COMPUTER-IMPLEMENTED SYSTEMS AND METHODS OF ANALYZING SPATIAL, TEMPORAL AND CONTEXTUAL ELEMENTS OF DATA FOR PREDICTIVE DECISION-MAKING

• US 20160217381A1
• Filed: 09/27/2013
• Published: 07/28/2016
• Est. Priority Date: 09/27/2013
• Status: Active Grant

• Current Assignee: TransVoyant Inc.
• Original Assignee: TransVoyant Inc.
• Inventors: Bloomquist, Kirk Elliot, Park, Christopher, Groseclose, Dennis William
• Granted Patent: US 9,424,521 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/02 Knowledge representation; Symbolic representation
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06Q 10/06375 Prediction of business process outcome or impact based on a proposed change

Abstract

A computer-implemented system and method of analyzing spatial, temporal and contextual elements of data for predictive decision-making. The computer-implemented method includes receiving a first set of rules and receiving first data and second data including spatial, temporal and contextual elements. The computer-implemented method also includes identifying each rule of the first set for which the received first data and the received second data is a respective candidate. For the identified rules for which the received first data is a candidate, and for the identified rules for which the received second data is a candidate, the respective received first data and received second data is indexed by its temporal, spatial or contextual elements as a function of the identified rules. The computer-implemented method also includes identifying an event as satisfying an identified rule in memory using the indexed first and second data.

Claims

1. A computer-implemented method for predictive decision-making, comprising:

receiving a first set of rules;

receiving first data comprising spatial, temporal and contextual elements;

identifying each rule of the first set for which the received first data is a candidate;

for the identified rules for which the received first data is a candidate, indexing the received first data in memory by its temporal, spatial or contextual elements as a function of said identified rules;

receiving second data comprising spatial, temporal and contextual elements;

identifying each rule of the first set for which the received second data is a candidate;

for the identified rules for which the received second data is a candidate, indexing the received second data in memory by its temporal, spatial or contextual elements as a function of said identified rules; and

identifying an event as satisfying an identified rule in memory using the indexed first and second data.

2. The method of claim 1, further comprising:

dynamically creating one or more spatial, temporal or contextual data structures in memory as a function of the identified rules for which the received first data or the received second data is a candidate;

and wherein the step of indexing comprises placing the respective spatial, temporal or contextual elements of the received first data or the received second data in an appropriate dynamically created data structure as a function of the identified rules.

3. The method of claim 1, further comprising:

disregarding the received first data and received second data that is not a candidate for any rule of the first set of rules.

4. The method of claim 1, further comprising:

indexing the event in memory by its temporal, spatial or contextual elements.

5. The method of claim 4, further comprising:

evaluating the indexed event in memory to determine whether one or more rules are satisfied.

6. The method of claim 1, further comprising:

storing the event in persistent storage.

7. The method of claim 1, further comprising:

evaluating the indexed first and second data in memory to determine whether one or more identified rules are satisfied.

8. The method of claim 1, further comprising:

creating a data structure in memory for each rule of the first set of rules; and

identifying whether received first data or received second data is a candidate for one or more rules of the first set using the created data structures.

9. The method of claim 1, further comprising:

creating a relationship between one or more respective spatial, temporal or contextual elements of said indexed first data and said indexed second data.

10. The method of claim 9, further comprising:

storing the created relationship in memory.

11. The method of claim 10, further comprising:

providing a rule suggestion based on the created relationship.

12. The method of claim 1, further comprising:

receiving static data associated with said first set of rules, wherein said spatial or contextual elements are related to said static data.

13. The method of claim 1, further comprising:

storing a plurality of received first data and received second data that is a candidate for one or more rules of the first set of rules in persistent storage;

retrieving the stored plurality of data;

indexing the retrieved data in memory by its temporal, spatial or contextual elements as a function of the identified rules for which the retrieved data is a candidate; and

identifying an event as satisfying one or more rules of the first set of rules using the indexed retrieved data.

14. The method of claim 13, further comprising:

providing a rule suggestion based on the identified event.

15. The method of claim 1, further comprising:

providing an indication that the identified rule is satisfied.

19. The method of claim 1, wherein each rule of the first set of rules comprises a respective field associated with a respective one of a spatial, temporal or contextual element and wherein the method further comprises determining whether the received first data is a candidate using said one or more fields.

20. The method of claim 1, further comprising:

providing a rule suggestion based on the identified event.

21. The method of claim 1, wherein the step of receiving the first data comprises:

receiving the first data from one or more sensors and one or more static data sources, and wherein each of the one or more sensors provide a real-time information feed for a dynamic source.

22. The method of claim 1, further comprising:

identifying an anomaly in the received first data or the received second data; and

correcting the anomaly prior to identifying each rule of the first set for which the received first data or the received second data is a candidate.

16. The method of claim 16, wherein the step of providing an indication comprises one or more of the following steps:

displaying a recommended action sequence based on the identified rule;

displaying a result based on the identified rule;

changing a display based on the identified rule;

providing an alert based on the identified rule; and

transmitting a notification message based on the identified rule.

17. The method of claim 16, wherein the recommended action sequence is selected from the group consisting of:

collecting additional data having one or more spatial, temporal and contextual elements, queuing a data sensor, evaluating additional indexed data having one or more spatial, temporal and contextual elements, evaluating indexed data as a function of a suggested rule, evaluating indexed events, deploying an asset, rescheduling an asset, tipping a data sensor, transmitting a message, initiating a new data stream, changing a display and combinations thereof.

18. The method of claim 16, wherein the notification message is selected from the group consisting of:

an electronic mail message, a telephone call, an alphanumeric page, a numeric page, a text message, a short messaging service message, a video message, a voice message, a tipping message, a queuing message, and combinations thereof.

23. A computer-implemented method for predictive decision-making, comprising:

receiving a request for a new rule defining a relationship between spatial, temporal and contextual elements;

identifying an existing rule having a defined relationship between spatial, temporal and contextual elements; and

recommending a modification to said new rule request based on the identified existing rule.

24. The method of claim 23, further comprising:

receiving a modification to the new rule request based on the recommendation; and

creating a new rule based on the modified new rule request.

25. The method of claim 24, further comprising:

creating a data structure for the new rule in memory.

26. The method of claim 24, wherein the new rule comprises one or more fields associated with spatial, temporal or contextual elements.

27. The method of claim 23, wherein the modification comprises one or more additional fields.

28. The method of claim 24, wherein the new rule comprises one or more fields and values associated with the one or more fields, and wherein the modification comprises a modified value associated with the one or more fields.

29. A system for predictive decision-making, comprising:

a plurality of predictive service cores configured to provide processing, distributed working memory, and a plurality of distributed nodes in a network in a cloud of a cloud computing environment;

a user interface module configured to provide a plurality of portals and a plurality of service catalogs for respective users of the cloud;

a rules manager configured to receive a first set of rules for a respective user and define a respective distributed data structure in memory for determining whether data is a candidate for each respective rule of the first set of rules;

one or more data modules configured to receive data comprising spatial, temporal and contextual elements;

a rules/decision engine module configured to identify each rule of the first set for which the received data is a candidate, index the received data in memory by its spatial, temporal and contextual elements as a function of the identified rules, and identify events as satisfying identified rules in memory using the indexed data; and

wherein the distributed working memory comprises a plurality of in memory distributed data structures to place the indexed received data.

30. The system of claim 29, wherein the rules/decision engine module is further configured to disregard received data that is determined not to be a candidate for any rule of the first set of rules.

31. The system of claim 29, further comprising:

a forensics module configured to receive a plurality of data comprising spatial, temporal and contextual elements that is a candidate for one or more rules of the first set of rules for a predetermined period of time, store said plurality of data in persistent storage and provide said plurality of data to the rules/decision engine module; and

wherein the rules/decision engine module is further configured to index the plurality of data in memory by its temporal, spatial or contextual elements as a function of the identified rules for which the plurality of data is a candidate.

32. The system of claim 29, further comprising:

a communications interface module in communication with the rules/decision engine module and configured to provide an indication that one or more rules of the first set of rules is satisfied.

33. The system of claim 29, wherein the rules/decision engine module is further configured to provide a rule suggestion based on an identified event.