Predictive analytics and device tracking to facilitate minimization of alert events

Patent metadata

Field	Value
Publication number	US-10637720-B2
Application number	US-201715445009-A
Country	US
Kind code	B2
Filing date	Feb 28, 2017
Priority date	Feb 28, 2017
Publication date	Apr 28, 2020
Grant date	Apr 28, 2020

Abstract

Techniques for autonomously tracking and/or predicting an alert event are provided. In one example, a system can comprise a memory that stores computer executable components. The system can also comprise a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory. The computer executable components can comprise a schedule component that determines plan information for a hub of a plurality of hubs, and the hub can be coupled to a device. The computer executable components can further comprise a tracking component that identifies a deviation from the plan information by the hub. Additionally, the computer executable components can comprise a prediction component that determines a probability that the deviation will result in an alert event.

First claim

What is claimed is:

1. A system, comprising:
a memory that stores computer executable components;
a processor, operably coupled to the memory, and that executes the computer executable components stored in the memory, wherein the computer executable components comprise:
a schedule component that determines plan information for a hub of a plurality of hubs, wherein the hub is communicatively coupled to a device;
a tracking component that identifies a deviation from the plan information by the hub;
a prediction component that determines a probability value that indicates that the deviation will result in an alert event; and
an alert component that:
generates and sends, via direct electrical connection or via one or more networks, an alert signal to a second entity based on the probability value indicating that the deviation will result in the alert event being equal to or greater than a defined threshold, wherein the alert signal causes notification to be generated at the hub, wherein the notification comprises a first entity location, wherein a first entity is likely to be affected by the deviation, the device is a mobile device worn by or associated with the first entity, and the second entity is distinct from but associated with the first entity, wherein the first entity is a dependent of the second entity, wherein the second entity is a caretaker of the first entity; and
generates and sends, via direct electrical connection or via one or more networks, a second alert signal to a third entity based on a determination that the first entity is within a defined proximity of the third entity and based on the probability value indicating that the deviation will result in the alert event being equal to or greater than a defined threshold, the third entity being another caregiver of the first entity.

2. The system of claim 1 , wherein the plan information comprises a parameter selected from a group consisting of an event, a location, a date, and a time, and wherein the determining the plan information comprises employing a word embedding technique to identify and extract information from a scheduling application associated with the second entity.

3. The system of claim 1 , wherein identification of the deviation from the plan information comprises a tracking of a location of the hub and comparing the location to the plan information.

4. The system of claim 1 , wherein the alert event comprises disconnection of the device from the hub and failure of the device to connect to a second hub from the plurality of hubs.

5. The system of claim 1 , further comprising:
a reception component that receives information from a second hub of the plurality of hubs, wherein the information is generated employing blockchain technology and is indicative of a monitored status of the device.

6. The system of claim 5 , wherein the monitored status is selected from a group consisting of a location of the device and an active wireless communication connection of the device.

7. The system of claim 5 , wherein the computer executable components further comprise:
a status component that determines whether the device has disconnected from the hub and whether the device has connected to the second hub.

8. The system of claim 5 , wherein the information is verified by a first signature from the hub and a second signature from the second hub.

9. The system of claim 1 , wherein the notification is a digital image.

10. The system of claim 9 , wherein the alert signal further causes the notification to be generated at the hub repeatedly until a confirmation receipt is received by the system from the hub.

11. The system of claim 1 , wherein software is provided as a service in a cloud environment to track a location of the hub.

12. The system of claim 1 , further comprising:
an extraction component that extracts a social action from an information corpus, wherein the schedule component determines the plan information based on the social action.

13. The system of claim 12 , wherein the information corpus is selected from a group consisting of a text message and a website on the Internet.

14. The system of claim 12 , wherein the information corpus comprises a social media post and the social action comprises an event the second entity plans to attend, a place the second entity plans to visit or an errand the second entity plans to perform, and wherein the social action is determined based on evaluation of content of the social media post.

15. The system of claim 1 , wherein the hub is selected from a group consisting of a smartphone, a personal computer and a tablet, and wherein the device is selected from a group consisting of a smartphone, a wearable device, smart eyewear and a smart watch.

16. The system of claim 1 , wherein the alert event is equal to or greater than the defined threshold based on a determination that the device is more than a defined distance from the hub.

17. The system of claim 1 , wherein the determination of plan information comprises:
identification of a text message from the second entity;
determination of a name in the text message is a name of the first entity based on comparison of the name with an authorized caregivers database; and
extraction of the text message and updating the schedule information with content of the text message, wherein the identification, the determination of the name and the extraction is performed employing word embedding techniques or natural language techniques.

18. A non-transitory computer program product for tracking an alert event, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
determine a schedule information for a hub of a plurality of hubs, wherein the hub is communicatively coupled to a plurality of devices;
identify a deviation from the schedule information by the hub;
determine a probability value that indicates that the deviation will result in an alert event; and
generate and send, via direct electrical connection or via one or more networks, to a second hub identified in a caregiver database, an alert signal to a second entity based on the probability value indicating that the deviation will result in the alert event being equal to or greater than a defined threshold, wherein the alert signal causes notification to be generated at the hub and the second hub and wherein the alert signal is sent to the second hub based on a determination that no response was received from the alert signal being sent to the hub, wherein the notification comprises a first entity location, wherein a first entity is likely to be affected by the deviation, the device is a mobile device worn by or associated with the first entity, and a second entity is distinct from but associated with the first entity, wherein the first entity is a dependent of the second entity, wherein the second entity is a caretaker of the first entity; and
generate and send, via direct electrical connection or via one or more networks, a second alert signal to a third entity based on a determination that the first entity is within a defined proximity of the third entity and based on the probability value indicating that the deviation will result in the alert event being equal to or greater than a defined threshold, the third entity being another caregiver of the first entity.

19. The non-transitory computer program product of claim 18 , wherein the program instructions further cause the proc

Assignees

• IBM

Inventors

• Bar-Joshua Michael
• Goldberg Itzhack
• Monge Núñez Roxana
• Vukovic Maja

Classifications

• H04L41/0686 Primary

  Additional information in the notification, e.g. enhancement of specific meta-data · CPC title

• H04L41/0681

  Configuration of triggering conditions · CPC title

• H04L41/12

  Discovery or management of network topologies · CPC title

• H04L41/147

  for predicting network behaviour · CPC title