- Number
- 11455549
- Published
- 2022-09-27
- Filed
- 2016-12-08
- Assignee
- Disney Enterprises, Inc.
- Inventors
- Abrams; Michael, Haseltine; Eric
- CPC
- G06N5/04; G06N20/00; G06N3/006
- Verdict
- Low Notable software
- Source
- Google Patents · FreePatentsOnline
The keeper's note
Interactive character AI (character-as-a-service).
Abstract
In one embodiment, a character engine models a character that interacts with users. The character engine receives user input data from a user device, and analyzes the user input data to determine a user intent and an assessment domain. Subsequently, the character engine selects inference algorithm(s) that include machine learning capabilities based on the intent and the assessment domain. The character engine computes a response to the user input data based on the selected inference algorithm(s) and a set of personality characteristics that are associated with the character. Finally, the character engine causes the user device to output the response to the user. In this fashion, the character engine includes sensing functionality, thinking and learning functionality, and expressing functionality. By aggregating advanced sensing techniques, inference algorithms, character-specific personality characteristics, and expressing algorithms, the character engine provides a realistic illusion that users are interacting with the character.
Background
BACKGROUND OF THE INVENTION Field of the Invention (1) Embodiments of the present invention relate generally to computer processing and, more specifically, to modeling characters that interact with users as part of a character-as-a-service implementation. Description of the Related Art (2) Interacting with large numbers of users (e.g., customers, guests, clients, etc.) is an essential part of many services. For instance, an entertainment service provider oftentimes interacts with thousands or millions of individual users via help call lines, sales call lines, and/or entertainment characters. Some service providers employ human operators to interact with the users. However, as the number of user interactions increases, the costs associated with employing human operators to interact with the users becomes prohibitively expensive. For this reason, many service providers leverage touch-tone menus or simple menu voice recognition systems to automate interactions between remote users and various mass-market services, such as technical support, reservations, billing, and the like. Similarly, some entertainment service providers generate predetermined recordings to automate interactions between children and animation characters. (3) However, while interacting with these types of automated systems, users are typically aware that they are interacting with an automated system. For example, when the responses of an animated character are predetermined, many children quickly ascertain tha
Claims
1. A computer-implemented method for generating a character response during an interaction with a user, the method comprising: evaluating user input data that is associated with a user device to identify a user intent and an assessment domain; selecting at least one inference algorithm from a plurality of inference algorithms based, at least in part, on the user intent and the assessment domain, wherein each inference algorithm included in the plurality of inference algorithms implements machine learning functionality; generating an inference based on the at least one inference algorithm; selecting a first set of personality characteristics and a second set of personality characteristics from a plurality of sets of personality characteristics based, at least in part, on the inference, wherein the first set of personality characteristics is selected for generating content of the character response and the second set of personality characteristics is selected for generating an expression of the content of the character response, wherein the first set of personality characteristics comprises a first plurality of parameters and the second set of personality characteristics comprises a second plurality of parameters that is different from the first plurality of parameters, each parameter being associated with a personality dimension; computing the character response to the user input data based on the at least one inference algorithm, the user input data, the first set of personality characteristics, the second set of personality characteristics, and data representing knowledge associated with a character; and causing the user device to output the character response to the user. ||
11. A character engine that executes on one or more processors, the character engine comprising: a user intent engine that, when executed by the one or more processors, evaluates user input data that is associated with a user device to determine a user intent; a domain engine that, when executed by the one or more processors, evaluates at least one of the user input data or the user intent to identify an assessment domain; and an inference engine that, when executed by the one or more processors: selects at least one inference algorithm from a plurality of inference algorithms based on the user intent and the assessment domain, wherein each inference algorithm included in the plurality of inference algorithms implements machine learning functionality; generates an inference based on the at least one inference algorithm; selects a first set of personality characteristics and a second set of personality characteristics from a plurality of sets of personality characteristics based, at least in part, on the inference, wherein the first set of personality characteristics is selected for generating content of a character response and the second set of personality characteristics is selected for generating an expression of the content of the character response, wherein the first set of personality characteristics comprises a first plurality of parameters and the second set of personality characteristics comprises a second plurality of parameters that is different from the first plurality of parameters, each parameter being associated with a personality dimension; and compute the character response to the user input data based on the at least one inference algorithm, the user input data, the first set of personality characteristics, the second set of personality characteristics, and data representing knowledge associated with a character; and an output device abstraction infrastructure that, when executed by the one or more processors, causes the user device to output the character response to a user. ||
18. One or more non-transitory computer-readable media including instructions that, when executed by one or more processors, cause the one or more processors to generate a character response during an interaction with a user by performing the steps of: evaluating user input data that is associated with a user device to identify a user intent and an assessment domain; selecting at least one inference algorithm from a plurality of inference algorithms based, at least in part, on the user intent and the assessment domain, wherein each inference algorithm included in the plurality of inference algorithms implements machine learning functionality; causing the at least one inference algorithm to compute an inference based on the user input data and data representing knowledge associated with a character; selecting a first set of personality characteristics and a second set of personality characteristics from a plurality of sets of personality characteristics based, at least in part, on the inference, wherein the first set of personality characteristics is selected for generating content of the character response and the second set of personality characteristics is selected for generating an expression of the content of the character response, wherein the first set of personality characteristics comprises a first plurality of parameters and the second set of personality characteristics comprises a second plurality of parameters that is different from the first plurality of parameters, each parameter being associated with a personality dimension; and causing a personality engine associated with the character to compute the character response to the user input data based on the inference, the first set of personality characteristics, and the second set of personality characteristics.