COMPUTER-IMPLEMENTED SYSTEMS AND METHODS OF ANALYZING DATA IN AN AD-HOC NETWORK FOR PREDICTIVE DECISION-MAKING

• US 20160337441A1
• Filed: 05/16/2014
• Published: 11/17/2016
• Est. Priority Date: 09/27/2013
• Status: Active Grant

• Current Assignee: TransVoyant Inc.
• Original Assignee: TransVoyant LLC
• Inventors: Bloomquist, Kirk Elliot, Groseclose, Dennis William
• Granted Patent: US 10,091,276 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G08B 31/00 Predictive alarm systems characterised by extrapolation or other computation using updated historic data
• CPC Class Codes: H04L 67/5651 Reducing the amount or size of exchanged application data
• CPC Class Codes: H04W 4/02 Services making use of location information
• CPC Class Codes: H04W 4/029 Location-based management or tracking services
• CPC Class Codes: H04W 84/18 Self-organising networks, e.g. ad-hoc networks or sensor networks

Abstract

A computer-implemented system and method of predictive decision-making in an ad hoc network. The computer-implemented method includes receiving a set of rules into the ad hoc network and identifying a data set for each rule. The computer-implemented method also includes selecting a first and second node from the ad hoc network to process a first and second rule as a function of the identified data set according to an optimizing algorithm. The computer-implemented method also selects a third node to receive the processed results from the first and second nodes. An indication is provided of the processed results by the third node.

Claims

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

receiving a set of rules into an ad-hoc network having distributed nodes, wherein each distributed node is capable of processing data as a function of one or more rules in the set of rules;

identifying a respective data set including data that is a respective potential candidate for each rule of the received set of rules;

selecting a first node from the distributed nodes configured to identify candidate data and disregard non-candidate data received by the first node for a first rule of the received set of rules as a function of the identified respective data set for the first rule;

selecting a second node from the distributed nodes configured to identify candidate data, and disregard non-candidate data, received by the second node for a second rule of the received set of rules as a function of the identified respective data set for the second rule;

selecting a third node from the distributed nodes configured to receive identified candidate data from each of the first and second nodes and to index the received candidate data in memory by its spatial, temporal, or contextual elements as a function of the received set of rules;

receiving identified candidate data from each of the first and second nodes at the third node;

indexing the received candidate data in memory at the third node by its spatial, temporal, or contextual elements as a function of the received set of rules; and

providing an indication of the indexed candidate data at the third node.

2. The method of claim 1, wherein the first node is different from the second node and the third node is the same as the first or second node.

3. The method of claim 1, wherein the step of selecting the first node includes identifying a source of data in the respective identified data set for the first rule.

4. The method of claim 3, wherein the step of identifying a source of data includes identifying one or more of a dynamic data source, a location of the data, or an origin of the data.

5. The method of claim 1, wherein the step of selecting the first node includes using an optimizing algorithm.

6. The method of claim 5, wherein the optimizing algorithm minimizes the amount of candidate data transferred between distributed nodes of the ad hoc network.

7. The method of claim 5, wherein the optimizing algorithm minimizes the processing required by the distributed nodes to process spatial, temporal, or contextual elements of data as a function of the received set of rules.

8. The method of claim 5, wherein the optimizing algorithm selects the first node as a function of the availability of the first node.

9. The method of claim 1, wherein the first rule and the second rule are subrules of a third rule of the received set of rules;

wherein the method further comprises the third node identifying an event as satisfying the third rule using the indexed candidate data; and

wherein the step of providing an indication comprises providing an indication that the third rule is satisfied.

10. The method of claim 1, wherein the step of providing an indication comprises one or more of the following steps:

displaying the indexed candidate data at the third node;

providing an alert from the third node based on the indexed candidate data;

transmitting a notification message from the third node based on the indexed candidate data;

changing a display at the third node based on the indexed candidate data; and

displaying a recommended action sequence at the third node based on the indexed candidate data.

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

a set of rules;

a plurality of distributed nodes forming an ad hoc network, each of the plurality of nodes being capable of processing data as a function of one or more rules in the set of rules and of receiving data from a data source;

wherein the plurality of distributed nodes further comprises;

a first distributed node to identify candidate data, and disregard non-candidate date, received by the first node for a first rule;

a second distributed node to identify candidate data, and disregard non-candidate date, received by the first node for a second rule; and

a third distributed node to receive identified candidate data from each of the first and second nodes, and to index the received candidate data in memory by its spatial, temporal, or contextual elements as a function of the set of rules; and

a rules manager configured to identify a respective data set including data that is a respective potential candidate for each rule of the set of rules, to select the first and second nodes as a function of the respective identified data set for the first and second rules, and to select the third node as a function of the set of rules.

12. The system of claim 11, wherein the first node is different from the second node and the third node is the same as the first or second node.

13. The system of claim 11, wherein the rules manager is in a distributed node of the plurality of distributed nodes.

14. The system of claim 11, wherein the rules manager is distributed between two or more distributed nodes of the plurality of distributed nodes.

15. The system of claim 11, wherein the first rule and the second rule are subrules of a third rule of the set of rules, wherein the third distributed node is further to identify an event as satisfying the third rule using the indexed candidate data.

16. The system of claim 11, wherein the rules manager comprises an optimizing algorithm.

17. The system of claim 11, wherein the third distributed node further comprises at least one of a display, or an interface to provide an alert or notification message to another distributed node based on the indexed candidate data.

18. The system of claim 16, wherein the rules manager is configured to distribute respective rules of the set of rules to selected nodes of the plurality of distributed nodes using the optimizing algorithm.

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

receiving a set of rules into an ad-hoc network having a plurality of distributed nodes, where each distributed node is capable of processing data as a function of one or more rules in the received set of rules;

identifying a respective data set including data that is a respective potential candidate for each rule of the received set of rules;

using an optimizing algorithm to select two or more distributed nodes from the plurality of distributed nodes to each identify respective candidate data, and to disregard non-candidate data, received by the respective distributed node for a respective rule of the received set of rules and to select a third distributed node from the plurality of distributed nodes to receive identified candidate data from each of the two or more distributed nodes and to index the received candidate data in memory by its respective spatial, temporal, or contextual elements as a function of the received set of rules;

receiving the identified candidate data from each of the two or more distributed nodes at the third distributed node;

indexing the received candidate data in memory at the third distributed node by its respective spatial, temporal, or contextual elements as a function of the received set of rules; and

providing a rule suggestion based on the indexed candidate data.

20. The method of claim 19, wherein the third distributed node is a different distributed node from each of the two or more distributed nodes and wherein the method further comprises the third distributed node creating a relationship in memory between one or more respective spatial, temporal or contextual elements of the indexed candidate data received from the first distributed node and one or more respective spatial, temporal or contextual elements of the indexed candidate data received from the second distributed node.