Unified cognition for a virtual personal cognitive assistant when cognition is embodied across multiple embodied cognition object instances

Patent metadata

Field	Value
Publication number	US-11443196-B2
Application number	US-201715813113-A
Country	US
Kind code	B2
Filing date	Nov 14, 2017
Priority date	Nov 14, 2017
Publication date	Sep 13, 2022
Grant date	Sep 13, 2022

Abstract

Provided are techniques for unified cognition for a virtual personal cognitive assistant. A personal cognitive agent creates an association with an entity and a personalized embodied cognition manager that includes an object instance registry, wherein the object instance registry stores embodied cognition object instances. A cognitive assistant agent for a domain that is associated with the embodied cognition object instances stored in the object instance registry is provided. Input is received from the entity for a first object instance and for a second object instance of the embodied cognition object instances. Interaction is coordinated between the cognitive assistant agent, the first object instance, and the second object instance by: identifying a goal based on the input and providing the first object instance and the second object instance with instructions to meet the goal based on the input. A response is provided to the input with an indication of the goal.

First claim

What is claimed is:

1. A computer program product, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by at least one processor to perform operations comprising:
under control of a personal cognitive agent that comprises a plurality of goals,
providing a cognitive assistant agent for a domain that is associated with a plurality of embodied cognition object instances stored in an object instance registry; and
consolidating entity interactions of a particular cognitive capability of a plurality of cognitive capabilities across multiple embodied cognition object instances of the plurality of embodied cognition object instances and of multiple cognitive capabilities of the plurality of cognitive capabilities across the multiple embodied cognition object instances of the plurality of embodied cognition object instances for the cognitive assistant agent, wherein the plurality of embodied cognition object instances comprise a speaker, a smart phone, a robot, and a smart car, by:
receiving a first input at a first location and at a first time from an entity for a first object instance of the plurality of embodied cognition object instances, wherein the first input is received from a first Internet of Things (IoT) device;
receiving a second input at a second location and at a second time from the entity for a second object instance of the plurality of embodied cognition object instances, wherein the second object instance is different from the first object instance, and wherein the second input is received from a second IoT device;
coordinating interaction of the cognitive assistant agent, the first object instance, and the second object instance by:
identifying a goal of the plurality of goals based on the first input received from the first IoT device and the second input received from the second IoT device;
providing the first object instance with first instructions for the first IoT device to meet the goal, wherein the first object instance executes the first instructions; and
providing the second object instance with second instructions for the second IoT device to meet the goal, wherein the second object instance executes the second instructions; and

providing a response to the first input and the second input with an indication of the goal.

2. The computer program product of claim 1 , wherein the program code is executable by the at least one processor to perform operations comprising:
using a manifest file of the cognitive assistant agent to identify the plurality of embodied cognition object instances; and
downloading the plurality of embodied cognition object instances from the cognitive assistant agent to the object instance registry.

3. The computer program product of claim 2 , wherein the program code is executable by the at least one processor to perform operations comprising:
configuring cognitive capabilities for each of the plurality of embodied cognition object instances.

4. The computer program product of claim 1 , wherein the program code is executable by the at least one processor to perform operations comprising:
for each of the plurality of embodied cognition object instances,
loading a cognition kernel; and
downloading one or more cognitive modules into the cognition kernel.

5. The computer program product of claim 1 , wherein a Software as a Service (SaaS) is configured to perform the operations of the computer program product.

6. The computer program product of claim 1 , wherein the plurality of cognitive capabilities comprise speech, vision, location, and time.

7. A computer system, comprising:
one or more processors, one or more computer-readable memories and one or more computer-readable, tangible storage devices; and
program instructions, stored on at least one of the one or more computer-readable, tangible storage devices for execution by at least one of the one or more processors via at least one of the one or more computer-readable memories, to perform operations comprising:
under control of a personal cognitive agent that comprises a plurality of goals,
providing a cognitive assistant agent for a domain that is associated with a plurality of embodied cognition object instances stored in an object instance registry; and
consolidating entity interactions of a particular cognitive capability of a plurality of cognitive capabilities across multiple embodied cognition object instances of the plurality of embodied cognition object instances and of multiple cognitive capabilities of the plurality of cognitive capabilities across the multiple embodied cognition object instances of the plurality of embodied cognition object instances for the cognitive assistant agent, wherein the plurality of embodied cognition object instances comprise a speaker, a smart phone, a robot, and a smart car, by:
receiving a first input at a first location and at a first time from an entity for a first object instance of the plurality of embodied cognition object instances, wherein the first input is received from a first Internet of Things (IoT) device;
receiving a second input at a second location and at a second time from the entity for a second object instance of the plurality of embodied cognition object instances, wherein the second object instance is different from the first object instance, and wherein the second input is received from a second IoT device;
coordinating interaction of the cognitive assistant agent, the first object instance, and the second object instance by:
identifying a goal of the plurality of goals based on the first input received from the first IoT device and the second input received from the second IoT device;
providing the first object instance with first instructions for the first IoT device to meet the goal, wherein the first object instance executes the first instructions; and
providing the second object instance with second instructions for the second IoT device to meet the goal, wherein the second object instance executes the second instructions; and

providing a response to the first input and the second input with an indication of the goal.

8. The computer system of claim 7 , wherein the operations further comprise:
using a manifest file of the cognitive assistant agent to identify the plurality of embodied cognition object instances; and
downloading the plurality of embodied cognition object instances from the cognitive assistant agent to the object instance registry.

9. The computer system of claim 8 , wherein the operations further comprise:
configuring cognitive capabilities for each of the plurality of embodied cognition object instances.

10. The computer system of claim 7 , wherein the operations further comprise:
for each of the plurality of embodied cognition object instances,
loading a cognition kernel; and
downloading one or more cognitive modules into the cognition kernel.

11. The computer system of claim 7 , wherein a Software as a Service (SaaS) is configured to perform the operations of the computer system.

12. The computer system of claim 7 , wherein the plurality of cognitive capabilities comprise speech, vision, location, and time.

Assignees

• IBM

Inventors

• Ng Joanna W
• Booch Ernest Grady

Classifications

• G06F8/20 Primary

  Software design · CPC title

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title

• G06N5/02 Primary

  Knowledge representation; Symbolic representation · CPC title

• G06F9/453

  Help systems · CPC title

• G06F9/46

  Multiprogramming arrangements · CPC title