# US 2019/0356712 A1 · Intelligent and near real-time monitoring in a streaming environment

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

- Number: US 2019/0356712 A1
- Document ID: US20190356712A1
- Status: Published application
- Kind: A1
- Application number: 16/525,901
- Filed: 2019-07-30
- Published: 2019-11-21
- Earliest claimed: 2016-12-23
- Assignees: Cerner Innovation, Inc.
- Applicants: Cerner Innovation, Inc.
- Inventors: Elizabeth Fay Osborne; Scott Gordon Siebers; Chad G. Hays; Jason Andrew Komarek; Todd Bechtel
- Web page: https://patentgrep.com/patent/US20190356712A1

## CPC

- H04L 65/61: for supporting one-way streaming services, e.g. Internet radio
- G06N 5/046: Forward inferencing; Production systems
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- H04L 65/1083: In-session procedures
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present invention is directed to intelligent and near real-time monitoring in a streaming environment. In embodiments, a streaming platform streams raw data from raw data capture devices, where the raw data is contextually enriched using multiple information sources. A rule execution operator, integrated within the streaming platform, detects events by executing rules against the contextually enriched data. The rules applied are customizable, flexible, multivariate, and dynamically responsive to changing information. When an event is detected, an action can be instantiated in response to the event detection and/or newly derived information. The action and/or instructions for performing the action are communicated to external sources, where the action can be initiated and/or completed. Accordingly, actions are instantiated in near real time relative to the initial receipt of raw data from which the events were detected. Actions may be delayed using sophisticated temporal reasoning, in some embodiments.

## Claims

### Claim 1

One or more non-transitory computer-readable storage media having computer-executable instructions embodied thereon that, when executed by one or more processors, perform a method, the method comprising:
detecting, in near real-time, an event based on execution of a rule against an enriched data stream;
based on the event that was detected, identifying a defined period of time;
based on a lapse of the defined period of time, determining whether to instantiate the event that is detected;
when it is determined to instantiate the event, instantiating the event; and
communicating a notification of the event in response to instantiating the event that is detected.

### Claim 2 (depends on 1)

The method of claim 1 wherein the notification prompts a user to perform an action, wherein the action is a specific patient care task that is responsive to the event.

### Claim 3 (depends on 1)

The method of claim 1 wherein the notification instructs a device to perform an action, wherein the action is streaming physiologic patient data to a streaming platform having an integrated rule execution operator.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
storing an indication of the event that is detected in an entity-specific record stored in cache memory; and
purging the cache memory of the entity-specific record based on the lapse of a session.

### Claim 5 (depends on 1)

The method of claim 1 wherein the notification of the event instructs a mobile device to perform an action, wherein the action is issuing an alert of the event that was instantiated.

### Claim 6 (depends on 1)

The method of claim 1 wherein, based on the lapse of the defined period of time, determining to instantiate the event that was detected.

### Claim 7 (depends on 1)

The method of claim 1 wherein, based on the lapse of the defined period of time, determining not to instantiate the event that was detected.

### Claim 8 (depends on 1)

The method of claim 1 wherein, based on instantiating the event that was detected, instantiating one or more actions.

### Claim 9

A computerized method comprising:
detecting, in near real-time, a plurality of events based on execution of a rule against an enriched data stream;
based on the plurality of events that are detected, identifying a defined period of time;
based on a lapse of the defined period of time, determining whether to instantiate the plurality of events that are detected;
when it is determined to instantiate the plurality of events that are detected, instantiating the plurality of events; and
communicating a notification of the plurality of events in response to instantiating the plurality of events.

### Claim 10 (depends on 9)

The method of claim 9 wherein the defined period of time is specific to a particular combination of events in the plurality of events that are detected.

### Claim 11 (depends on 9)

The method of claim 9 wherein the defined period of time is based on one or more of a rule type or a quantity of the plurality of events.

### Claim 12 (depends on 9)

The method of claim 9 wherein it is determined to instantiate the plurality of events when at least one additional event is detected in near real-time in the enriched data stream prior to the lapse of the defined period of time.

### Claim 13 (depends on 9)

The method of claim 9 wherein it is determined not to instantiate the plurality of events when at least one additional event is detected in near real-time in the enriched data stream prior to the lapse of the defined period of time.

### Claim 14 (depends on 9)

The method of claim 9 wherein it determined to instantiate the plurality of events when one or more data items are received prior to the lapse of the defined period of time.

### Claim 15 (depends on 9)

The method of claim 9 wherein it determined to not instantiate the plurality of events when one or more data items are not received prior to the lapse of the defined period of time.

### Claim 16 (depends on 9)

The method of claim 9 further comprising instantiating an action in response to instantiating the action.

### Claim 17 (depends on 9)

The method of claim 9 further comprising, based on detecting at least one of the plurality of events, activating a different rule that was previously dormant, wherein the different rule as activated is executed against the enriched data stream in near real-time to detect an additional event.

### Claim 18 (depends on 9)

The method of claim 9 further comprising, based on detecting at least one of the plurality of events, de-activating a different rule that was previously active, wherein the different rule as de-activated is blocked from execution against the enriched data stream.

### Claim 19 (depends on 9)

The method of claim 9 further comprising instantiating one or more actions in response to instantiating the plurality of events.

### Claim 20

A system comprising:
a streaming platform that comprises a rule execution operator, the streaming platform configured to:
detect, in near real-time, a plurality of events based on execution of a rule against an enriched data stream;
based on the plurality of events that are detected, identify a defined period of time for the plurality of events;
based on a lapse of the defined period of time, determine whether to instantiate the plurality of events that are detected;
when it is determined to instantiate the plurality of events, instantiate the plurality of events; and
communicate a notification of instantiation of the plurality of events in response to instantiating the plurality of events that are detected.
