- Number
- 11256460
- Published
- 2022-02-22
- Filed
- 2019-02-05
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Goslin; Michael P., Nocon; Nathan D., Panec; Timothy M., Hsu; Jonathan R D, Rosenthal; Janice K.
- CPC
- G06F9/453; G06F1/1605; G06F40/30; G02B30/54; G06F3/14; G06F3/011; G02B30/56; G06F3/167
- Verdict
- Low Hardware
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Physical companion-device hardware with integrated display.
Abstract
Techniques for improved interactive devices are provided. Input is received from a user, where the input includes a first request. The input is evaluated using one or more natural language processing techniques to determine a context of the input, and a response to the input is generated based at least in part on the determined context. A first virtual character of a plurality of virtual characters is selected based at least in part on the determined context. The first virtual character is displayed on a rotating display, and the generated response is implemented while the first virtual character is being displayed.
Background
BACKGROUND (1) Embodiments presented in this disclosure generally relate to interactive devices. More specifically, embodiments disclosed herein relate to companion devices configured to enable a cohesive and immersive user experience. (2) The Internet of Things (IoT) has expanded dramatically in recent years. Generally, the IoT refers to a network of physical devices (often referred to as IoT devices or smart devices) with computing capability included in them. For example, smart devices have become increasingly common in modern households. These smart devices can often be activated and deactivated wirelessly, for example from a mobile phone or other device. Smart devices frequently serve utilitarian roles in modern houses. For example, smart locks can automatically lock your doors when you leave the house, intelligent thermostats can adjust the temperature when you are gone, and smart lights can turn on your lights when you return home. (3) Smart assistants have also increased in popularity recently. These virtual assistants serve similar utilitarian functions, such as checking local weather. Some virtual assistants can also interface with one or more smart devices, such that the virtual assistant can control the smart device at the behest of the user. Given the ever-increasing number of smart devices that play a part in our daily lives, there is a need for a unified system that integrates the disparate capabilities of each device into a cohesive and immersive experience fo
Claims
1. A method comprising: establishing a connection between a first device and a second device; receiving, by the first device, a first input from a user, wherein the first input includes a first request to output multimedia belonging to a first franchise; evaluating the first input using one or more natural language processing (NLP) techniques to determine a context of the first input; generating, by the first device, a response to the first input based at least in part on the determined context; selecting a first virtual character of a plurality of virtual characters based at least in part on the determined context, comprising: identifying one or more characters in one or more multimedia assets belonging to the first franchise; and determining that the first virtual character is a character in the requested multimedia; displaying the first virtual character on a rotating display of the first device; triggering the second device to output the requested multimedia; implementing the generated response while the first virtual character is being displayed; receiving metadata for the requested multimedia, wherein the metadata specifies a set of timestamps for a set of events in the requested multimedia; determining, based on a first timestamp of the set of timestamps, that a first event from the set of events will occur next in the requested multimedia; upon reaching the first timestamp in the requested multimedia, outputting, by the the first device, an indication of an available second response based on the first event; receiving, by the first device, a second input from the user, wherein the second input includes a second request in response to the indication of the available second response; and upon receiving the second request from the user, implementing, on the first device, the available second response, wherein the available second response comprises verbal commentary performed by the first virtual character about the first event at the first timestamp in the requested multimedia. ||
8. A system comprising: one or more computer processors; and a memory containing a program which when executed by the one or more computer processors performs an operation, the operation comprising: establishing a connection between a first device and a second device; receiving, by the first device, a first input from a user, wherein the first input includes a first request to output multimedia belonging to a first franchise; evaluating the first input using one or more natural language processing (NLP) techniques to determine a context of the first input; generating, by the first device, a response to the first input based at least in part on the determined context; selecting a first virtual character of a plurality of virtual characters based at least in part on the determined context, comprising: identifying one or more characters in one or more multimedia assets belonging to the first franchise; and determining that the first virtual character is a character in the requested multimedia; displaying the first virtual character on a rotating display of the first device; triggering the second device to output the requested multimedia; implementing the generated response while the first virtual character is being displayed; receiving metadata for the requested multimedia, wherein the metadata specifies a set of timestamps for a set of events in the requested multimedia; determining, based on a first timestamp of the set of timestamps, that a first event from the set of events will occur next in the requested multimedia; upon reaching the first timestamp in the requested multimedia, outputting, by the first device, an indication of an available second response based on the first event; receiving, by the first device, a second input from the user, wherein the second input includes a second request in response to the indication of the available second response; and upon receiving the second request from the user, implementing, on the first device, the available second response, wherein the available second response comprises verbal commentary performed by the first virtual character about the first event at the first timestamp in the requested multimedia. ||
15. A computer product comprising logic encoded in a non-transitory medium, the logic executable by operation of one or more computer processors to perform an operation comprising: establishing a connection between a first device and a second device; receiving, by the first device, a first input from a user, wherein the first input includes a first request to output multimedia belonging to a first franchise; evaluating the first input using one or more natural language processing (NLP) techniques to determine a context of the first input; generating, by the first device, a response to the first input based at least in part on the determined context; identifying one or more characters in one or more multimedia assets belonging to the first franchise; and determining that the first virtual character is a character in the requested multimedia; selecting a first virtual character of a plurality of virtual characters based at least in part on the determined context and based on determining that the first virtual character corresponds to a character from the multimedia; displaying the first virtual character on a rotating display of the first device; triggering the second device to output the requested multimedia; implementing the generated response while the first virtual character is being displayed; receiving metadata for the requested multimedia, wherein the metadata specifies a set of timestamps for a set of events in the requested multimedia; determining, based on a first timestamp of the set of timestamps, that a first event from the set of events will occur next in the requested multimedia; upon reaching the first timestamp in the requested multimedia, outputting, by the first device, an indication of an available second response based on the first event; receiving, by the first device, a second input from the user, wherein the second input includes a second request in response to the indication of the available second response; and upon receiving the second request from the user, implementing, on the first device, the available second response, wherein the available second response comprises verbal commentary performed by the first virtual character about the first event at the first timestamp in the requested multimedia.