Activity Based Analytics

• US 20150095333A1
• Filed: 09/27/2013
• Published: 04/02/2015
• Est. Priority Date: 09/27/2013
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Spann, Janet L., Porpora, Gregory A.
• Granted Patent: US 9,396,253 B2
• Time in Patent Office: Days
• US Class Current: 707/737
• CPC Class Codes: G06F 16/24568 Data stream processing; Continuous queries
• CPC Class Codes: G06F 16/285 Clustering or classification
• CPC Class Codes: G06F 16/29 Geographical information databases
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/35 Clustering; Classification
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques
• CPC Class Codes: G06Q 50/26 Government or public services business processes related to the transportation industry G06Q50/40

Abstract

An approach for filtering data into a geo-activity zone cell is presented. An area of interest specifying an individual, organization, or entity is selected. Data is extracted from streaming data and from data at rest. Metadata of the extracted data is determined. The metadata includes time and date stamp(s) and contextual information specifying the area of interest. A first portion of the metadata includes geospatial tag(s) specifying the area of interest, and a second portion of the metadata is initially missing geospatial tag(s). The missing geospatial tag(s) are determined and added to the second portion of the metadata by extracting a location from profile data and/or inferring the location based on a region-based geo-topic model. The extracted data is filtered into a geo-activity zone cell based on the first and second portions of metadata being within metadata boundaries.

Claims

1. A method of filtering data, the method comprising the steps of:

a computer selecting an area of interest specifying an individual, organization, or entity;

the computer extracting data from streaming data and from data at rest;

the computer determining metadata of the extracted data, a first portion of the metadata including one or more geospatial tags, one or more time and date stamps, and contextual information specifying the area of interest, and a second portion of the metadata including one or more other time and date stamps and other contextual information specifying the area of interest with the second portion of the metadata missing one or more other geospatial tags specifying the area of interest;

the computer determining the one or more other geospatial tags missing from the second portion of metadata by;

extracting a location of the individual, organization or entity from profile data specifying the individual, organization, or entity, or inferring the location of the individual, organization or entity based on a region-based geo-topic model of the individual, organization or entity; and

assigning the extracted location or the inferred location to the one or more other geospatial tags; and

subsequent to the step of determining the one or more other geospatial tags, the computer filtering the extracted data into an entity-metadata element in a geo-activity zone cell based on the first and second portions of metadata and the one or more other geospatial tags being within metadata boundaries of the entity-metadata element.

2. The method of claim 1, further comprising the steps of:

the computer receiving coordinates of a geographic point and a distance;

the computer generating and displaying the geo-activity zone cell based on the geographic point and the distance from the geographic point; and

the computer tracking movements of the geo-activity zone cell or changes to the geo-activity zone cell.

3. The method of claim 2, wherein the step of generating and displaying the geo-activity zone cell includes:

performing a continuous query against the filtered extracted data using a master key to search for metadata that is geo-referenced based on the geographic point and the distance from the geographic point;

based on the master key, cross correlating and disambiguating the metadata that is geo-referenced into a set of groups including at least a first group associated with a person of interest, a second group associated with a network of persons, and a third group associated with an entity; and

displaying the cross correlated and disambiguated metadata in representations of the set of groups.

4. The method of claim 1, further comprising the steps of:

the computer selecting another area of interest specifying another individual, organization, or entity;

the computer extracting other data from streaming data and from data at rest;

the computer determining other metadata of the extracted other data, the computer filtering the extracted other data into another entity-metadata element in another geo-activity zone cell based on the other metadata being within other metadata boundaries of the other entity-metadata element;

the computer employing complex entity correlation which determines a relationship between the geo-activity zone cell and the other geo-activity zone cell; and

the computer generating and sending an alert about the geo-activity zone cell and the other geo-activity zone cell being related.

5. The method of claim 1, further comprising the steps of:

the computer employing supervised learning with the geo-activity zone cell;

the computer employing unsupervised learning with the geo-activity zone cell; and

based on results of the steps of employing supervised and unsupervised learning, the computer employing predictive analysis which predicts an activity or a behavior of the individual, organization or entity.

6. The method of claim 1, wherein the step of determining the one or more other geospatial tags includes:

the computer extracting the location of the individual, organization or entity from the profile data;

the computer inferring the location of the of the individual, organization or entity based on the region-based geo-topic model of the individual, organization or entity;

the computer converting the extracted location and the inferred location to respective first and second geo-hashes;

based on predetermined criteria, the computer selecting the first geo-hash instead of the second geo-hash or the second geo-hash instead of the first geo-hash; and

the computer assigning the selected geo-hash to a geospatial tag included in the one or more other geospatial tags.

7. The method of claim 1, further comprising the step of:

providing at least one support service for at least one of creating, integrating, hosting, maintaining, and deploying computer-readable program code in the computer, the program code being executed by a processor of the computer to implement the steps of selecting, extracting the data, determining the metadata, determining the one or more other geospatial tags, and filtering.

8. A computer system comprising:

a central processing unit (CPU);

a memory coupled to the CPU;

a computer-readable, tangible storage device coupled to the CPU, the storage device containing instructions that are executed by the CPU via the memory to implement a method of filtering data, the method comprising the steps of;

the computer system selecting an area of interest specifying an individual, organization, or entity;

the computer system extracting data from streaming data and from data at rest;

the computer system determining metadata of the extracted data, a first portion of the metadata including one or more geospatial tags, one or more time and date stamps, and contextual information specifying the area of interest, and a second portion of the metadata including one or more other time and date stamps and other contextual information specifying the area of interest with the second portion of the metadata missing one or more other geospatial tags specifying the area of interest;

the computer system determining the one or more other geospatial tags missing from the second portion of metadata by;

extracting a location of the individual, organization or entity from profile data specifying the individual, organization, or entity, or inferring the location of the individual, organization or entity based on a region-based geo-topic model of the individual, organization or entity; and

assigning the extracted location or the inferred location to the one or more other geospatial tags; and

subsequent to the step of determining the one or more other geospatial tags, the computer system filtering the extracted data into an entity-metadata element in a geo-activity zone cell based on the first and second portions of metadata and the one or more other geospatial tags being within metadata boundaries of the entity-metadata element.

9. The computer system of claim 8, wherein the method further comprises the steps of:

the computer system receiving coordinates of a geographic point and a distance;

the computer system generating and displaying the geo-activity zone cell based on the geographic point and the distance from the geographic point, wherein the step of displaying the geo-fenced area includes displaying a representation of the entity-metadata element within the geo-activity zone cell; and

the computer system tracking movements of the geo-activity zone cell or changes to the geo-activity zone cell.

10. The computer system of claim 9, wherein the step of generating and displaying the geo-activity zone cell includes:

performing a continuous query against the filtered extracted data using a master key to search for metadata that is geo-referenced based on the geographic point and the distance from the geographic point;

based on the master key, cross correlating and disambiguating the metadata that is geo-referenced into a set of groups including at least a first group associated with a person of interest, a second group associated with a network of persons, and a third group associated with an entity; and

displaying the cross correlated and disambiguated metadata in representations of the set of groups.

11. The computer system of claim 8, wherein the method further comprises the steps of:

the computer system selecting another area of interest specifying another individual, organization, or entity;

the computer system extracting other data from streaming data and from data at rest;

the computer system determining other metadata of the extracted other data, the computer system filtering the extracted other data into another entity-metadata element in another geo-activity zone cell based on the other metadata being within other metadata boundaries of the other entity-metadata element;

the computer system employing complex entity correlation which determines a relationship between the geo-activity zone cell and the other geo-activity zone cell based on a relationship between the entity-metadata element and the other entity-metadata element; and

the computer system generating and sending an alert about the geo-activity zone cell and the other geo-activity zone cell being related.

12. The computer system of claim 8, wherein the method further comprises the steps of:

the computer system employing supervised learning with the geo-activity zone cell;

the computer system employing unsupervised learning with the geo-activity zone cell; and

based on results of the steps of employing supervised and unsupervised learning, the computer system employing predictive analysis which predicts an activity or a behavior of the individual, organization or entity.

13. The computer system of claim 8, wherein the step of determining the one or more other geospatial tags includes:

the computer system extracting the location of the individual, organization or entity from the profile data;

the computer system inferring the location of the of the individual, organization or entity based on the region-based geo-topic model of the individual, organization or entity;

the computer system converting the extracted location and the inferred location to respective first and second geo-hashes;

based on predetermined criteria, the computer system selecting the first geo-hash instead of the second geo-hash or the second geo-hash instead of the first geo-hash; and

the computer system assigning the selected geo-hash to a geo-spatial tag included in the one or more other geospatial tags.

14. A computer program product, comprising:

a computer-readable, tangible storage device; and

a computer-readable program code stored in the computer-readable, tangible storage device, the computer-readable program code containing instructions that are executed by a central processing unit (CPU) of a computer system to implement a method of filtering data, the method comprising the steps of;

the computer system selecting an area of interest specifying an individual, organization, or entity;

the computer system extracting data from streaming data and from data at rest;

the computer system determining metadata of the extracted data, a first portion of the metadata including one or more geospatial tags, one or more time and date stamps, and contextual information specifying the area of interest, and a second portion of the metadata including one or more other time and date stamps and other contextual information specifying the area of interest with the second portion of the metadata missing one or more other geospatial tags specifying the area of interest;

the computer system determining the one or more other geospatial tags missing from the second portion of metadata by;

extracting a location of the individual, organization or entity from profile data specifying the individual, organization, or entity, or inferring the location of the individual, organization or entity based on a region-based geo-topic model of the individual, organization or entity; and

assigning the extracted location or the inferred location to the one or more other geospatial tags; and

subsequent to the step of determining the one or more other geospatial tags, the computer system filtering the extracted data into an entity-metadata element in a geo-activity zone cell based on the first and second portions of metadata and the one or more other geospatial tags being within metadata boundaries of the entity-metadata element.

15. The program product of claim 14, wherein the method further comprises the steps of:

the computer system receiving coordinates of a geographic point and a distance;

the computer system generating and displaying the geo-activity zone cell based on the geographic point and the distance from the geographic point, wherein the step of displaying the geo-fenced area includes displaying a representation of the entity-metadata element within the geo-activity zone cell; and

the computer system tracking movements of the geo-activity zone cell or changes to the geo-activity zone cell.

16. The program product of claim 15, wherein the step of generating and displaying the geo-activity zone cell includes:

performing a continuous query against the filtered extracted data using a master key to search for metadata that is geo-referenced based on the geographic point and the distance from the geographic point;

based on the master key, cross correlating and disambiguating the metadata that is geo-referenced into a set of groups including at least a first group associated with a person of interest, a second group associated with a network of persons, and a third group associated with an entity; and

displaying the cross correlated and disambiguated metadata in representations of the set of groups.

17. The program product of claim 14, wherein the method further comprises the steps of:

the computer system selecting another area of interest specifying another individual, organization, or entity;

the computer system extracting other data from streaming data and from data at rest;

the computer system determining other metadata of the extracted other data, the computer system filtering the extracted other data into another entity-metadata element in another geo-activity zone cell based on the other metadata being within other metadata boundaries of the other entity-metadata element;

the computer system employing complex entity correlation which determines a relationship between the geo-activity zone cell and the other geo-activity zone cell based on a relationship between the entity-metadata element and the other entity-metadata element; and

the computer system generating and sending an alert about the geo-activity zone cell and the other geo-activity zone cell being related.

18. The program product of claim 14, wherein the method further comprises the steps of:

the computer system employing supervised learning with the geo-activity zone cell;

the computer system employing unsupervised learning with the geo-activity zone cell; and

based on results of the steps of employing supervised and unsupervised learning, the computer system employing predictive analysis which predicts an activity or a behavior of the individual, organization or entity.

19. The program product of claim 14, wherein the step of determining the one or more other geospatial tags includes:

the computer system extracting the location of the individual, organization or entity from the profile data;

the computer system inferring the location of the of the individual, organization or entity based on the region-based geo-topic model of the individual, organization or entity;

the computer system converting the extracted location and the inferred location to respective first and second geo-hashes;

based on predetermined criteria, the computer system selecting the first geo-hash instead of the second geo-hash or the second geo-hash instead of the first geo-hash; and

the computer system assigning the selected geo-hash to a geo-spatial tag included in the one or more other geospatial tags.