Data analysis based on data linking elements
First Claim
1. A computer controlled method for analyzing unstructured data, wherein said unstructured data comprises a plurality of data elements, and wherein the unstructured data is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data, the method comprising acts of:
- identifying a first subset of the plurality of data elements as Linking Data Elements (LDEs), wherein each of the LDEs is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data, wherein identifying a first subset comprises;
retrieving, from a repository, a predetermined set of stored LDEs; and
comparing the unstructured data to the predetermined set of stored LDEs;
identifying a second subset of the plurality of data elements as Information Carrying Data Elements (ICDEs), wherein the second subset is comprised of every data element not identified as an LDE; and
representing the unstructured data in a structured format based on the identification of LDEs and ICDEs.
1 Assignment
0 Petitions
Accused Products
Abstract
A computer controlled method for automatically segmenting an ensemble of data. The method starts by acquiring an ensemble of data and data is segmented by identifying a first subset of sequences of Linking Data Elements based on a repository of Linking Data Elements. A second subset of sequences of Information Carrying Data Elements is identified, wherein the sequences are linked by the Linking Data Elements. The subsets are provided in a structured format.
13 Citations
14 Claims
-
1. A computer controlled method for analyzing unstructured data, wherein said unstructured data comprises a plurality of data elements, and wherein the unstructured data is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data, the method comprising acts of:
-
identifying a first subset of the plurality of data elements as Linking Data Elements (LDEs), wherein each of the LDEs is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data, wherein identifying a first subset comprises; retrieving, from a repository, a predetermined set of stored LDEs; and comparing the unstructured data to the predetermined set of stored LDEs; identifying a second subset of the plurality of data elements as Information Carrying Data Elements (ICDEs), wherein the second subset is comprised of every data element not identified as an LDE; and representing the unstructured data in a structured format based on the identification of LDEs and ICDEs. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12)
-
-
13. A computer controlled method for analyzing unstructured data, wherein said unstructured data comprises a plurality of data elements, the method comprising acts of:
-
retrieving a plurality of Linking Data Elements (LDEs) from a repository, wherein each of the plurality of LDEs is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data; segmenting the unstructured data into a first subset of sequences of LDEs included within the plurality of LDEs, each sequence of said first subset of sequences comprising at least one LDE; identifying, in the unstructured data, a second subset of sequences of Information Carrying Data Elements (ICDEs) not included within said first subset of sequences of LDEs, each sequence of said second subset of sequences being linked by a sequence of said first subset of sequences and comprising at least one ICDE, wherein every data element of the unstructured data not identified as an LDE is identified as an ICDE; and representing combinations of LDEs of the first subset and ICDEs of the second subset in a structured format based on occurrence thereof in the unstructured data; wherein the unstructured data is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data.
-
-
14. A computer controlled method for analyzing unstructured data, wherein said unstructured data consists essentially of a plurality of Linking Data Elements (LDEs) and a plurality of Information Carrying Data Elements (ICDEs), and wherein the unstructured data is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data, the method comprising acts of:
-
identifying the plurality of LDEs of the unstructured data, wherein each of the LDEs is at least one of text data, linguistic data, image data, video data, sound data, control data, measurement data, olfactive data and tactile data, wherein identifying the plurality of LDEs comprises; retrieving, from a repository, a predetermined set of stored LDEs; and comparing the unstructured data to the predetermined set of stored LDEs; identifying every portion of the unstructured data not previously identified as an LDE as one of the plurality of ICDEs; and representing the unstructured data in a structured format based on the identification of LDEs and ICDEs.
-
Specification