and the second behavior data from the storage;

(d) enabling the processor to establish a first tree structure data and a second tree structure data according to the first behavior data and the second behavior data respectively by using an ontology construction algorithm;

(e) enabling the processor to calculate a first similarity between the first tree structure data and the second tree structure data by using a similarity evaluation algorithm;

(f) enabling the processor to analyze the first similarity to subsume the first tree structure data and the second tree structure data into a first group by using a clustering algorithm;

(g) enabling the processor to determine a piece of first difference information between the first tree structure data and the second tree structure data according to the first group; and

(h) enabling the processor to generate a piece of first recommending information corresponding to the first user which is arranged in the first period according to the piece of first difference information so that a first monitor displays the piece of first recommending information.

7. The personalized information recommending method as claimed in claim 6, wherein:

the step (a) further comprises the step of;

(a1) enabling the input/output interface to receive a third behavior data of a third user, wherein the third behavior data is arranged in the first period;

the step (b) further comprises the step of;

(b1) enabling the storage to store the third behavior data;

the step (c) further comprises the step of;

(c1) enabling the processor to retrieve the third behavior data from the storage;

the step (d) further comprises the step of;

(d1) enabling the processor to establish a third tree structure data according to the third behavior data by using the ontology construction algorithm;

the step (e) further comprises the step of;

(e1) enabling the processor to calculate a second similarity between the first tree structure data and the third tree structure data and a third similarity between the second tree structure data and the third tree structure data by using the similarity evaluation algorithm;

the step (f) is further the step of;

(f1) enabling the processor to analyze the first similarity, the second similarity and the third similarity to subsume the first tree structure data, the second tree structure data and the third tree structure data into the first group by using the clustering algorithm; and

the step (g) is further the step of;

(g1) enabling the processor to determine the piece of first difference information between the first tree structure data and the second and the third tree structure data.

8. The personalized information recommending method as claimed in claim 7, wherein the piece of first difference information comprises a plurality of difference words, and the processor further accumulates a number of appearances of each of the difference words and generates the piece of first recommending information according to an optimum difference word of which the accumulated number of appearances is the largest.

9. The personalized information recommending method as claimed in claim 7, wherein the piece of first difference information comprises a plurality of difference words, and the processor further generates the piece of first recommending information according to when an appearance ratio of at least one of the plurality of difference words is higher than a threshold.

10. The personalized information recommending method as claimed in claim 6, further comprising the steps of:

(i) enabling the input/output interface to receive a fourth behavior data of a fourth user, a fifth behavior data of the first user and a sixth behavior data of the second user, wherein the fourth behavior data, the fifth behavior data and the sixth behavior data are arranged in a second period;

(j) enabling the storage to store the fourth behavior data, the fifth behavior data and the sixth behavior data;

(k) enabling the processor to retrieve the fourth behavior data, the fifth behavior data and the sixth behavior data from the storage;

(l) enabling the processor to establish a fourth tree structure data, a fifth tree structure data and a sixth tree structure data according to the fourth behavior data, the fifth behavior data and the sixth behavior data respectively by using the ontology construction algorithm;

(m) enabling the processor to calculate a fourth similarity between the fourth tree structure data and the fifth tree structure data, a fifth similarity between the fifth tree structure data and the sixth tree structure data and a sixth similarity between the sixth tree structure data and the fourth tree structure data by using the similarity evaluation algorithm;

(n) enabling the processor to analyze the fourth similarity, the fifth similarity and the sixth similarity to subsume the fourth tree structure data and the fifth tree structure data into a second group and subsume the fourth tree structure data, the fifth tree structure data and the sixth tree structure data into a third group by using the clustering algorithm, wherein an internal data correlation of the second group is higher than an internal data correlation of the third group;

(o) enabling the processor to determine a piece of second difference information between the fifth tree structure data and the fourth tree structure data according to the second group; and

(p) enabling the processor to generate a piece of second recommending information corresponding to the first user which is arranged in the second period according to the piece of second difference information so that the first monitor displays the piece of second recommending information.

11. A non-transitory machine-readable medium comprising a plurality of codes, wherein when the plurality of codes are loaded into an electronic computing device, the codes comprised in the non-transitory machine-readable medium will be executed by the electronic computing device to accomplish a personalized information recommending method, the codes comprising:

a code A for enabling the electronic computing device to receive a first behavior data of a first user and a second behavior data of a second user, wherein the first behavior data and the second behavior data are arranged in a first period;

a code B for enabling the electronic computing device to store the first behavior data and the second behavior data;

a code C for enabling the electronic computing device to establish a first tree structure data and a second tree structure data according to the first behavior data and the second behavior data respectively by using an ontology construction algorithm;

a code D for enabling the electronic computing device to calculate a first similarity between the first tree structure data and the second tree structure data by using a similarity evaluation algorithm;

a code E for enabling the electronic computing device to analyze the first similarity to subsume the first tree structure data and the second tree structure data into a first group by using a clustering algorithm;

a code F for enabling the electronic computing device to determine a piece of first difference information between the first tree structure data and the second tree structure data according to the first group; and

a code G for enabling the electronic computing device to generate a piece of first recommending information corresponding to the first user which is arranged in the first period according to the piece of first difference information so that a first monitor displays the piece of first recommending information.

12. The non-transitory machine-readable medium as claimed in claim 11, wherein:

the code A further comprises a code for;

enabling the electronic computing device to receive a third behavior data of a third user, wherein the third behavior data is arranged in the first period;

the code B further comprises a code for;

enabling the electronic computing device to store the third behavior data;

the code C further comprises a code for;

enabling the electronic computing device to establish a third tree structure data according to the third behavior data by using the ontology construction algorithm;

the code D further comprises a code for;

enabling the electronic computing device to calculate a second similarity between the first tree structure data and the third tree structure data and a third similarity between the second tree structure data and the third tree structure data by using the similarity evaluation algorithm;

the code E is further a code for;

enabling the electronic computing device to analyze the first similarity, the second similarity and the third similarity to subsume the first tree structure data, the second tree structure data and the third tree structure data into the first group by using the clustering algorithm; and

the code F is further a code for;

enabling the electronic computing device to determine the piece of first difference information between the first tree structure data and the second and the third tree structure data.

13. The non-transitory machine-readable medium as claimed in claim 12, wherein the piece of first difference information comprises a plurality of difference words, and the codes further comprising:

a code, enabling the electronic computing device to accumulate a number of appearances of each of the difference words and generates the piece of first recommending information according to an optimum difference word of which the accumulated number of appearance is the largest.

14. The non-transitory machine-readable medium as claimed in claim 12, wherein the piece of first difference information comprises a plurality of difference words, and the codes further comprising:

a code, enabling the electronic computing device to generate the piece of first recommending information when an appearance ratio of at least one of the plurality of difference words is higher than a threshold.

15. The non-transitory machine-readable medium as claimed in claim 11, wherein the codes further comprises:

a code H for enabling the electronic computing device to receive a fourth behavior data of a fourth user, a fifth behavior data of the first user and a sixth behavior data of the second user, wherein the fourth behavior data, the fifth behavior data and the sixth behavior data are arranged in a second period;

a code I for enabling the electronic computing device to store the fourth behavior data, the fifth behavior data and the sixth behavior data;

a code J for enabling the electronic computing device to establish a fourth tree structure data, a fifth tree structure data and a sixth tree structure data according to the fourth behavior data, the fifth behavior data and the sixth behavior data respectively by using the ontology construction algorithm;

a code K for enabling the electronic computing device to calculate a fourth similarity between the fourth tree structure data and the fifth tree structure data, a fifth similarity between the fifth tree structure data and the sixth tree structure data and a sixth similarity between the sixth tree structure data and the fourth tree structure data respectively by using the similarity evaluation algorithm;

a code L for enabling the electronic computing device to analyze the fourth similarity, the fifth similarity and the sixth similarity to subsume the fourth tree structure data and the fifth tree structure data into a second group and subsume the fourth tree structure data, the fifth tree structure data and the sixth tree structure data into a third group by using the clustering algorithm, wherein an internal data correlation of the second group is higher than an internal data correlation of the third group;

a code M for enabling the electronic computing device to determine a piece of second difference information between the fifth tree structure data and the fourth tree structure data according to the second group; and

a code O for enabling the electronic computing device to generate a piece of second recommending information corresponding to the first user which is arranged in a second period according to the piece of second difference information so that the first monitor displays the piece of second recommending information.