System and method for behavioural modelling

• US 7,340,060 B2
• Filed: 10/26/2005
• Issued: 03/04/2008
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Black Box Intelligence Limited
• Original Assignee: Black Box Intelligence Limited
• Inventors: Tomkins, Benjamin M, Nimmo, Craig T, Ladde, Cedric
• Primary Examiner(s): Knight; Anthony
• Assistant Examiner(s): Brown, Jr.; Nathan H.
• Application Number:
  US11/258,167
• Publication Number:
  US 20070112704A1
• Time in Patent Office: 860 Days
• Field of Search: 706/21
• US Class Current: 380/277
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

The present invention is a computer system that analyses the factual and behavioural data of a group of subjects, extracts the common behavioural patterns from the collection, and is capable of forecasting the behaviour of a new subject when his or her factual data are inputted to the system. It does so by first taking a collection of both the factual data and behavioural data from a group of subjects. A clustering engine is employed to compute a set of exemplars that concisely represent the population. Afterwards, the factual data of a subject, and the corresponding behavioural exemplar that he or she belongs, are fed to a learning module so that it can learn the mapping between the subject'"'"'s factual data and behavioural exemplar. After learning, the system is able to predict the behaviour patterns when factual data of a new subject is presented.

Claims

1. A computer system for behavioral modeling comprising

a. means for receiving factual data and behavioral data from at least one subject;

b. a clustering engine for grouping said behavioral data to form exemplars automatically, said exemplars representing the behavioral patterns of said at least one subject;

c. a learning module for mapping said factual data to said exemplars; and

d. a selection module;

said selection module configured to examine the outputs of said learning module upon receiving input of factual data of a selected subject, and selecting at least one exemplar from said clustering engine as a predicted behavioral pattern of said selected subject;

wherein the system is further configured to receive new factual and behavioral data in a pre-determined time period from at least one subject;

said clustering engine and said learning module further configured to perform the steps of

e. adjusting the internal parameters of said clustering engine and said learning module based on said new data;

f. computing new exemplar values of said clustering engine and activation values of said learning module from factual and behavioral data of a set of test subjects;

g. obtaining the differences, using the same said test subjects, between results from step (f) and original activation values of said learning module and original exemplar values of clustering engine before performing step (e) and

h. reporting said differences as the behavioral changes of said at least one subject during said pre-determined time period.

2. The system according to claim 1 wherein said new factual and behavioral data replaces the same amount and earliest of said factual and behavioral data.

3. A computer system for behavioral modeling comprising

a. means for receiving factual data and behavioral data from at least one subject;

b. a clustering engine for grouping said behavioral data to form exemplars automatically, said exemplars representing the behavioral patterns of said at least one subject;

c. a learning module for mapping said factual data to said exemplars; and

d. a selection module;

said selection module configured to examine the outputs of said learning module upon receiving input of factual data of a selected subject, and selecting at least one exemplar from said clustering engine as a predicted behavioral pattern of said selected subject;

wherein said at least one subject and said selected subject are the same subject.

4. A computer system for behavioral modeling comprising

a. means for receiving factual data and behavioral data from at least one subject;

b. a clustering engine for grouping said behavioral data to form exemplars automatically, said exemplars representing the behavioral patterns of said at least one subject;

c. a learning module for mapping said factual data to said exemplars; and

d. a selection module;

said selection module configured to examine the outputs of said learning module upon receiving input of factual data of a selected subject, and selecting at least one exemplar from said clustering engine as a predicted behavioral pattern of said selected subject;

wherein said at least one subject comprises a plurality of subjects and said selected subject comprises a subject different from said plurality of subjects.

5. A computer system for behavioral modeling comprising

a. means for receiving factual data and behavioral data from at least one subject;

b. a clustering engine for grouping said behavioral data to form exemplars automatically, said exemplars representing the behavioral patterns of said at least one subject;

c. a learning module for mapping said factual data to said exemplars; and

d. a selection module;

said selection module configured to examine the outputs of said learning module upon receiving input of factual data of a selected subject, and selecting at least one exemplar from said clustering engine as a predicted behavioral pattern of said selected subject;

wherein said at least one subject comprises a plurality of subjects and said selected subject comprises a subject chosen from one of said plurality of subjects.

6. A method for behavioral modeling in a computer comprising

a. receiving factual data and behavioral data from at least one subject;

b. grouping said behavioral data using a clustering engine to form exemplars, said exemplars representing the behavioral patterns of said at least one subject; and

c. performing a mapping using a learning module that maps said factual data to said exemplars;

d. examining the outputs of said learning module upon receiving input of factual data of a selected subject; and

selecting at least one exemplar from said clustering engine as a predicted behavioral pattern of said selected subject;

e. receiving new factual and behavioral data from at least one subject in pre-determined time period;

f. adding said new data from step (e) to existing factual database and behavioral database;

g. adjusting the internal parameters of said clustering engine and said learning module using databases in step (f);

h. computing new exemplar values of said clustering engine and activation values of said learning module from factual and behavioral data of a set of test subjects;

i. obtaining the differences, using same said test subjects, between results from step (h) and original activation values of said learning module and original exemplar values of clustering engine before step (g) is performed, and

j. reporting said differences as the behavioral changes of said at least one subject during said pre-determined time period.

7. The method according to claim 6 wherein said new factual and behavioral data replaces the same amount and earliest of said factual and behavioral data.