CONVERSATIONAL LANGUAGE AND INFORMATIONAL RESPONSE SYSTEMS AND METHODS

Number: 20190197106
Published: 2019-06-27
Filed: 2017-12-22
Assignee: Disney Enterprises, Inc.
Inventors: DOGGETT; ERIKA VARIS
CPC: G06F16/3329; G06F16/3344; G06F16/353; G06F40/205; G06F40/284; G06F40/30; G10L15/1815; G10L15/1822; G10L15/22
Verdict: Set aside conversational language/informational response systems, generic chatbot
Source: Google Patents · FreePatentsOnline

Abstract

Systems and methods for a computer-based, interactive communications system capable of generating a response to a human language input are provided. The computer-based, interactive communications systems includes a plurality of response models that may be selected to process one or more keywords extracted from the human language input. The plurality of response models may include at least one conversational response model and at least one informational response model, so that the computer-based, interactive communications system is able to respond to the human language input in a manner commensurate with the type of human language input it receives.

Background

TECHNICAL FIELD

The present disclosure relates generally to computer-based, interactive communications systems.DESCRIPTION OF THE RELATED ART

Computer-based communications, such as chatbots or similar interactive agents refer to computer programs that can conduct a conversation with a human counterpart. Such computer programs are designed to respond to textual and/or auditory (spoken) inputs in a way that attempts to convincingly simulate an actual human-to-human interaction. They may be used as virtual assistants, used on websites, used as part of instant messaging platforms, etc. Sometimes, these computer programs may be used for entertainment or research purposes. Sometimes, these computer programs may be used for promoting products and/or services.BRIEF SUMMARY OF THE DISCLOSURE

In accordance with one embodiment, a computer-implemented method comprises receiving a language input, parsing the language input into one or more token segments, and classifying the token segments according to a response model for suitably generating a response to the token segments. The computer-implemented method further comprises determining whether the classification is suitable, and processing the token segments through one or more response models upon a determination that the classification is suitable. Further still, the computer-implemented method comprises determining whether a proposed response generated by the one or more response models is suitable, and generating th

Claims

1. A computer-implemented method, comprising: receiving a language input; parsing the language input into one or more token segments; classifying the token segments according to a response model for suitably generating a response to the token segments; determining whether the classification is suitable; processing the token segments through one or more response models upon a determination that the classification is suitable; determining whether a proposed response generated by the one or more response models is suitable; and generating the proposed response upon a determination that the proposed response is suitable; wherein parsing the language input comprises correlating each of the one or more classification keywords with at least one of a plurality of response models, and wherein the at least one response model comprises at least one of a plurality of language generation models. | 14. An apparatus, comprising: a processor; and a memory unit operatively connection to the processor, the memory unit including computer code configured to cause the processor: receive a language input from a human user; parse the language input to determine one or more keywords; based on at least one of the one or more keywords, select at least one response model from a plurality of response models, wherein the at least one response model comprises at least one of a plurality of language generation models; process the one or more keywords through the selected response model; and generate a conversational response to received language input.