- Number
- 12307203
- Published
- 2025-05-20
- Filed
- 2019-09-17
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Goslin; Michael P. et al.
- CPC
- A63F13/822; G06F18/2178; G06F18/285; G06F40/279; G06F40/35; G06N20/00; G06N5/043
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
AI-based interactive roleplaying/character-experience technique.
Abstract
Embodiments provide interactive artificial intelligence. Input to an artificial intelligence (AI) system is received, where the AI system comprises a plurality of machine learning (ML) models. A context of the input is determined, where the context indicates a role-playing scenario. A first ML model of the plurality of ML models is then selected based on the determined context, where the first ML model was trained based at least in part on the role-playing scenario. Output is generated by processing the input using the first ML model. The output is then returned.
Background
BACKGROUND (1) The present disclosure generally relates to interactivity through machine learning, and more specifically, to interactive artificial intelligence systems using machine learning models. (2) Conversational agents, such as chat bots, can provide rudimentary responses to users, but typically rely on limited decision-trees with restricted scripts. Further, existing chat agents have limited scope and topics of discussion. For example, a help desk bot may respond well to IT requests, but is useless for questions about commercial products. Similarly, a bot cannot be used to respond to generic requests without sacrificing the specificity required to engage in useful discussions that are more narrowly-focused. Moreover, existing chat agents fail to provide immersive interactivity, as their limited responses and narrow scope of useful discussion are severely limiting. SUMMARY (3) According to one embodiment of the present disclosure, a method is provided. The method includes receiving a first input to an artificial intelligence (AI) system, wherein the AI system comprises a plurality of machine learning (ML) models. The method further includes determining a first context of the first input, wherein the first context indicates a first role-playing scenario. Additionally, the method includes selecting a first ML model of the plurality of ML models based on the determined first context, wherein the first ML model was trained based at least in part on the first role-playing s
Claims
1. A method comprising: receiving a first input to an artificial intelligence (AI) system, wherein the AI system comprises a plurality of machine learning (ML) models, and wherein the first input comprises natural language; determining a first context of the first input, wherein the first context indicates a first role-playing scenario; selecting a first ML model of the plurality of ML models based on the determined first context and a set of context-specific weights associated with the first ML model, wherein the first ML model was trained based at least in part on training data corresponding to a natural language interaction relating to the first role-playing scenario; generating a first output by processing the first input using the first ML model, wherein the first output comprises natural language; returning the first output; and refining, based on feedback for the first output, at least one of (i) one or more internal weights of the first ML model, or (ii) one or more of the set of context-specific weights associated with the first ML model. ||
8. A non-transitory computer-readable medium containing computer program code that, when executed by operation of one or more computer processors, performs an operation comprising: receiving a first input to an artificial intelligence (AI) system, wherein the AI system comprises a plurality of machine learning (ML) models, and wherein the first input comprises natural language; determining a first context of the first input, wherein the first context indicates a first role-playing scenario; selecting a first ML model of the plurality of ML models based on the determined first context and a set of context-specific weights associated with the first ML model, wherein the first ML model was trained based at least in part on training data corresponding to a natural language interaction relating to the first role-playing scenario; generating a first output by processing the first input using the first ML model, wherein the first output comprises natural language; and returning the first output; and refining, based on feedback for the first output, at least one of (i) one or more internal weights of the first ML model, or (ii) one or more of the set of context-specific weights associated with the first ML model. ||
15. 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: receiving a first input to an artificial intelligence (AI) system, wherein the AI system comprises a plurality of machine learning (ML) models, and wherein the first input comprises natural language; determining a first context of the first input, wherein the first context indicates a first role-playing scenario; selecting a first ML model of the plurality of ML models based on the determined first context and a set of context-specific weights associated with the first ML model, wherein the first ML model was trained based at least in part on training data corresponding to a natural language interaction relating to the first role-playing scenario; generating a first output by processing the first input using the first ML model, wherein the first output comprises natural language; and returning the first output; and refining, based on feedback for the first output, at least one of (i) one or more internal weights of the first ML model, or (ii) one or more of the set of context-specific weights associated with the first ML model.