Techniques for generating contextually-relevant recommendations

Number: 11457281
Published: 2022-09-27
Filed: 2020-01-31
Assignee: Disney Enterprises, Inc.
Inventors: Goslin; Michael P., Doggett; Erika Varis, Accardo; Anthony M., Vasquez; Noel Brandon
CPC: G09B19/0092; H04N21/4668; G06F9/453; G06F16/2379; G06F16/2455; G06Q10/087; G06Q10/08776; G09B19/003; H04N21/4131; H04N21/42202; H04N21/43615; H04N21/47217; H04N21/854; H05B6/6435; H05B6/6438; H05B6/668
Verdict: Set aside recommendation engine, business
Source: Google Patents · FreePatentsOnline

Abstract

A recommendation engine generates contextually relevant media programs tailored to the specific context of the user. The recommendation engine interfaces with one or more Internet-of-Things (IoT) appliances to determine one or more food items stored within the IoT appliance(s) and/or one or more cooking capabilities associated with the IoT appliance(s). The recommendation engine also gathers profile data that reflects a set of preferences associated with the user. Based on the gathered data, the recommendation engine queries a database of cooking program data associated with various cooking programs. The recommendation engine obtains cooking program data that is contextually relevant to the user and then generates a contextual cooking program that describes how to perform a given recipe. During playback of the contextual cooking program, the recommendation engine can modify the contextual cooking program based on the progress of the user in following the recipe.

Background

BACKGROUND Field of the Various Embodiments (1) The various embodiments relate generally to computer science and recommendation engines and, more specifically, to techniques for generating contextually-relevant recommendations. Description of the Related Art (2) A recommendation engine is a type of software program that recommends items to users. Recommendation engines are commonly implemented in consumer-facing websites in order to assist users with finding items that are relevant to those users. For example, a recommendation engine associated with an online shoe retailer could recommend specific types of shoes to different users. Among other things, recommendation engines can reduce the extent to which users have to manually search for relevant items and, therefore, can increase user engagement with various types of consumer-facing websites, including product-oriented websites, service-oriented websites, and media-oriented websites, to name a few. (3) A recommendation engine associated with a consumer-facing website can implement several techniques for recommending items to a user. Using one technique, the recommendation engine analyzes the browsing history of the user and then recommends items that are similar to the items the user has previously viewed. For example, the recommendation engine could determine that the user previously viewed different gardening tools and could then recommend one or more additional gardening tools to the user. Using another technique, the rec

Claims

1. A computer-implemented method for generating a media program, the method comprising: determining a first state that is associated with a procedure to be performed by a user, wherein the first state comprises a capability of a first appliance or an availability of at least one item stored within the first appliance; determining a set of instructions for performing the procedure based on a comparison of (i) a set of weighted data values and (ii) a set of dependencies for the procedure, wherein the set of weighted data values is generated based on a set of data values that quantify one or more characteristics included in the first state and a set of weights indicating relative importances of the one or more characteristics; determining a first portion of media content that depicts a first instruction included in the set of instructions; and generating a first media program based on the first portion of media content, wherein the first media program provides the first instruction to the user. || 11. A non-transitory computer-readable medium storing program instructions that, when executed by a processor, cause the processor to generate a media program by performing the steps of: determining a first state that is associated with a procedure to be performed by a user, wherein the first state comprises a capability of a first appliance or an availability of at least one item stored within the first appliance; determining a set of instructions for performing the procedure based on a comparison of (i) a set of weighted data values and (ii) a set of dependencies for the procedure, wherein the set of weighted data values is generated based on a set of data values that quantify one or more characteristics included in the first state and a set of weights indicating relative importances of the one or more characteristics; determining a first portion of media content that depicts a first instruction included in the set of instructions; and generating a first media program based on the first portion of media content, wherein the first media program provides the first instruction to the user. || 20. A system, comprising: a memory storing a software application; and a processor that, when executing the software application, is configured to generate a media program by performing the steps of: determining a first state that is associated with a procedure to be performed by a user, wherein the first state comprises a capability of a first appliance or an availability of at least one item stored within the first appliance; determining a set of instructions for performing the procedure based on a comparison of (i) a set of weighted data values and (ii) a set of dependencies for the procedure, wherein the set of weighted data values is generated based on a set of data values that quantify one or more characteristics included in the first state and a set of weights indicating relative importances of the one or more characteristics; determining a first portion of media content that depicts a first instruction included in the set of instructions; and generating a first media program based on the first portion of media content, wherein the first media program provides the first instruction to the user.