INTELLIGENT AND NEAR REAL-TIME MONITORING IN A STREAMING ENVIRONMENT

• US 20180183843A1
• Filed: 12/23/2016
• Published: 06/28/2018
• Est. Priority Date: 12/23/2016
• Status: Active Grant

• Current Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Original Assignee: Cerner Innovation, Inc. (Oracle Corporation)
• Inventors: OSBORNE, ELIZABETH FAY, SIEBERS, SCOTT GORDON, HAYS, CHAD G., KOMAREK, JASON ANDREW, BECHTEL, TODD
• Granted Patent: US 10,462,199 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: H04L 65/1083 In-session procedures
• CPC Class Codes: H04L 65/61 for supporting one-way streaming services, e.g. Internet radio

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

1. A computer-implemented method comprising:

when an event is detected based on execution of at least one rule against enriched streamed data, receiving a notification of the event detection; and

determining, in near real time, to instantiate one or more actions based on the notification and the event detected.

2. The method of claim 1, further comprising:

instantiating the one or more actions for communication to an end user device, wherein the one or more actions prompt an end user to perform a patient care task.

3. The method of claim 1, further comprising:

instantiating the one or more actions for communication to a raw data capture device, wherein the one or more actions instruct the raw data capture device to stream physiologic patient data to a streaming platform having an integrated rule execution operator.

4. The method of claim 1, further comprising:

storing an indication of the event detected and the notification in an entity-specific record stored in cache memory.

5. The method of claim 1, further comprising:

instantiating the one or more actions; and

communicating the one or more actions to at least one mobile user device for implementing at the mobile user device, wherein implementing the one or more actions results in an alert being issued by the mobile user device.

6. The method of claim 1, wherein determining to instantiate one or more actions based on the notification and the event detected includes determining to prevent instantiation of another action.

7. The method of claim 1, further comprising:

assigning a defined period of time to at least one of the one or more actions to be instantiated, wherein the defined period of time is based on the corresponding event detected; and

upon expiration of the defined period of time, purging the at least one action when the at least one action has not been instantiated.

8. The method of claim 7, further comprising:

assigning a defined period of time to at least one of the one or more actions to be instantiated, wherein the defined period of time is specified by a rule corresponding to the event detected;

instantiating the at least one event; and

upon expiration of the defined period of time, communicating the at least one action instantiated to an external source for implementation.

9. One or more non-transitory computer-readable storage media having computer-executable instructions embodied thereon that, when executed, perform a method for event-detection action instantiation in a complex event processing system, the media comprising:

one or more processors configured to;

when an event is detected based on execution of at least one rule against enriched streamed data of a streaming platform, receive a notification of the event detection;

determine, in near real time, to instantiate one or more actions based on the notification and the event detected; and

instantiate the one or more actions.

10. The computer-readable media of claim 9, wherein the one or more processors instantiate the one or more actions by instructing a raw data capture device to stream physiologic measurements encoded as raw data to the streaming platform.

11. The computer-readable media of claim 9, wherein the one or more processors instantiate the one or more actions by communicating an alert for issuance via a user device.

12. The computer-readable media of claim 9, wherein the one or more processors are configured to:

retrieve, from a digital information system, data for enrichment of streamed data via the streaming runtime, wherein the data retrieved for enrichment and the enriched streamed data against which the at least one rule was executed correspond to the one individual; and

communicate the data retrieved for enrichment to the streaming platform.

13. The computer-readable media of claim 9, wherein the one or more processors are configured to:

using the at least one rule executed against the enriched streamed data, update a record in a database by storing an indication of the event detected and the notification in the record, wherein the record is specific to an individual who corresponds to the enriched streamed data underlying the event detected.

14. The computer-readable media of claim 9, wherein the one or more processors instantiate the one or more actions by communicating, to a middleware component, instructions for performance of the one or more actions via one or more remote computing devices.

15. The computer-readable media of claim 9, wherein the one or more processors are configured to:

using the at least one rule executed against the enriched streamed data to detect the event, identify one or more actions responsive to the event detected.

16. The computer-readable media of claim 9, wherein the one or more processors are configured to:

using the at least one rule executed against the enriched streamed data to detect the event, identify one or more of a middleware component, a remote user device, an application, a database storing electronic records specific to individuals, or a raw data capture device, corresponding to at least one of the one or more actions instantiated; and

direct instructions for performance of the one or more actions to the one or more of a middleware component, a remote user device, an application, a database storing electronic records specific to individuals, or a raw data capture device identified, wherein the one or more of a middleware component, a remote user device, an application, a database storing electronic records specific to individuals, or a raw data capture device perform the one or more actions according to said instructions.

17. The computer-readable media of claim 9, wherein the instructions for performance of the one or more actions instruct a raw data capture device that is not currently streaming data to initiate capturing and encoding raw data for communication to the streaming platform.

18. The computer-readable media of claim 9, wherein the one or more processors are configured to:

using the at least one rule executed against the enriched streamed data to detect the event, identify one or more of a middleware component, a remote user device, an application, a database storing electronic records specific to individuals, or a raw data capture device, corresponding to the event detected; and

direct instructions for performance of the one or more actions to the one or more of a middleware component, a remote user device, an application, a database storing electronic records specific to individuals, or a raw data capture device identified, wherein the one or more of a middleware component, a remote user device, an application, a database storing electronic records specific to individuals, or a raw data capture device perform the one or more actions according to said instructions.

19. The computer-readable media of claim of claim 18, wherein the instructions for performance of the one or more actions instruct a raw data capture device that is currently streaming data to cease streaming data to the streaming platform.

20. A system comprising:

a middleware component communicatively coupled to a complex processing system, the middleware component configured to;

receive raw data in near real time from a plurality of raw data capture devices; and

communicate the raw data, in near real time, to a streaming platform having a rule execution operator integrated therein; and

one or more processors integrated within the middleware component, wherein the one or more processors are configured to;

when an event is detected based on execution of at least one rule against enriched streamed data of the streaming platform, receive a notification of the event detection;

determine, in near real time, to instantiate one or more actions based on the notification and the event detected; and

instantiate the one or more actions.