Back to results
US 10,885,065 B2Granted
Data convergence
AssigneeInternational Business Machines Corporation
InventorsJonathan Dunne, Karen Forde, William Holmes, Andrew Penrose
Life of this patent
Estimating the term…
Abstract
Embodiment for identifying data convergence are presented. First and second sets of data each comprising heterogeneous data are each processed in accordance with a data clustering algorithm so as to obtain a plurality of primary and secondary data clusters, respectively, where each data cluster comprising homogeneous data. The primary and secondary data clusters are analyzed with respect to time to identify convergence of data of the first and second sets of data to first and second topics, respectively. The first and second topics are compared to determine a pattern of data convergence for the first and second data sets.
Claims15
A computer-implemented method for identifying data convergence, the method comprising:
- processing a first set of data comprising heterogeneous data in accordance with a data clustering algorithm so as to obtain a plurality of primary data clusters, wherein each primary data cluster is associated with a point in time, and wherein each of the plurality of primary data clusters comprises homogeneous data;
- analyzing the plurality of primary data clusters with respect to time to identify convergence of data of the first set of data to a first topic over time further comprising:
- defining a first time slice of the first set of data using a first time interval to form a first plurality of consecutive primary data clusters;
- defining a second time slice of the first set of data using a second time interval to form a second plurality of consecutive primary data clusters;
- and
- comparing the data from the first plurality of consecutive primary data clusters and the second plurality of consecutive primary data clusters to identify a pattern of convergence of data of the first set of data to the first topic over time;
- processing a second set of data comprising heterogeneous data in accordance with a data clustering algorithm so as to obtain a plurality of secondary data clusters, wherein each primary data cluster is associated with a point in time, and wherein each of the plurality of primary data clusters comprises homogeneous data, wherein the processing further comprises:
- dividing the communications or documents into data bundles;
- analyzing the data bundles to identify data similarity;
- and
- redefining the communications or documents based on identified data similarity;
- analyzing the plurality of secondary data clusters with respect to time to identify convergence of data of the second set of data to a second topic over time;
- and
- comparing the first and second topics to determine a pattern of data convergence of data of the first and second data sets further comprising:
- determining relevance scores for topics of the primary and secondary data clusters;
- determining differences between relevance scores of topics of the primary and secondary data clusters;
- using the determined differences to identify a pattern of data convergence selected from the group comprising:
- increasing relevance of one or more topics, indicative of topic convergence;
- and decreasing relevance of one or more topics, indicative of topic divergence;
- processing a set of data in accordance with a data clustering algorithm,
- wherein the set of data comprises a set of communications or documents, comprising:
- dividing the communications or documents into data bundles;
- analyzing the data bundles to identify data similarity;
- and
- redefining the communications or documents based on identified data similarity.
22 more elements
A computer program product for identifying data convergence, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing unit to cause the processing unit to perform a method comprising:
- processing a first set of data comprising heterogeneous data in accordance with a data clustering algorithm so as to obtain a plurality of primary data clusters, wherein each primary data cluster is associated with a point in time, and wherein each of the plurality of primary data clusters comprises homogeneous data;
- analyzing the plurality of primary data clusters with respect to time to identify convergence of data of the first set of data to a first topic over time further comprising:
- defining a first time slice of the first set of data using a first time interval to form a first plurality of consecutive primary data clusters;
- defining a second time slice of the first set of data using a second time interval to form a second plurality of consecutive primary data clusters;
- and
- comparing the data from the first plurality of consecutive primary data clusters and the second plurality of consecutive primary data clusters to identify a pattern of convergence of data of the first set of data to the first topic over time;
- processing a second set of data comprising heterogeneous data in accordance with a data clustering algorithm so as to obtain a plurality of secondary data clusters, wherein each primary data cluster is associated with a point in time, and wherein each of the plurality of primary data clusters comprises homogeneous data, wherein the processing further comprises:
- dividing the communications or documents into data bundles;
- analyzing the data bundles to identify data similarity;
- and
- redefining the communications or documents based on identified data similarity;
- analyzing the plurality of secondary data clusters with respect to time to identify convergence of data of the second set of data to a second topic over time;
- and
- comparing the first and second topics to determine a pattern of data convergence of data of the first and second data sets further comprising:
- determining relevance scores for topics of the primary and secondary data clusters;
- determining differences between relevance scores of topics of the primary and secondary data clusters;
- using the determined differences to identify a pattern of data convergence selected from the group comprising:
- increasing relevance of one or more topics, indicative of topic convergence;
- and decreasing relevance of one or more topics, indicative of topic divergence;
- processing a set of data in accordance with a data clustering algorithm,
- wherein the set of data comprises a set of communications or documents, comprising:
- dividing the communications or documents into data bundles;
- analyzing the data bundles to identify data similarity;
- and
- redefining the communications or documents based on identified data similarity.
22 more elements
A system for identifying data convergence, the system comprising a memory having computer readable instructions, and one or more processors for executing the computer readable instructions, the computer readable instruction controlling the one or more processors to perform operations comprising:
- processing a first set of data comprising heterogeneous data in accordance with a data clustering algorithm so as to obtain a plurality of primary data clusters, wherein each primary data cluster is associated with a point in time, and wherein each of the plurality of primary data clusters comprises homogeneous data;
- analyzing the plurality of primary data clusters with respect to time to identify convergence of data of the first set of data to a first topic over time further comprising:
- defining a first time slice of the first set of data using a first time interval to form a first plurality of consecutive primary data clusters;
- defining a second time slice of the first set of data using a second time interval to form a second plurality of consecutive primary data clusters;
- and
- comparing the data from the first plurality of consecutive primary data clusters and the second plurality of consecutive primary data clusters to identify a pattern of convergence of data of the first set of data to the first topic over time;
- processing a second set of data comprising heterogeneous data in accordance with a data clustering algorithm so as to obtain a plurality of secondary data clusters, wherein each primary data cluster is associated with a point in time, and wherein each of the plurality of primary data clusters comprises homogeneous data, wherein the processing further comprises:
- dividing the communications or documents into data bundles;
- analyzing the data bundles to identify data similarity;
- and
- redefining the communications or documents based on identified data similarity;
- analyzing the plurality of secondary data clusters with respect to time to identify convergence of data of the second set of data to a second topic over time;
- and
- comparing the first and second topics to determine a pattern of data convergence of data of the first and second data sets further comprising:
- determining relevance scores for topics of the primary and secondary data clusters;
- determining differences between relevance scores of topics of the primary and secondary data clusters;
- using the determined differences to identify a pattern of data convergence selected from the group comprising:
- increasing relevance of one or more topics, indicative of topic convergence;
- and decreasing relevance of one or more topics, indicative of topic divergence;
- processing a set of data in accordance with a data clustering algorithm,
- wherein the set of data comprises a set of communications or documents, comprising:
- dividing the communications or documents into data bundles;
- analyzing the data bundles to identify data similarity;
- and
- redefining the communications or documents based on identified data similarity.
22 more elements
Dependencies are inferred from the claim text.