# US 2018/0082193 A1 · Cognitive modeling apparatus for defuzzification of multiple qualitative signals into human-centric threat notifications

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2018/0082193 A1
- Document ID: US20180082193A1
- Status: Published application
- Kind: A1
- Application number: 15/707,892
- Filed: 2017-09-18
- Published: 2018-03-22
- Earliest claimed: 2016-09-21
- Assignees: Scianta Analytics, LLC
- Applicants: Scianta Analytics, LLC
- Inventors: Michael E. Cormier; Earl D. Cox; William E. Thackrey; Joseph McGlynn; Harry Gardner
- Web page: https://patentgrep.com/patent/US20180082193A1

## CPC

- G06N 20/00: Machine learning
- G06F 11/0754: {by exceeding limits}
- G06F 11/3447: {Performance evaluation by modeling}
- G06F 16/2365: {Ensuring data consistency and integrity}
- G06F 16/27: Replication, distribution or synchronisation of data between databases or within a distributed database system; Distributed database system architectures therefor
- G06N 3/043: based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
- G06N 5/02: Knowledge representation; Symbolic representation
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 5/025: Extracting rules from data
- G06N 5/043: Distributed expert systems; Blackboards
- G06N 5/048: Fuzzy inferencing
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 7/02: using fuzzy logic (computing arrangements based on biological models G06N3/00; computing arrangements using knowledge-based models G06N5/00)
- G06N 7/046: {Implementation by means of a neural network (neural networks using fuzzy logic G06N3/043)}
- G05B 17/02: electric
- G06F 17/15: Correlation function computation {including computation of convolution operations (arithmetic circuits for sum of products per se, e.g. multiply-accumulators G06F7/5443; digital filters, e.g. FIR, IIR, adaptive filters H03H17/00)}
- G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)}
- G06F 18/2411: based on the proximity to a decision surface, e.g. support vector machines
- G06F 18/2433: Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
- G06F 2201/81: Threshold
- G06N 3/126: Evolutionary algorithms, e.g. genetic algorithms or genetic programming
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G05B: CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS (systems for controlling or regulating non-electric variables G05D; systems for regulating electric or magnetic variables G05F; control devices or systems insofar as characterised by mechanical features only G05G)

## Abstract

The present design is directed to a system for defuzzification of multiple qualitative signals into human-centric threat notifications using cognitive computing techniques, including a series of periodic execution components configured to operate over full or partial sets of received data, and a plurality of event reception components configured to operate on each event in a stream relevant to a terrain and selectively provide information to the series of periodic execution components. The system detects and signals anomalies upon detecting behavior inconsistent with normal behavior.

## Claims

### Claim 1

A system for defuzzification of multiple qualitative signals into human-centric threat notifications using cognitive computing techniques, comprising:
a series of periodic execution components configured to operate over full or partial sets of received data; and
a plurality of event reception components configured to operate on each event in a stream relevant to a terrain and selectively provide information to the series of periodic execution components;
wherein the system detects and signals anomalies upon detecting behavior inconsistent with normal behavior.

### Claim 2 (depends on 1)

The system of claim 1, wherein an anomaly has properties including severity and degree of inconsistency from normal behavior represented by mathematical distance, wherein severity is a class of anomaly assigned by an analytical component that detected and measured the anomaly.

### Claim 3 (depends on 1)

The system of claim 1, wherein the system detects and signals hazards, wherein a hazard is an unperfected threat associated with an actor without regard to any related assets or the behavior of other actors.

### Claim 4 (depends on 3)

The system of claim 3, wherein a hazard represents risk to an enterprise based on cumulative multi-dimensional behaviors comprising anomalous states generated from thresholds, orders of operation, peer-to-peer similarity, and actor behavior change over time.

### Claim 5 (depends on 4)

The system of claim 4, wherein a hazard has two properties comprising severity of medium, elevated or high, derived from inherent terrain risks.

### Claim 6 (depends on 3)

The system of claim 3, wherein the system detects and signals threats, wherein a threat is a perfected threat that ties together actors with behaviors of other actors and assets used by all actors in a hazard collection.

### Claim 7 (depends on 5)

The system of claim 5, wherein:
threats develop a sequence of operations over a dynamic time-frame; and
threats are connected in a heterogeneous graph comprising nodes and edges, wherein nodes can be actors or assets and edges define the dynamic time-frame as well as the strength of their connection as a function of risk.

### Claim 8

A system, comprising:
a series of periodic execution components configured to operate over full or partial sets of received data;
a plurality of event reception components configured to operate on each event in a stream relevant to a terrain and selectively provide information to the series of periodic execution components; and
a signal manager configured to manage signals for one of the series of periodic execution components and the plurality of event reception components;
wherein the system performs defuzzification of multiple qualitative signals into human-centric threat notifications using cognitive computing techniques by detecting and signaling anomalies upon detecting behavior inconsistent with normal behavior.

### Claim 9 (depends on 8)

The system of claim 8, wherein an anomaly has properties including severity and degree of inconsistency from normal behavior represented by mathematical distance, wherein severity is a class of anomaly assigned by an analytical component that detected and measured the anomaly.

### Claim 10 (depends on 8)

The system of claim 8, wherein the system detects and signals hazards, wherein a hazard is an unperfected threat associated with an actor without regard to any related assets or the behavior of other actors.

### Claim 11 (depends on 10)

The system of claim 10, wherein a hazard represents risk to an enterprise based on cumulative multi-dimensional behaviors comprising anomalous states generated from thresholds, orders of operation, peer-to-peer similarity, and actor behavior change over time.

### Claim 12 (depends on 11)

The system of claim 11, wherein a hazard has two properties comprising severity of medium, elevated or high, derived from inherent terrain risks.

### Claim 13 (depends on 10)

The system of claim 10, wherein the system detects and signals threats, wherein a threat is a perfected threat that ties together actors with behaviors of other actors and assets used by all actors in a hazard collection.

### Claim 14 (depends on 12)

The system of claim 12, wherein:
threats develop a sequence of operations over a dynamic time-frame; and
threats are connected in a heterogeneous graph comprising nodes and edges, wherein nodes can be actors or assets and edges define the dynamic time-frame as well as the strength of their connection as a function of risk.

### Claim 15

A system, comprising:
a series of periodic execution components configured to operate over full or partial sets of received data;
a plurality of event reception components configured to operate on each event in a stream relevant to a terrain and selectively provide information to the series of periodic execution components; and
a threat detector configured to detect threats based on information provided by the series of periodic execution components and the plurality of event reception components;
wherein the system performs defuzzification of multiple qualitative signals into human-centric threat notifications using cognitive computing techniques by detecting and signaling anomalies upon detecting behavior inconsistent with normal behavior.

### Claim 16 (depends on 15)

The system of claim 15, wherein an anomaly has properties including severity and degree of inconsistency from normal behavior represented by mathematical distance, wherein severity is a class of anomaly assigned by an analytical component that detected and measured the anomaly.

### Claim 17 (depends on 15)

The system of claim 15, wherein the system detects and signals hazards, wherein a hazard is an unperfected threat associated with an actor without regard to any related assets or the behavior of other actors.

### Claim 18 (depends on 17)

The system of claim 17, wherein a hazard represents risk to an enterprise based on cumulative multi-dimensional behaviors comprising anomalous states generated from thresholds, orders of operation, peer-to-peer similarity, and actor behavior change over time.

### Claim 19 (depends on 18)

The system of claim 18, wherein a hazard has two properties comprising severity of medium, elevated or high, derived from inherent terrain risks.

### Claim 20 (depends on 17)

The system of claim 17, wherein the threat detector operates with the series of periodic execution components and the plurality of event reception components to detect and signal threats, wherein a threat is a perfected threat that ties together actors with behaviors of other actors and assets used by all actors in a hazard collection.
