Back to results
US 10,950,355 B2Granted
Simulation method and system
AssigneeInternational Business Machines Corporation
InventorsKomminist Weldemariam, Maja Vukovic, Clifford A. Pickover
Life of this patent
Estimating the term…
Abstract
A computer device may identify an interaction device that is capable of outputting a simulation representative of an identified aspect of an entity. The computer device may trigger the identified interaction device to output a simulation of the identified aspect.
Claims20
A method for generating a simulacrum representative of an entity, the method comprising:
- training, by a computer device, a machine learning model using engagement data associated with historical interactions between a first entity and a plurality of entities;
- running, by the computer device, the trained machine learning model to derive classification data indicating at least one reaction of the first entity to a plurality of aspects of the plurality of entities;
- storing, by the computer device, the classification data in a database stored in a memory;
- determining, by the computer device, a current context associated with the first entity and a second entity, wherein the second entity is among the plurality of entities, and the current context indicates that the first entity and the second entity are separated;
- detecting, by the computer device, that the first entity is experiencing a behavior relating to the separation of the first entity and the second entity;
- in response to detecting that the first entity is experiencing the behavior, performing, by the computer device, a lookup function in the database stored in the memory to identify an aspect of the second entity corresponding to a particular reaction by the first entity;
- identifying, by the computer device, an interaction device that is capable of outputting a simulacrum representative of the identified aspect of the second entity;
- and
- triggering, by the computer device, the identified interaction device to output the identified simulacrum.
6 more elements
A system effective to generate a simulacrum representative of an entity, the system comprising:
- a memory configured to store a set of instructions;
- a processor configured to be in communication with the memory;
- at least one interaction device configured to be in communication with the processor;
- the processor being configured to execute the set of instructions to:
- train a machine learning model using engagement data associated with historical interactions between a first entity and a plurality of entities;
- run the trained machine learning model to derive classification data indicating at least one reaction of the first entity to a plurality of aspects of the plurality of entities;
- store the classification data in a database stored in the memory;
- determine a current context associated with the first entity and a second entity, wherein the second entity is among the plurality of entities, and the current context indicates that the first entity and second entity are separated;
- detect that the first entity is experiencing a behavior relating to the separation of the first entity and the second entity;
- in response to the detection that the first entity is experiencing the behavior, perform a lookup function in the database stored in the memory to identify an aspect of the second entity corresponding to a particular reaction by the first entity;
- identify an interaction device among the at least one interaction device, wherein the identified interaction device is capable of outputting a simulacrum representative of the identified aspect of the second entity;
- and
- trigger the identified interaction device to output the identified simulacrum.
10 more elements
A computer program product for generating a simulacrum representative of an entity, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processing element of a device to cause the device to:
- train a machine learning model using engagement data associated with historical interactions between a first entity and a plurality of entities;
- run the trained machine learning model to derive classification data indicating at least one reaction of the first entity to a plurality of aspects of the plurality of entities;
- store the classification data in a database stored in a memory;
- determine a current context associated with first entity and a second entity, wherein the second entity is among the plurality of entities, and the current context indicates that the first entity and second entity are separated;
- detect that the first entity is experiencing a behavior relating to the separation of the first entity and the second entity;
- in response to detecting that the first entity is experiencing the behavior, perform a lookup function in the database stored in the memory to identify an aspect of the second entity corresponding to a particular reaction by the first entity;
- identify an interaction device that is capable of outputting a simulacrum representative of the identified aspect of the second entity;
- and
- trigger the identified interaction device to output the identified simulacrum.
6 more elements
Dependencies are inferred from the claim text.