Appeal No. 2004-2099
Application No. 09/487,191
original data. The server computer estimates the distribution of
the original data based on the distribution of the perturbed data
and generates a data-mining model from the estimate. Also, the
server computer generates at least one classification model using
the perturbed data. See Appellants' specification at pages 3 and
7.
Claims 1 and 7 are representative of the claimed invention
and are reproduced as follows:
1. A computer-implemented method for obtaining data from at
least one user computer via the Internet while maintaining the
privacy of a user of the computer, comprising the acts of:
perturbing original data associated with the user computer
to render perturbed data;
using a distribution of the perturbed data, generating at
least one estimate of a distribution of the original data; and
using the estimate of the distribution of the original data,
generating at least one data mining model.
7. A computer system including a program of instructions
including structure to undertake method acts comprising:
at a user computer, randomizing at least some original
values of at least some numeric attributes to render perturbed
values;
sending the perturbed values to a server computer not having
access to the original values;
and
at the server computer, processing the perturbed values to
generate at least one classification model.
2
Page: Previous 1 2 3 4 5 6 7 8 9 10 Next
Last modified: November 3, 2007