Data model pattern updating in a data collecting system

• US 9,805,111 B2
• Filed: 10/04/2010
• Issued: 10/31/2017
• Est. Priority Date: 10/04/2010
• Status: Active Grant

• Current Assignee: Telefonaktiebolaget LM Ericsson
• Original Assignee: Telefonaktiebolaget LM Ericsson
• Inventors: Hjelm, Johan, Lidstrom, Mattias, Matti, Mona
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US13/877,576
• Publication Number:
  US 20130311468A1
• Time in Patent Office: 2,584 Days
• Field of Search: 705 711- 742
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A pattern analysing device (27) in a pattern processing node {21} of a data collection system (10) comprises a pattern updating unit equipped with a pattern collecting element configured to obtain an existing pattern of historical data according to at least one existing data model, where the existing pattern relates to an entity (11) associated with the data collection system and obtain a further pattern of newer data according to a further data model, where the further pattern also relates to the entity, <<pattern updating element configured to compare the patterns with each other, determine if the existing data model can be mapped on the further data model and update the existing pattern with the further pattern in relation to the historical data if the existing data model can be mapped on the further data model.

Claims

1. A method for changing a pattern in data according to at least one data model in a communication system comprising hardware, said data comprising collected data of activities of user terminals communicating with the communication system using a network interface and said data of activities being grouped in a data base according to user terminal, the method being performed in a pattern processing node of the communication system and comprising the steps of:

obtaining an existing pattern of historical data according to at least one existing data model, said existing pattern relating to said user terminal associated with the communication system,

obtaining a further pattern of newer data according to a further data model, said further pattern also relating to said user terminal, wherein the historical data is generated before the existing pattern is identified and the newer data is generated after the historical data,

comparing the existing pattern with the further pattern,

determining if the existing data model can be mapped on the further data model based on the comparison,

determining a Euclidean distance between a vector of the existing pattern and a vector of the further pattern;

when the Euclidean distance between the vector of the existing pattern and the vector of the further pattern is above a distance threshold, updating the existing pattern with the further pattern in relation to the historical data based on determining that the existing data model can be mapped on the further data model, wherein the updated existing pattern is stored in the database; and

when the Euclidean distance is not above the distance threshold, the existing pattern is not updated.

2. The method according to claim 1, wherein each pattern comprises a number of attributes, the step of comparing patterns comprises comparing attributes of the patterns with each other, where each attribute corresponds to data of a data model and the step of updating comprises adding attributes of the further pattern to the existing pattern.

3. The method according to claim 2, wherein each pattern is provided as a vector and the step of comparing comprises determining the Euclidean distance between the vectors and the step of determining if the existing data model can be mapped on the further data model comprises comparing the Euclidean distance with the distance threshold.

4. The method according to claim 1, wherein the step of comparing is made while considering a set of policies.

5. The method according to claim 4, wherein the set of policies comprises an absolute policy regarding at least one attribute.

6. The method according to claim 4, wherein the set of policies comprises an aggregate policy regarding at least one attribute.

7. The method according to claim 1, wherein the step of comparing the existing pattern with the further pattern comprises comparing the occurrence of the further pattern in relation to the occurrence of the existing pattern in the newer data according to the further data model and the step of updating comprises updating the existing pattern with the further pattern with the same relationship as in the newer data.

8. The method according to claim 1, further comprising the step of identifying the further pattern based on at least some newer data.

9. The method according to claim 1, wherein the existing pattern has a label and further comprising the step of changing the label based on the updated pattern.

12. The method of claim 1, wherein the existing pattern is maintained in a pattern database, the method further comprising:

responsive to updating the existing pattern, recursively updating the pattern database.

13. The method of claim 1, wherein the Euclidean distance is determined according to:

d(A,B)=√

{square root over ((a₁−

b₁)²+(a₂−

b₂)²+. . . (a_n−

b_n)²)}

where d represents the Euclidean distance, A represents the vector of the existing pattern, and B represents the vector of the further pattern.

10. A communication system comprising a pattern analysing device in a pattern processing node and a database having data comprising collected data of activities of user terminals communicating with the communication system using a network interface and said data of activities being grouped according to user terminal, the pattern analysing device comprising:

a pattern updating unit equipped with a pattern collecting element configured to;

obtain an existing pattern of historical data according to at least one existing data model, said existing pattern relating to a user terminal associated with the communication system, and

obtain a further pattern of newer data according to a further data model, said further pattern also relating to said user terminal, wherein the historical data is generated before the existing pattern is identified and the newer data is generated after the historical data, compare the existing pattern with the further pattern, and a pattern updating element configured to determine if the existing data model can be mapped on the further data model based on the comparison, and

determine a Euclidean distance between a vector of the existing pattern and a vector of the further pattern;

when the Euclidean distance between the vector of the existing pattern and the vector of the further pattern is above a distance threshold, update the existing pattern with the further pattern in relation to the historical data based on determining that the existing data model can be mapped on the further data model, wherein the updated existing pattern is stored in the database, and

when the Euclidean distance is not above the distance threshold, the existing pattern is not updated.

11. A communication system according to claim 10, wherein the pattern analysing device further comprises a pattern analysing unit configured to identify at least the further pattern based on at least some of the newer data.

14. The communication system of claim 10, wherein the existing pattern is maintained in a pattern database, the a pattern updating unit equipped with a pattern collecting element further configured to:

responsive to updating the existing pattern, recursively update the pattern database. updating the existing pattern.

15. The communication system of claim 10, wherein the Euclidean distance is determined according to:

d(A,B)=√

{square root over ((a₁−

b₁)²+(a₂−

b₂)²+. . . (a_n−

b_n)²)}

where d represents the Euclidean distance, A represents the vector of the existing pattern, and B represents the vector of the further pattern.