Use of generative artificial intelligence for interactive television recommendations

Abstract

Method comprising: receiving, by a computing device, an indication to launch a voice-based television assistant; displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation. Method for providing a personalized description of a media content item and method for providing a trivia game related to a media content item.

Description

Atty Docket No.0120-705WO1 USE OF GENERATIVE ARTIFICIAL INTELLIGENCE FOR INTERACTIVE TELEVISION RECOMMENDATIONS CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 607,953, filed on December 8, 2023, the disclosure of which is incorporated herein by reference in its entirety. BACKGROUND

[0002] A television (TV) application may present various types of media content of interest to a user. The media content may have different formats such as streaming video and audio. The types of media content may include, but are not limited to, movies, television shows, sporting events, news items, short form videos, and music. In addition, or in the alternative, a variety of media content providers may deliver various types of media content for viewing by the user. The TV application may find it difficult to personalize a viewing experience for a user because of the diverse types of media content provided by the variety of media content providers. SUMMARY

[0003] In a non-limiting example, a user may use a voice-based television assistant to provide input to a television. The user may provide the voice-based television assistant with verbal descriptions of media content they would like to view. The user may provide verbal commands to the voice-based television assistant describing how they would like to view and interact with the media content. Though helpful, in general, inputs to voice-based television assistants may have to be carefully worded or less naturally worded (e.g., not based on natural speaking language) to generate the desired user recommendation. The voice-based television assistant may not be nuanced enough to deal with the many different needs and desires of the user. The voice-based television assistant may not have a strong enough knowledge base for use in determining what may be useful to the user.

[0004] The TV application is presented with the technical problem of determining what media content the user may be interested in viewing based on verbal inputs to the voice- based television assistant. A technical solution to the technical problem, as described herein,Atty Docket No.0120-705WO1 may be to use a voice-based television assistant and generative artificial intelligence to implement an interactive conversation between the user and the TV application that allows the user to refine or fine-tune the information for the requested media content. The generative artificial intelligence may be implemented as an artificial neural network. The technical effect is the providing of media content to the user that meets the needs of the user. In particular, the media content provided is not just any old file; it is media content identified by the application of technical criteria which the TV application has worked out for itself through the interactive conversation. The output of the TV application is thus media content that would not otherwise be selected. This is a technical effect outside the computer which, when coupled with the purpose and method of selection, fulfils the requirement of technical effect.

[0005] In a non-limiting example, a television (TV) application may provide personalized media content recommendations for a user of the TV application based in part on generic descriptions associated with the media content as provided by, for example, a metadata provider or an editorial team. The generic descriptions may not provide any information to the user as to why the media content is recommended.

[0006] The TV application may be presented with the technical problem of how to provide a user of the TV application with media content recommendations that may be based on specified interests of the user as related to genres, actors, themes, etc. associated with the media content so that the user has a better understanding as to why the media content is recommended. A technical solution to the technical problem may be to utilize a knowledge module that includes information (metadata) associated with media content items and multi- dimensional user activity characteristics associated with the account of the user, a unified media platform for managing media content provided to a user, and generative artificial intelligence to generate customized descriptions of recommended media content to a user. The technical effect is providing the user with media content descriptions that clearly indicate why the media content is being recommended to the user.

[0007] In a non-limiting example, a television (TV) application may implement a trivia game for a user based on media content recommendations for the user of the TV application. In some implementations, the trivia game may provide a user with questions directed towards trivia for a recommended media content item selected by the user. In some implementations, the trivia questions may be directed towards trivia for the media content item that may be related to one or more preferences of the user. In some implementations, the trivia questions may be directed towards trivia for the media content item that may be related to past behaviors, history, and interests of the user. For example, a user who is interested in aAtty Docket No.0120-705WO1 particular actor that is cast in a recommended movie may be presented with trivia questions related to the actor and their part in the movie. A user interface may present and guide the user through the trivia game. The TV application may provide a score for the trivia game. The TV application may provide a leader board for the trivia game.

[0008] The TV application may be presented with the technical problem of how to provide an engaging experience to the user of the TV application. The technical solution to the technical problem may be for the TV application to engage the user in a trivia game that involves media content of interest to the user. The technical effect is to provide an enjoyable user experience with the TV application.

[0009] In some aspects, the techniques described herein relate to a method including: receiving, by a computing device, an indication to launch a voice-based television assistant; and in response to receiving the indication, launching the voice-based television assistant including: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0010] In some aspects, the techniques described herein relate to a method, wherein launching the voice-based television assistant further includes: sending, by the computing device and to the server computer, the second voice data for the second query, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the method further includes displaying, by a television application executing on the computing device, a selectable information item in a user interface of the television application, the selectable information item being associated with the at least one media content recommendation.

[0011] In some aspects, the techniques described herein relate to a method, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.Atty Docket No.0120-705WO1

[0012] In some aspects, the techniques described herein relate to a method, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

[0013] In some aspects, the techniques described herein relate to a method, wherein the received first voice data and the received second voice data are included in a conversation between a user of the computing device and the voice-based television assistant.

[0014] In some aspects, the techniques described herein relate to a method, further including receiving, by a microphone of the computing device, the verbal input.

[0015] In some aspects, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0016] In some aspects, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0017] In some aspects, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0018] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a computing device cause the at least one processor to execute operations, the operations including: receiving, by the computing device, an indication to launch a voice- based television assistant; and in response to receiving the indication, launching the voice- based television assistant including: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0019] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein launching the voice-based television assistant further includes: sending, by the computing device and to the server computer, the second voice data for the second query, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and whereinAtty Docket No.0120-705WO1 the operations further include displaying, by a television application executing on the computing device, a selectable information item in a user interface of the television application, the selectable information item being associated with the at least one media content recommendation.

[0020] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

[0021] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

[0022] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the received first voice data and the received second voice data are included in a conversation between a user of the computing device and the voice-based television assistant.

[0023] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, further including receiving, by a microphone of the computing device, the verbal input.

[0024] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0025] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0026] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0027] In some aspects, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing executable instructions that execute a unified television application on a network-connected display device, the unified television application configured to: receive an indication to launch a voice-based television assistant; and in response to receiving the indication, launch the voice- based television assistant including: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending the first voice data for the first query to a server computer; receivingAtty Docket No.0120-705WO1 a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0028] In some aspects, the techniques described herein relate to a system, wherein launching the voice-based television assistant further includes: sending the second voice data for the second query to the server computer, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the unified television application is further configured to display a selectable information item in a user interface of the unified television application, the selectable information item being associated with the at least one media content recommendation.

[0029] In some aspects, the techniques described herein relate to a system, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

[0030] In some aspects, the techniques described herein relate to a system, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

[0031] In some aspects, the techniques described herein relate to a system, wherein the received first voice data and the received second voice data are included in a conversation between a user of the system and the voice-based television assistant.

[0032] In some aspects, the techniques described herein relate to a system, wherein the unified television application is further configured to receive, by a microphone of the system, the verbal input.

[0033] In some aspects, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0034] In some aspects, the techniques described herein relate to a method including: receiving, by a server computer and from a computing device, first voice data for a first query related to a media content recommendation; generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previousAtty Docket No.0120-705WO1 responses, or a context for the first query; sending, by the server computer and to the computing device, the response to the computing device; receiving second voice data for a second query responsive to the response; generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and sending the at least one media content recommendation to the computing device.

[0035] In some aspects, the techniques described herein relate to a method, further including: generating a text string for the first voice data; and providing the text string to a generative artificial intelligence engine in the server computer.

[0036] In some aspects, the techniques described herein relate to a method, further including: generating, by the generative artificial intelligence engine, the response based on the text string; and parsing the response to identify at least one media content item associated with the media content recommendation.

[0037] In some aspects, the techniques described herein relate to a method, further including: fetching at least one of the media content item and a description of the media content item; and sending the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

[0038] In some aspects, the techniques described herein relate to a method, wherein generating the response includes creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

[0039] In some aspects, the techniques described herein relate to a method, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the method further includes storing a context for the conversation session, the context for use in determining future media content recommendations for the user.

[0040] In some aspects, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0041] In some aspects, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0042] In some aspects, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.Atty Docket No.0120-705WO1

[0043] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations including: receiving, by the server computer and from a computing device, first voice data for a first query related to a media content recommendation; generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; sending, by the server computer, the response to the computing device; receiving second voice data for a second query responsive to the response; generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and sending the at least one media content recommendation to the computing device.

[0044] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include: generating a text string for the first voice data; and providing the text string to a generative artificial intelligence engine in the server computer.

[0045] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include: generating, by the generative artificial intelligence engine, the response based on the text string; and parsing the response to identify at least one media content item associated with the media content recommendation.

[0046] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include: fetching at least one of the media content item and a description of the media content item; and sending the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

[0047] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein generating the response includes creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.Atty Docket No.0120-705WO1

[0048] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the operations further include storing a context for the conversation session, the context for use in determining future media content recommendations for the user.

[0049] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0050] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0051] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0052] In some aspects, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receive first voice data for a first query related to a media content recommendation from a computing device; generate a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; send the response to the computing device; receive second voice data for a second query responsive to the response; generate at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and send the at least one media content recommendation to the computing device.

[0053] In some aspects, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to: generate a text string for the first voice data; and provide the text string to a generative artificial intelligence engine in the system.

[0054] In some aspects, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to: generate, by the generative artificial intelligence engine, the response based on the text string;Atty Docket No.0120-705WO1 and parse the response to identify at least one media content item associated with the media content recommendation.

[0055] In some aspects, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to: fetch at least one of the media content item and a description of the media content item; and send the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

[0056] In some aspects, the techniques described herein relate to a system, wherein generating the response includes creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

[0057] In some aspects, the techniques described herein relate to a system, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the instructions when executed by the at least one processor further cause the system to store a context for the conversation session, the context for use in determining future media content recommendations for the user.

[0058] In some aspects, the techniques described herein relate to a system, wherein the computing device is a network-connected display device.

[0059] In some aspects, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0060] In some aspects, the techniques described herein relate to a system, wherein the computing device is a mobile computing device.

[0061] In some aspects, the techniques described herein relate to a method including: receiving, by a server computer, information and data related to preferences of a user for media content; identifying metadata associated with a media content item; determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and sending, by the server computer and to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.Atty Docket No.0120-705WO1

[0062] In some aspects, the techniques described herein relate to a method, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

[0063] In some aspects, the techniques described herein relate to a method, wherein the personalized description is a text string.

[0064] In some aspects, the techniques described herein relate to a method, wherein the method further includes generating a request for the personalized description for the media content item, the request specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

[0065] In some aspects, the techniques described herein relate to a method, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

[0066] In some aspects, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0067] In some aspects, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0068] In some aspects, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0069] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations including: receiving information and data related to preferences of a user for media content; identifying metadata associated with a media content item; determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and sending, to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

[0070] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

[0071] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the personalized description is a text string.Atty Docket No.0120-705WO1

[0072] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include generating a request for the personalized description for the media content item, the request specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

[0073] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

[0074] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0075] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0076] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0077] In some aspects, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receiving information and data related to preferences of a user for media content; identify metadata associated with a media content item; determine that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generate a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and send, to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

[0078] In some aspects, the techniques described herein relate to a system, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

[0079] In some aspects, the techniques described herein relate to a system, wherein the personalized description is a text string.Atty Docket No.0120-705WO1

[0080] In some aspects, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to generate a request for the personalized description for the media content item, the request specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

[0081] In some aspects, the techniques described herein relate to a system, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

[0082] In some aspects, the techniques described herein relate to a system, wherein the computing device is a network-connected display device.

[0083] In some aspects, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0084] In some aspects, the techniques described herein relate to a system, wherein the computing device is a mobile computing device.

[0085] In some aspects, the techniques described herein relate to a method including: receiving, by a server computer, a request for a trivia question for a media content item; sending, by the server computer and to a computing device, a trivia question for display in a user interface on the computing device; receiving an answer to the trivia question; determining whether the answer is a correct answer; and sending a message as to whether the answer is the correct answer for display in the user interface.

[0086] In some aspects, the techniques described herein relate to a method, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

[0087] In some aspects, the techniques described herein relate to a method, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

[0088] In some aspects, the techniques described herein relate to a method, further including sending along with the trivia question at least two answers to the trivia question for display in the user interface.

[0089] In some aspects, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0090] In some aspects, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.Atty Docket No.0120-705WO1

[0091] In some aspects, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0092] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations including: receiving, by the server computer, a request for a trivia question for a media content item; sending a trivia question to a computing device for display in a user interface on the computing device; receiving an answer to the trivia question; determining whether the answer is a correct answer; and sending a message as to whether the answer is a correct answer for display in the user interface.

[0093] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

[0094] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

[0095] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include sending along with the trivia question at least two answers to the trivia question for display in the user interface.

[0096] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0097] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0098] In some aspects, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0099] In some aspects, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receive a request for a trivia question for a media content item; send a trivia question to a computing device for display in a user interface on the computing device; receive an answer to the trivia question; determine whether the answer is a correct answer; and send a message as to whether the answer is the correct answer for display in the user interface.Atty Docket No.0120-705WO1

[0100] In some aspects, the techniques described herein relate to a system, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

[0101] In some aspects, the techniques described herein relate to a system, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

[0102] In some aspects, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to send along with the trivia question at least two answers to the trivia question for display in the user interface.

[0103] In some aspects, the techniques described herein relate to a system, wherein the computing device is a network-connected display device.

[0104] In some aspects, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0105] In some aspects, the techniques described herein relate to a system, wherein the computing device is a mobile computing device.

[0106] The details of one or more implementations are set forth in the accompanying drawings and the description below. Other features will be apparent from the description and drawings, and from the claims. BRIEF DESCRIPTION OF THE DRAWINGS

[0107] FIG.1A illustrates an example of a user interacting with a network-connected display device and a media adapter, according to implementations described throughout this disclosure.

[0108] FIG.1B illustrates an example of a user interacting with a network-connected display device in a location different from a location of a television adapter, according to implementations described throughout this disclosure.

[0109] FIGS. 2A-I are illustrations of example user interfaces for an interactive conversation or chat between a user and a TV application for requesting and refining recommendations for media content, according to implementations described throughout this disclosure.

[0110] FIG. 3 illustrates a flowchart depicting example operations of an interactive conversation of a user with a TV application.Atty Docket No.0120-705WO1

[0111] FIG. 4 illustrates a flowchart depicting another example of operations of an interactive conversation of a user with a TV application.

[0112] FIGS.5A-E are illustrations of example user interfaces that a user may interact with to provide user preferences for or interests in characteristics or criteria associated with media content, according to implementations described throughout this disclosure.

[0113] FIG. 6 is an illustration of media content preference categories for three different users.

[0114] FIG.7 is an illustration of an example of a TV application providing the same media content recommendation to two different users based on different user preferences.

[0115] FIG. 8 is a diagram showing a description of an example process 800 for generating customized descriptive text for a media content recommendation.

[0116] FIG. 9 is a block diagram of an example process for generating customized descriptive text for a media content recommendation for one or more users as performed by systems enclosed herein.

[0117] FIG. 10 illustrates a flowchart depicting example operations of generating a personalized description of a media content item.

[0118] FIGS.11A-J are illustrations of example user interfaces for an interactive trivia game between a user and a TV application, according to implementations described throughout this disclosure.

[0119] FIG. 12 illustrates a flowchart depicting example operations of the implementation of a trivia game for media content items of interest to a user. DETAILED DESCRIPTION

[0120] In a non-limiting example, a user may use a voice-based television assistant to provide input to a television. The user may provide the voice-based television assistant with verbal descriptions of media content they would like to view. The user may provide verbal commands to the voice-based television assistant describing how they would like to view and interact with the media content. Though helpful, in general, inputs to voice-based television assistants may have to be carefully worded or less naturally worded (e.g., not based on natural speaking language) to generate the desired user recommendation. The voice-based television assistant may not be nuanced enough to deal with the many different needs and desires of the user. The voice-based television assistant may not have a strong enough knowledge base for use in determining what may be useful to the user. Moreover, the media content items may be collated from or provided by different media content providers, and so may each have differentAtty Docket No.0120-705WO1 associated information or metadata. Therefore, the TV application is presented with the technical problem of determining what media content the user may be interested in viewing based on verbal inputs to the voice-based television assistant.

[0121] A TV application may curate or provide media content recommendations based on the past activities of the user when interacting with the TV application, the viewing history of the user, and / or the popularity of media content items of a certain type, classification, category, group or genre. When a user launches the TV application, whether it be on a mobile device, a network-connected display device, or a television (e.g., a smart television), the user may have an idea as to the media content they would like to watch, which in some circumstances may not be the same as the media content recommendations (e.g., “What to watch now”) made by the TV application when launched.

[0122] A user may refine or fine-tune the media content recommendations made by the TV application using an interactive verbal exchange or chat session between the user and the TV application using the voice-based television assistant. In some implementations, the TV application may use generative artificial intelligence (generative AI) to recommend media content to a user based on an interactive verbal exchange or conversation between the user and the voice-based television assistant. For example, the media content may include but is not limited to television shows, movies, live media content, sporting events, trivia, and games. Though the media content may be described as viewed on a television (e.g., a smart television), the TV application may provide the media content for viewing on a mobile device or a network-connected display device.

[0123] FIG. 1A illustrates an example of a user 101 interacting with a network- connected display device 104 and a media adapter 107, according to implementations described throughout this disclosure. FIG.1B illustrates an example system 100 for generating interactive media content recommendations, personalized media content descriptions, and an interactive trivia game, according to implementations described throughout this disclosure.

[0124] In some implementations, referring to FIGS.1A-B, the user 101 may connect to and interact with the media adapter 107 using a television (TV) application 110 installed on a mobile computing device 102. Examples of the mobile computing device 102 may include, but are not limited to, a mobile phone, a smartphone, a tablet computer, a laptop computer, and a personal digital assistant.

[0125] The user, interacting with the TV application 110, may launch a user interface (UI) 112 on a display 132 of the network-connected display device 104. The TV application 110 may present a list of recommended media content in a row 111 in the user interface 112Atty Docket No.0120-705WO1 (e.g., “Top Picks For You”). For example, the row 111 may include, for each media content recommendation, an area or slot (e.g., slot 109) that includes a visual representation of the media content recommendation along with a link to the recommended media content.

[0126] The network-connected display device 104 may communicate with a server computer 106 and media content providers 160 by way of a network 150. The media content providers 160, the network-connected display device 104, the server computer 106, and the mobile computing device 102 may interact with and communicate with one other by way of the network 150. In some implementations, the mobile computing device 102 may interface or connect to the media adapter 107 and / or the network-connected display device 104 by way of a wireless communication link that may be a short-range wireless connection such as, for example a Bluetooth connection or a Wi-Fi (e.g., direct Wi-Fi) connection.

[0127] In some implementations, the user 101 may connect to and interact with the media adapter 107 by way of the network-connected display device 104 using a server-side television (TV) application 116 installed on the server computer 106. The media adapter 107 may be connected or interfaced to the network-connected display device 104. The network- connected display device 104 may be communicatively coupled or connected to the server computer 106 by way of a network 150. The network-connected display device 104 may execute a unified television application 130 that may interface with the server-side TV application 116. The unified television application 130 may present a list of recommended media content in the row 111 in the user interface 112 (e.g., “Top Picks For You”). The network-connected display device 104 may receive the ranked list as a media content recommendation stream from the server computer 106.

[0128] The mobile computing device 102 may include a voice module 134. In some implementations, a voice input device (e.g., the smart speaker 103) may provide voice data input to the mobile computing device 102. The voice module 134 may receive the voice data from the voice input devices. In some implementations, the mobile computing device 102 may include a voice input device (e.g., a microphone 136). The voice module 134 may process the voice data or human speech received from the voice input device to provide textual input as a sequence of words to the TV application 110. In some implementations, the voice module 134 may perform natural language processing to convert the human speech into the sequence of words. In some implementations, the voice module 134 may be included in the smart speaker 103. In some implementations, the voice-based TV assistant application 118 may be included in the remote control device 105. The sequence of words may be text representative of theAtty Docket No.0120-705WO1 verbal input received by the voice input devices. The unified television application 130 may receive the sequence of words.

[0129] In some implementations, the user 101 may interact with the network- connected display device 104 using a remote control device 105. In some implementations, the TV application 110 may render a virtual remote control 138 in a user interface (e.g., the UI 114) on a display (e.g., the mobile computing device display 108) on the mobile computing device 102. The user may interact with the remote control device 105 and / or the virtual remote control 138 when selecting media content for viewing on the network-connected display device 104.

[0130] In some implementations, the user may interact with a voice-based television (TV) assistant application 118 included on the network-connected display device 104. For example, the voice-based TV assistant application 118 may receive voice data or commands from voice input devices that include a microphone such as a remote control device 105 or a smart speaker 103. In some implementations, the network-connected display device 104 may include a voice input device. In some implementations, the mobile computing device 102 may provide the virtual remote control 138 in the UI 114 on the mobile computing device display 108 that allows the mobile computing device 102 to act as a remote control for the network- connected display device 104. In some implementations, the voice-based TV assistant application 118 may receive voice data or commands from the mobile computing device 102 when acting as a remote control for the network-connected display device 104. For example, a microphone 136 may receive verbal commands or voice data from a user. In some implementations, a voice module 134 may send the voice data to the network-connected display device 104 by way of the network 150. In some implementations, the voice module 134 may send the voice data to the network-connected display device 104 by way of a wireless communication link (e.g., wireless communication link 163d).

[0131] A user may speak into a voice input device providing a verbal description of media content they would like to view. In addition, or in the alternative, the user may provide verbal commands describing how they would like to view and interact with the media content by speaking into the voice input devices.

[0132] The voice-based television assistant application 118 may receive the voice data from the voice input devices. The voice-based TV assistant application 118 may process the voice data or human speech to provide textual input as a sequence of words to the unified television application 130. In some implementations, the voice-based TV assistant application 118 may perform natural language processing to convert the human speech into the sequenceAtty Docket No.0120-705WO1 of words. In some implementations, the voice-based TV assistant application 118 may be included in the smart speaker 103. In some implementations, the voice-based TV assistant application 118 may be included in the remote control device 105. In some implementations, the voice-based TV assistant application 118 may be included in the voice module 134 on the mobile computing device 102. The sequence of words may be text representative of the verbal input received by the voice input device.

[0133] In some implementations, the unified television application 130 may receive the sequence of words. The unified television application 130 may send the sequence of words to a knowledge base for help in identifying media content of interest to the user. For example, the network-connected display device 104 may send the sequence of words to a knowledge module 166 included in the server computer 106. The knowledge module 166 may include information associated with media content items provided by the media content providers 160. In some implementations, the knowledge module 166 may generate media content recommendations for associating with an account of a user based, in part, on a multi- dimensional user activity characteristic associated with the account of the user and the information associated with media content items provided by the media content providers 160. The user activity characteristic associated with the account of the user may be obtained from a plurality of information sources that may include, but are not limited to, a search engine, a mapping application, and an online retailer. The information sources may provide activity data related to activities of the account of the user by way of a respective software program or application.

[0134] The knowledge module 166 may help the unified television application 130 identify media content that may be useful and of interest to the user. The unified television application 130 interfacing with the knowledge module 166 may curate or provide media content recommendations based on the past activities of the user when interacting with the unified television application 130, the viewing history of the user, and / or the popularity of media content items of a certain type, classification, category, group or genre.

[0135] When a user launches the unified television application 130, the user may have an idea as to the media content they would like to watch, which in some circumstances may not be the same as the media content recommendations (e.g., “Top Picks For You”) made by the unified television application 130 when launched. The unified television application 130 may implement an interactive verbal exchange or chat session with the user with the assistance of the voice-based TV assistant application 118. The interactive verbal exchange may allow the user to direct the refining or fine-tuning of the media content recommendations made byAtty Docket No.0120-705WO1 the unified television application 130. An example of this process will be shown with reference to FIGS.2A-I.

[0136] The mobile computing device 102 may be configured to execute the TV application 110. The mobile computing device 102 may include the mobile computing device display 108 configured to display the UI 114. A user may interact with the UI 114 to set up, control, and interact with the TV application 110. In some implementations, as described, the TV application 110 may display the virtual remote control 138 in the UI 114 allowing the user 101 to interact with and control the network-connected display device 104.

[0137] The mobile computing device 102 may be any type of computing device that includes one or more processors (processor(s) 140), one or more memory devices (memory device(s) 142), and an operating system 144. The mobile computing device 102 may be a smartphone, a tablet, a wearable device, a laptop computer, or a desktop computer. In some implementations, the operating system 144 may be system software that manages computer hardware, software resources, and provides common services for computing programs.

[0138] In some implementations, the mobile computing device 102 may be a tablet, a smartphone, or a wearable. In these implementations, the operating system 144 may be referred to as a mobile operating system. The mobile operating system may be configured to execute on devices that, in general, include display devices that may be smaller in size than, for example, a display device included in a laptop computer or a desktop computer. In some implementations, the mobile computing device 102 may be a laptop computer. In these implementations, the operating system may be referred to as a laptop or desktop operating system. In these implementations, the operating system 144 may be an operating system designed for a display that is larger in size than that included in a tablet, a smartphone, or a wearable.

[0139] In some implementations, the media adapter 107 (e.g., a casting device, a media streaming device, a media streaming player) may be interfaced with or connected to the network-connected display device 104. The media adapter 107 may interact with and communicate with the media content providers 160, the server computer 106, and the mobile computing device 102 when providing media content to the network-connected display device 104. In some implementations, the media adapter 107 may be embedded in and / or an integrated part of the network-connected display device 104.

[0028] The media content providers 160 may include a variety of streaming service and media content sources and service platforms. The media adapter 107 may facilitate providing (e.g., streaming) media content (e.g., streaming video such as movies, TV shows,Atty Docket No.0120-705WO1 etc.) from one or more streaming services included in the media content providers 160 to the network-connected display device 104. For example, the media adapter 107 may directly connect to a connector on the network-connected display device 104 by way of connection 165. The media adapter 107 may provide digital video and / or audio to the network-connected display device 104. For example, the media adapter 107 may connect to a high-definition multimedia interface (HDMI) connector included in the network-connected display device 104. Examples of the media adapter 107 may include, but are not limited to, a set-top box, a television box, and a streaming media adapter.

[0140] The user 101 may connect to and interact with the media adapter 107 using the TV application 110 installed on the mobile computing device 102. The user, interacting with the TV application 110, may select streaming services (e.g., free services, subscription-based services) for viewing media content on the network-connected display device 104. As described, the media adapter 107 can facilitate the interface between the media content providers 160 and the network-connected display device 104 that the user 101 uses to view media content (e.g., streaming media content, movies, TV shows, etc.).

[0141] In some implementations, the mobile computing device 102 may connect to or interface with the media adapter 107 by way of a wireless communication link 163b. Wireless communication links 163a-e may be short-range wireless connections such as a Bluetooth connection. In some examples, wireless communication links 163a-e may be a Wi-Fi (e.g., direct Wi-Fi) connection.

[0142] The media adapter 107 may be any type of computing device that includes one or more processors (processor(s) 170), one or more memory devices (memory device(s) 172), and an operating system 174. In some implementations, the processor(s) 170 may include a system on a chip (SoC). The SoC may include a central processing unit (CPU), a graphic processing unit (GPU), one or more memory interfaces, and one or more input / output interfaces and devices. In some implementations, the operating system 174 may be system software that manages computer hardware, software resources, and provides common services for computing programs.

[0143] The network-connected display device 104 may include the unified television application 130. The unified television application 130 may keep a record of the interactions of the user with the media content in the media content recommendation stream received from the server computer 106 for display in one or more rows in the user interface 112. The network-connected display device 104 may send the record of the interactions to the server computer 106 for use in determining media content recommendations for the user.Atty Docket No.0120-705WO1

[0144] In some implementations, the network-connected display device 104 may be configured to execute the unified television application 130. For example, the network- connected display device 104 may be a smart television. For example, a smart television may be a network-connected television that may connect to media content providers (e.g., media content providers 160) by way of a network (e.g., the network 150). The media content providers may source media content to the smart television. In these implementations, a user may interact with the unified television application 130 to access media content from the media content providers 160. The unified television application 130 may interface with the server computer 106, and specifically with the server-side TV application 116. The unified television application 130 may provide similar functionality to the user as that provided by an application executing on the media adapter 107. For example, executing the unified television application 130 by the network-connected display device 104 allows the network-connected display device 104 to obtain a media content recommendation stream from the server computer 106.

[0145] The network-connected display device 104 may be configured to connect to the network 150. In some implementations, the network-connected display device 104 is a television (e.g., a smart television (TV)). The network-connected display device 104 may include one or more processors (processor(s) 156), one or more memory devices (memory device(s) 152), and an operating system (OS) 154. The operating system 154 may execute (or assist with executing) the unified television application 130.

[0146] In some implementations, the operating system 154 may be a browser application. A browser application is a web browser configured to access information on the Internet by way of a network (e.g., the network 150). A browser application may launch one or more browser tabs in the context of one or more browser windows in the browser application. In some implementations, the operating system 154 is a Linux-based operating system configured to execute (or assist with executing) the unified television application 130.

[0147] The system 100 may include one or more server computers (e.g., the server computer 106) configured to interface with the mobile computing device 102, the media adapter 107, the media content providers 160, and the network-connected display device 104 by way of the network 150. In some implementations, the network 150 may establish a wireless communication link between the network-connected display device 104, the mobile computing device 102, the media adapter 107, the media content providers 160, and the server computer 106.Atty Docket No.0120-705WO1

[0148] The server computer 106 may include a unified media platform (UMP) 158. The UMP 158 may contribute to the managing of media content recommendations. The UMP 158 may manage the providing of the media content associated with the media content recommendations to the network-connected display device 104. In some implementations, the UMP 158 may manage the providing of the media content associated with the media content recommendations from the media content providers 160 to the mobile computing device 102.

[0149] The UMP 158 may provide a media content recommendation stream as described herein to the network-connected display device 104. In some implementations, the UMP 158 may provide the media content recommendation stream to the media adapter 107, which in turn streams the selected media content from the media content providers 160 to the network-connected display device 104. In response to receiving an indication of a selection from the media content recommendations, the server-side television application 116 may enable display of the media content on the display 132. In some implementations, the UMP 158 may function as a centralized media content management module configured to provide the media content recommendations to the mobile computing device 102.

[0150] The server computer 106 may include a parsing module 122. The parsing module 122 may receive an input data stream that may include text and data. The parsing module 122 may parse the input streams to identify any media content items (e.g., videos, movies, TV shows, audio files, music, etc.) included in the input data stream. The parsing module 122 may identify metadata associated with the identified media content items such as actors, titles, descriptions, content providers, genres, etc.

[0151] The server computer 106 may include an artificial intelligence (AI) module 194. The AI module 194 may receive information and data from the mobile computing device 102 and / or the network-connected display device 104 to build an AI model for use by the AI module 194. In some implementations, the AI module 194 may provide the server-side TV application 116 with a plurality of recommended media content items directed towards fulfilling requests by the mobile computing device 102 and / or the network-connected display device 104. The server-side TV application 116 may generate a media content recommendation stream as a sequence of selectable information items that correspond to the plurality of recommended media content items.

[0152] The AI module 194 may receive updated media content recommendations from the knowledge module 166 along with updated information and data from the mobile computing device 102 and / or the network-connected display device 104 to retrain the AI model. The AI module 194 may use the retrained AI model to provide the server-side TVAtty Docket No.0120-705WO1 application 116 with updated recommended media content items. The server-side TV application 116 may generate an updated media content recommendation stream as a sequence of updated selectable information items that correspond to the updated recommended media content items. In some implementations, user queries to the unified television application 130 and responses to the user queries may train a deep learning algorithm for use by the AI module 194 and the generative AI engine 146.

[0153] In some implementations, the AI module 194 may use generative artificial intelligence along with a generative AI model. For example, in these implementations, the AI module 194 may be referred to as a generative artificial intelligence (generative AI) back end. For example, generative AI may identify themes related to media content viewed by the user across multiple different media content providers. The generative AI may curate or create a collection of media content recommendations based on the identified themes.

[0154] In some implementations, the TV application may use generative artificial intelligence (generative AI) to recommend media content to a user based on an interactive verbal exchange or conversation between the user and the voice-based television assistant. For example, the media content may include but is not limited to television shows, movies, live media content, sporting events, trivia, and games. In this way, thematically similar media content is identified by the application of technical criteria which the system has worked out for itself. The output is thus media content that would not otherwise be selected. This provides a technical effect outside the TV application itself, which when coupled with the purpose and method of selection, fulfils the requirement of technical effect.

[0155] The use of generative AI can help further focus and refine the information desired by the user. The TV application may refine the search for the information requested by the user as more knowledge is gained by receiving user responses and feedback on previously provided information. The TV application may filter the information provided to the user based on user responses and feedback to previously provided information. The TV application may pose a question to the user to further understand what information the user is seeking. In this way, the technical criteria for selection of the media content can be worked out by the TV application itself.

[0156] The server computer 106 may include a trivia question generator 148. For example, the trivia question generator 148 may interface with the server-side TV application 116 and the AI module 194 to generate trivia questions and answers for a trivia game. For media content items of interest to a user.

[0157] The server computer 106 may include a context module 162. The contextAtty Docket No.0120-705WO1 module 162 may determine, maintain, and store a context for spoken user requests received by TV applications (e.g., the unified television application 130, the TV application 110). The context may be stored in association with an interactive conversation session for the spoken user request. The context may be provided to the knowledge module 166 for association with the user. The knowledge module 166 may use the context information and data to help generate media content recommendations for associating with an account of a user as part of the multi-dimensional user activity characteristic associated with the account of the user and the information associated with media content items provided by the media content providers 160.

[0158] The server computer 106 may include a topic service 164. The topic service 164. The topic service 164 may receive information and data related to preferences and interests of a user. The topic service 164 may interface with the AI module 194 to provide information and data for use by the generative AI engine 146 when generating customized descriptive text for a media content item of interest to a user.

[0159] The mobile computing device 102 may include the mobile computing device display 108. In some implementations, the mobile computing device display 108 is a display device such as a liquid crystal display (LCD), a light-emitting diode (LED) display, an organic light-emitting diode (OLED) display, or an active-matrix organic light-emitting diode (AMOLED) display. The network-connected display device 104 may include the display 132. In some implementations, the display 132 is a display device such as a liquid crystal display (LCD), a light-emitting diode display (LED) display, a plasma display, a quantum dot light- emitting diode display (QLED) display, or an organic light-emitting diode (OLED) display.

[0160] The processor(s) 156, the processor(s) 140, the processor(s) 170, and the processor(s) 180 may be formed in a substrate configured to execute one or more machine executable instructions or pieces of software, firmware, or a combination thereof. The processor(s) 156, the processor(s) 140, the processor(s) 170, and the processor(s) 180 may be semiconductor-based. For example, the processor(s) 156, the processor(s) 140, the processor(s) 170, and the processor(s) 180 may include semiconductor material that can perform digital logic.

[0161] The memory device(s) 152, the memory device(s) 142, the memory device(s) 172, and the memory device(s) 182 may include main memory that stores information in a format that can be read and / or executed by the processor(s) 156, the processor(s) 140, the processor(s) 170, and the processor(s) 180 respectively. The memory device(s) 152, the memory device(s) 142, the memory device(s) 172, and the memory device(s) 182 may includeAtty Docket No.0120-705WO1 one or more random-access memory (RAM) devices and / or one or more read-only memory (ROM) devices.

[0162] The memory device(s) 152, memory device(s) 142, the memory device(s) 172, and the memory device(s) 182 may store applications that, when executed by the processor(s) 156, the processor(s) 140, the processor(s) 170, and the processor(s) 180, respectively, perform operations. For example, the memory device(s) 142 may store the operating system 144 and the TV application 110 that, when executed by the processor(s) 140, may perform operations on the mobile computing device 102. For example, the memory device(s) 152 may store operating system 154 and the unified television application 130 that, when executed by the processor(s) 156, may perform operations on the network-connected display device 104.

[0163] In some implementations, the memory device(s) 182 may represent any kind of (or multiple kinds of) memory (e.g., RAM, flash, cache, disk, tape, etc.). In some implementations, the memory device(s) 182 may include external storage, e.g., memory physically remote from but accessible by the server computer 106. The server computer 106 may include one or more modules, engines, or applications representing specially programmed software. In some implementations, the server computer 106 may include the operating system 184, the server-side TV application 116, the knowledge module 166, the parsing module 122, the AI module 194, the generative AI engine 146, the UMP 158, the trivia question generator 148, the context module 162, processor(s) 180, and the device(s) 182. For example, the memory device(s) 182 may store the operating system 184, the server-side TV application 116, the knowledge module 166, the parsing module 122, the UMP 158, the trivia question generator 148, the AI module 194, the generative AI engine 146, the context module 162, and the topic service 164 that, when executed by the processor(s) 180, may perform operations on server computer 106 to implement one or moreo f the methods and processes described herein.

[0164] The network 150 may include the Internet and / or other types of data networks, such as a local area network (LAN), a wide area network (WAN), a cellular network, satellite network, or other types of data networks. The network 150 may also include any number of computing devices (e.g., computer, servers, routers, network switches, etc.) that are configured to receive and / or transmit data within the network 150. The network 150 may further include any number of hardwired and / or wireless connections. The network 150 may be, for example, communications networks having one or more types of topologies, including but not limited to the Internet, intranets, local area networks (LANs), cellular networks, Ethernet, Storage Area Networks (SANs), telephone networks, and Bluetooth personal areaAtty Docket No.0120-705WO1 networks (PAN). In some implementations, two or more devices in a sub-network may be coupled by way of a wired connection, while at least some of the devices in the same sub- network are coupled by way of a local radio communication network (e.g., ZigBee, Z-Wave, Insteon, Bluetooth, Wi-Fi and other radio communication networks).

[0165] FIGS. 2A-I are illustrations of example user interfaces for an interactive conversation or chat between a user and a TV application for requesting and refining recommendations for media content, according to implementations described throughout this disclosure. FIGS.2A-I are described with reference to FIGS.1A-B.

[0166] A user may refine or fine-tune media content recommendations made by a TV application using an interactive verbal exchange, an interactive conversation, or chat session between the user and the TV application using a voice-based television assistant. A user may use a remote control device to interact with a user interface for a unified TV application 130. Using the remote control device, the user may select or click on an icon or text entry to open a user interface to begin an interactive verbal exchange with the TV application by way of the voice-based television assistant. For example, referring to FIG.2A, the user may launch the unified television application 130 on the network-connected display device 104. The unified television application 130 may display a first user interface 200 on the display 132. The user may use the remote control device 105 to interact with the first user interface 200. The user may click on or select a “Discover” text entry 202.

[0167] Once selected, the TV application may open a second user interface allowing the user to begin the interactive conversation. For example, referring to FIG.2B, the unified television application 130 may provide a second user interface 205 responsive to the selection of the “Discover” text entry 202. The user may begin an interactive conversation with the unified television application 130 by selecting or clicking on a “Click to speak” text entry 206. Once the user clicks on or selects the “Click to speak” text entry 206, the user may begin speaking into a voice input device, verbally describing what media content they are interested in viewing. For example, referring to FIGS.2B-C, in response to a first question 208 from the unified television application 130, the user may click on or select the “Click to speak” text entry 206, and then the user may speak into the remote control device 105, which may include a microphone, verbally describing what media content they are interested in viewing. The voice-based TV assistant application 118 may receive the voice data. The voice-based TV assistant application 118 may use natural language processing to generate a first text string 212 of the received voice data of the verbal description of the media content the user is interested in viewing in a third user interface 210. The voice-based TV assistant applicationAtty Docket No.0120-705WO1 118 may provide the first text string 212 to the unified television application 130 beginning the interactive conversation between the user and the unified television application 130.

[0168] The unified television application 130 may send the first text string 212 to the knowledge module 166. The knowledge module 166 may include information associated with media content items provided by the media content providers 160. The unified television application 130 interfacing with the knowledge module 166 may curate or provide media content recommendations responsive to the verbal input of the user as characterized by the first text string 212 based, in part, on the past activities of the user when interacting with the unified television application 130, the viewing history of the user, and / or the popularity of media content items of a certain type, classification, category, group or genre.

[0169] In addition, or in the alternative, a TV application may curate or provide media content recommendations responsive to the verbal input of the user based on the context of the verbal input. The media content recommendations by the TV application may be based on previous user inquiries and previous user responses to information and media content recommendations provided by the TV application. The information and media content recommendations provided by the TV application may be based on input received from the user about the media content recommendations and information provided by the TV application to previous user inquiries.

[0170] For example, the unified television application 130 interfacing with the knowledge module 166 may curate or provide media content recommendations further based on previous user verbal input (e.g., questions, commands, comments, responses, or queries) and previous inputs to the unified television application 130 (e.g., questions, comments, responses, or queries). For example, referring to FIG. 2D, the unified television application 130 may provide media content recommendations as media content items 1-4 in slots 219a-d, respectively, in a row 216 in a fourth user interface 215. A slot may include a visual representation of the recommended media content item along with a link to the recommended media content.

[0171] A user may want to further refine or fine-tune the media content recommendations made by a TV application using an interactive verbal exchange or chat session between the user and the TV application using the voice-based television assistant. For example, referring to FIGS. 2D-E, the user may want to further refine or fine-tune the media content recommendations presented in the row 216. The user may continue the interactive conversation with the unified television application 130 by selecting or clicking on a “Click to speak” text entry 218. Once the user clicks on or selects the “Click to speak” textAtty Docket No.0120-705WO1 entry 218, the user may begin speaking into a voice input device, verbally describing what additional criteria the unified television application 130 with the help of the knowledge module 166 may use in determining media content recommendations.

[0172] Referring to FIG.2E, the voice-based TV assistant application 118 may receive the voice input data. The voice-based TV assistant application 118 may use natural language processing to generate a second text string 222 of the received voice data of the verbal description of the criteria the user would like applied to the media content recommendations in a fifth user interface 220. The voice-based TV assistant application 118 may provide the second text string 222 to the unified television application 130 continuing the interactive conversation between the user and the unified television application 130.

[0173] The unified television application 130 may send the second text string 222 to the knowledge module 166. The unified television application 130 interfacing with the knowledge module 166 may fine-tune or refine the media content recommendations based on the described criteria provided by the verbal input of the user.

[0174] For example, the unified television application 130 interfacing with the knowledge module 166 may refine or fine-tune the media content recommendations based on the second text string 222. For example, referring to FIG.2F, the unified television application 130 may provide the updated fine-tuned or refined media content recommendations as media content items 2-4 in slots 228a-c, respectively, in a row 226 in a sixth user interface 225.

[0175] A user may want to continue to further refine or fine-tune the media content recommendations made by a TV application continuing an interactive verbal exchange or chat session between the user and the TV application using the voice-based television assistant. For example, referring to FIGS. 2F-G, the user may want to further refine or fine-tune the media content recommendations presented in the row 226. The user may continue the interactive conversation with the unified television application 130 by selecting or clicking on a “Click to speak” text entry 227. Once the user clicks on or selects the “Click to speak” text entry 227, the user may begin speaking into a voice input device, verbally describing what additional criteria the unified television application 130 with the help of the knowledge module 166 may use in determining media content recommendations.

[0176] Referring to FIG. 2G, the voice-based TV assistant application 118 may receive the voice input data. The voice-based TV assistant application 118 may use natural language processing to generate a third text string 232 of the received voice data of the verbal description of the criteria the user would like applied to the media content recommendations in a seventh user interface 230. The voice-based TV assistant application 118 may provide theAtty Docket No.0120-705WO1 third text string 232 to the unified television application 130 continuing the interactive conversation between the user and the unified television application 130.

[0177] The unified television application 130 may send the third text string 232 to the knowledge module 166. The unified television application 130 interfacing with the knowledge module 166 may further fine-tune or refine the media content recommendations based on the described criteria provided by the verbal input of the user.

[0178] For example, the unified television application 130 interfacing with the knowledge module 166 may further refine or fine-tune the media content recommendations based on the third text string 232. For example, referring to FIG. 2H, the unified television application 130 may provide the further updated fine-tuned or refined media content recommendations as media content item2 and media content item 4 in slot 238a and slot 238b, respectively, in a row 236 in an eighth user interface 235.

[0179] In some implementations, a user may turn on the network-connected display device 104, for example, using the remote control device 105. Upon turning on the network- connected display device 104, the network-connected display device 104 may automatically launch the voice-based TV assistant application 118. When launched, the voice-based TV assistant application 118 may present a ninth user interface 240 as shown in FIG. 2I. The network-connected display device 104 may present the ninth user interface 240 on the display 132. The ninth user interface 240 includes options 242a-e as part of a voice experience for the user. In these implementations, the user may be presented with a voice assistant first experience. For example, selecting option 242e may result in the network-connected display device 104 displaying the second user interface 205 as shown in FIG. 2B. In some implementations, the user may select a classic television (TV) option 244. For example, selecting option 244 may result in the network-connected display device 104 launching the unified television application 130 and displaying the first user interface 200 as shown in FIG. 2A. In some implementations, a user may be presented with a user interface that allows the user to select an option that launches the voice-based TV assistant application 118. Doing so may result in the displaying of the ninth user interface 240 by the network-connected display device 104.

[0180] In some implementations, the voice-based TV assistant application 118 may provide the information and responses of the unified television application 130 to the voice- based TV assistant application 118 as a text string. The voice-based TV assistant application 118 may process the text string to generate spoken words as an audio output of the network- connected display device 104. The audio output may be played on a speaker included in theAtty Docket No.0120-705WO1 network-connected display device 104. The unified television application 130 may provide the spoken words and / or the text string as output to the user responsive to user queries.

[0181] A front end of a TV application (e.g., the unified television application 130, the TV application 110) may include the user interfaces to implement an interactive verbal exchange or chat session between the user and the TV application using the voice-based television assistant (e.g., the voice-based TV assistant application 118, the voice module 134, respectively). The interactive verbal exchange may provide input and feedback to the TV application. For example, referring to FIG.1B, a front end of the unified television application 130 may include the user interfaces (e.g., the second user interface 205, the third user interface 210, the fourth user interface 215, the fifth user interface 220, the sixth user interface 225, the seventh user interface 230, and the eighth user interface 235) to implement an interactive verbal exchange or chat session between the user and the unified television application 130 using the voice-based TV assistant application 118.

[0182] A back end of a TV application may be a server-side TV application. For example, the back end of the unified television application 130 may be the server-side TV application 116 on the server computer 106. A generative AI engine 146 included in the AI module 194 may receive a textual version of the verbal request from the user as input from a middle layer, described in more detail herein. The generative AI engine 146 may generate a response to the request as output. The generative AI engine 146 may provide the output to the server-side TV application 116. The server-side TV application 116 may send the output to the unified television application 130. The output response may include recommended media content, information about the media content, or other information related to the user and their media content requests.

[0183] The generative AI engine 146 may receive a textual version of a verbal request or command from a user (e.g., the first text string 212, the second text string 222, the third text string 232) as input from the server-side TV application 116. The generative AI engine 146 may generate a response to the input request as output. For example, the output may be recommended media content items. The server-side TV application 116 may generate a media content recommendation stream as a sequence of selectable information items that correspond to the recommended media content items.

[0184] The use of generative AI can help further focus and refine the information desired by the user. A TV application may refine the search for the information requested by the user as more knowledge is gained by receiving user responses and feedback on previously provided information. The TV application may filter the information provided to the userAtty Docket No.0120-705WO1 based on user responses and feedback to previously provided information. As described, the TV application may pose a question to the user to further understand what information the user is seeking.

[0185] In some implementations, a middle layer may be a layer between the front end and the back end. The middle layer may include voice input devices and voice modules that may be considered part of an input module. The input to the input module may be the spoken words of the user. In some implementations, the input module may convert the received verbal (voice) data into textual data (e.g., a text string). The input module may provide the text string to the generative AI engine included in the back end. The generative AI engine may generate an output response to the verbal user request based on the textual data received by the generative AI engine and one or more training models used by the generative AI engine. The output response may include information and data related to fulfilling and / or refining or fine- tuning the user request.

[0186] The middle layer may include the parsing module 122 that may parse the output response from the generative AI engine to identify any media content items (e.g., videos, movies, TV shows, audio files, music, etc.) included in the output response. The middle layer may include the UMP 158 that may fetch or gather media content items from a media content provider that sources the media content item. The UMP 158 may also fetch or gather information about the media content item such as a description of the item. The UMP 158 provide this information about the media content item to the AI module 194 for use by the generative AI engine 146 in generating a response to send to the unified television application 130. The response may include but is not limited to text, streaming media content (e.g., movies, TV shows, live video content, sporting events), video and / or audio content (e.g., short-form videos, music), games, and trivia recommended by the generative AI engine 146. In addition, the context module 162 included in the middle layer may determine and maintain or store a context for the spoken user request received by the user input module in association with the verbal user request. The context may be stored in association with an interactive conversation session for the spoken user request. The generative AI engine 146 may use the stored context for the interactive conversation session to further train the models used by the generative AI engine so that the generative AI engine may make better recommendations that are closer to the desired user content. In this way, media content is identified by the application of technical criteria which the generative AI engine has worked out for itself through said training. The output is thus media content that would not otherwise be selected. This providesAtty Docket No.0120-705WO1 a technical effect outside the TV application itself, which when coupled with the purpose and method of selection, fulfils the requirement of technical effect.

[0187] In some implementations, the back end may create a JavaScript Object Notation (JSON) formatted response as output for input to the server-side TV application 116 from the response generated by the generative AI engine. The server-side TV application 116 may send the response to the unified television application 130 for including in a user interface for the unified television application 130. The response may include recommended media content items and information and data related to the recommended media content items. The response may include text, video assets, games, etc. recommended by the AI module 194.

[0188] FIG. 3 illustrates a flowchart 300 depicting example operations of an interactive conversation of a user with a TV application. Although the flowchart 300 of FIG. 3 illustrates the operations in sequential order, it will be appreciated that this is merely an example, and that additional or alternative operations may be included. Further, operations of FIG. 3 and related operations may be executed in a different order than that shown, or in a parallel or overlapping fashion. The operations may define a computer-implemented method. Although the flowchart 300 is described with reference to the system 100 of FIG. 1B, the flowchart 300 may be executed according to any of the figures discussed herein. In some examples, the operations of the flowchart 300 are executed by the server computer 106.

[0189] Operation 302 includes receiving, by a computing device, an indication to launch a voice-based television assistant.

[0190] Operation 304 includes, in response to receiving the indication, launching the voice-based television assistant.

[0191] The launching includes operation 306 that includes displaying a user interface including a prompt for receiving verbal input.

[0192] The launching includes operation 308 that includes receiving first voice data for a first query related to a media content recommendation.

[0193] The launching includes operation 310 that includes sending, by the computing device and to a server computer, the first voice data for the first query.

[0194] The launching includes operation 312 that includes receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query.Atty Docket No.0120-705WO1

[0195] The launching includes operation 314 that includes, in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0196] In some examples, the techniques described herein relate to a method including: receiving, by a computing device, an indication to launch a voice-based television assistant; and in response to receiving the indication, launching the voice-based television assistant including: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0197] In some examples, the techniques described herein relate to a method, wherein launching the voice-based television assistant further includes: sending, by the computing device and to the server computer, the second voice data for the second query, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the method further includes displaying, by a television application executing on the computing device, a selectable information item in a user interface of the television application, the selectable information item being associated with the at least one media content recommendation.

[0198] In some examples, the techniques described herein relate to a method, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

[0199] In some examples, the techniques described herein relate to a method, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

[0200] In some examples, the techniques described herein relate to a method, wherein the received first voice data and the received second voice data are included in a conversation between a user of the computing device and the voice-based television assistant.Atty Docket No.0120-705WO1

[0201] In some examples, the techniques described herein relate to a method, further including receiving, by a microphone of the computing device, the verbal input.

[0202] In some examples, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0203] In some examples, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0204] In some examples, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0205] In some examples, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a computing device cause the at least one processor to execute operations, the operations including: receiving, by the computing device, an indication to launch a voice- based television assistant; and in response to receiving the indication, launching the voice- based television assistant including: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0206] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein launching the voice-based television assistant further includes: sending, by the computing device and to the server computer, the second voice data for the second query, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the operations further include displaying, by a television application executing on the computing device, a selectable information item in a user interface of the television application, the selectable information item being associated with the at least one media content recommendation.Atty Docket No.0120-705WO1

[0207] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

[0208] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

[0209] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the received first voice data and the received second voice data are included in a conversation between a user of the computing device and the voice-based television assistant.

[0210] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, further including receiving, by a microphone of the computing device, the verbal input.

[0211] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0212] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0213] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0214] In some examples, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing executable instructions that execute a unified television application on a network-connected display device, the unified television application configured to: receive an indication to launch a voice-based television assistant; and in response to receiving the indication, launch the voice- based television assistant including: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending the first voice data for the first query to a server computer; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response toAtty Docket No.0120-705WO1 receiving the response, receiving second voice data for a second query related to the media content recommendation.

[0215] In some examples, the techniques described herein relate to a system, wherein launching the voice-based television assistant further includes: sending the second voice data for the second query to the server computer, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the unified television application is further configured to display a selectable information item in a user interface of the unified television application, the selectable information item being associated with the at least one media content recommendation.

[0216] In some examples, the techniques described herein relate to a system, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

[0217] In some examples, the techniques described herein relate to a system, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

[0218] In some examples, the techniques described herein relate to a system, wherein the received first voice data and the received second voice data are included in a conversation between a user of the system and the voice-based television assistant.

[0219] In some examples, the techniques described herein relate to a system, wherein the unified television application is further configured to receive, by a microphone of the system, the verbal input.

[0220] In some examples, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0221] These examples can be combined in any suitable combination.

[0222] FIG. 4 illustrates a flowchart 400 depicting example operations of an interactive conversation of a user with a TV application. Although the flowchart 400 of FIG. 4 illustrates the operations in sequential order, it will be appreciated that this is merely an example, and that additional or alternative operations may be included. Further, operations of FIG. 4 and related operations may be executed in a different order than that shown, or in a parallel or overlapping fashion. The operations may define a computer-implemented method. Although the flowchart 400 is described with reference to the system 100 of FIG. 1B, theAtty Docket No.0120-705WO1 flowchart 400 may be executed according to any of the figures discussed herein. In some examples, the operations of the flowchart 300 are executed by the network-connected display device 104.

[0223] Operation 402 includes receiving, by a server computer and from a computing device, first voice data for a first query related to a media content recommendation.

[0224] Operation 404 includes generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query.

[0225] Operation 406 includes sending, by the server computer and to the computing device, the response to the computing device.

[0226] Operation 408 includes receiving second voice data for a second query responsive to the response.

[0227] Operation 410 includes generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query.

[0228] Operation 412 includes sending the at least one media content recommendation to the computing device.

[0229] In some examples, the techniques described herein relate to a method including: receiving, by a server computer and from a computing device, first voice data for a first query related to a media content recommendation; generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; sending, by the server computer and to the computing device, the response to the computing device; receiving second voice data for a second query responsive to the response; generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and sending the at least one media content recommendation to the computing device.Atty Docket No.0120-705WO1

[0230] In some examples, the techniques described herein relate to a method, further including: generating a text string for the first voice data; and providing the text string to a generative artificial intelligence engine in the server computer.

[0231] In some examples, the techniques described herein relate to a method, further including: generating, by the generative artificial intelligence engine, the response based on the text string; and parsing the response to identify at least one media content item associated with the media content recommendation.

[0232] In some examples, the techniques described herein relate to a method, further including: fetching at least one of the media content item and a description of the media content item; and sending the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

[0233] In some examples, the techniques described herein relate to a method, wherein generating the response includes creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

[0234] In some examples, the techniques described herein relate to a method, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the method further includes storing a context for the conversation session, the context for use in determining future media content recommendations for the user.

[0235] In some examples, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0236] In some examples, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0237] In some examples, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0238] In some examples, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations including: receiving, by the server computer and from a computing device, first voice data for a first query related to a media content recommendation; generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; sending, by the server computer, the response to the computing device; receiving second voice data for a second queryAtty Docket No.0120-705WO1 responsive to the response; generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and sending the at least one media content recommendation to the computing device.

[0239] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include: generating a text string for the first voice data; and providing the text string to a generative artificial intelligence engine in the server computer.

[0240] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include: generating, by the generative artificial intelligence engine, the response based on the text string; and parsing the response to identify at least one media content item associated with the media content recommendation.

[0241] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include: fetching at least one of the media content item and a description of the media content item; and sending the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

[0242] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein generating the response includes creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

[0243] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the operations further include storing a context for the conversation session, the context for use in determining future media content recommendations for the user.

[0244] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.Atty Docket No.0120-705WO1

[0245] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0246] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0247] In some examples, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receive first voice data for a first query related to a media content recommendation from a computing device; generate a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; send the response to the computing device; receive second voice data for a second query responsive to the response; generate at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and send the at least one media content recommendation to the computing device.

[0248] In some examples, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to: generate a text string for the first voice data; and provide the text string to a generative artificial intelligence engine in the system.

[0249] In some examples, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to: generate, by the generative artificial intelligence engine, the response based on the text string; and parse the response to identify at least one media content item associated with the media content recommendation.

[0250] In some examples, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to: fetch at least one of the media content item and a description of the media content item; and send the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.Atty Docket No.0120-705WO1

[0251] In some examples, the techniques described herein relate to a system, wherein generating the response includes creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

[0252] In some examples, the techniques described herein relate to a system, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the instructions when executed by the at least one processor further cause the system to store a context for the conversation session, the context for use in determining future media content recommendations for the user.

[0253] In some examples, the techniques described herein relate to a system, wherein the computing device is a network-connected display device.

[0254] In some examples, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0255] In some examples, the techniques described herein relate to a system, wherein the computing device is a mobile computing device.

[0256] These examples can be combined in any suitable combination.

[0257] FIGS.5A-E are illustrations of example user interfaces that a user may interact with to provide user preferences for or interests in characteristics or criteria associated with media content, according to implementations described throughout this disclosure. FIGS.5A- E are described with reference to FIGS.1A-B.

[0258] A user may provide a TV application with preferences for media content of interest to the user. The preferences may be related to one or more characteristics of the media content. The preferences may relate to metadata associated with the media content. For example, referring to FIG.5A, the user may launch the unified television application 130 on the network-connected display device 104. The unified television application 130 may display the first user interface 500 on the display 132. The user may use the remote control device 105 to interact with the first user interface 500. The user may click on or select a settings icon 502.

[0259] Responsive to the selection of the settings icon 502, referring to FIG.5B, the unified television application 130 may open a second user interface 510 allowing the user to begin identifying and selecting media content preferences. The user may begin to select preferences by selecting or clicking on a preferences button 512.

[0260] Responsive to the selection of the preferences button 512, referring to FIG.5C, the unified television application 130 may open a third user interface 515 allowing the user to select preference categories associated with media content. For example, the user may selectAtty Docket No.0120-705WO1 a genre category by selecting or clicking on a genre button 516. The user may want to identify preferred genres of interest for media content.

[0261] Responsive to the selection of the genre button 516, referring to FIG.5D, the unified television application 130 may open a fourth user interface 520 allowing the user to select from a list of genres 522. For example, the user may select or click on an action button 524 selecting “action” as a preferred genre for media content.

[0262] FIG. 5C illustrates an example user interface 515 that allows a user to select preference categories associated with media content. As shown in FIG.5C, the user may select other and / or additional preference categories such as, for example, a media content type category associated with a type button 517 and an actors category associated with an actors button 518. Once a preference category is selected, the TV application (e.g., unified television application 130) may provide a user interface for entering information and data for the preference category.

[0263] For example, referring to FIG. 5C, a user may select an actors category by selecting or clicking on the actors button 518. Responsive to the selection of the actors button 518, referring to FIG.5E, the unified television application 130 may open a fifth user interface 525 allowing the user enter text for or speak the name of an actor.

[0264] In some implementations, the unified television application 130 may send the selected user preferences to the knowledge module 166 for associating with the account of the user. The knowledge module 166 may generate media content recommendations for associating with an account of a user based on a multi-dimensional user activity characteristic associated with the account of the user, information associated with media content items provided by the media content providers 160, and the selected user preferences for media content.

[0265] FIG. 6 is an illustration of media content preference categories for three different users. For example, a first user 602 selected comedy as a preferred genre and John Doe as a preferred actor. A second user 604 selected action as a preferred genre and Jane Doe as a preferred actor. A third user 606 selected cyberpunk as a preferred genre and Jack Smith as a preferred actor.

[0266] In some implementations, a TV application may interface with a generative artificial intelligence (AI) system. The generative AI system may use a large language model (LLM) to generate personalized media content recommendations for the user. Examples of a generative AI system which may be used as described herein include systems based on the Language Model for Dialog Applications (LaMDA), Gemini, or Generative Pre-trainedAtty Docket No.0120-705WO1 Transformer 4 (GPT-4) families of large language models, or e.g., a generative AI system such as Bard. For example, the generative AI system may generate personalized media content recommendations based on user preferences or interests in particular genres, actors, actresses, musicians, themes, etc. For example, the unified television application 130 may interface with the server-side TV application 116 as described herein. The server-side TV application 116 may interface with the AI module 194. For example, the AI module 194 may use generative AI to generate personalized media content recommendations for a user based on the selected user preferences or interests in particular genres, actors, actresses, musicians, themes, etc.

[0267] FIG. 7 illustrates an example of a TV application providing the same media content recommendation to two different users based on different user preferences. Referring to FIG.6, the first user 602 selected comedy as a preferred genre and John Doe as a preferred actor. The second user 604 selected action as a preferred genre and Jane Doe as a preferred actor.

[0268] Referring to FIG.1B, in some implementations, the server-side TV application 116 may receive preferences for media content as selected by a user while interacting with the unified television application 130 as described with reference to FIGS.5A-E. The server- side TV application 116 may provide the received user preferences to the AI module 194 for use by the generative AI engine 146. The generative AI engine 146 may generate a personalized media content recommendation for the user for a media content item based on an affinity between the media content item and the preferences of the user.

[0269] The UMP 158 may fetch or gather media content items from a media content provider that sources the media content item. The UMP 158 may also fetch or gather information about the media content item that may include a description of the item and other metadata associated with the media content item such as a genre, people associated with the media content items such as actors, producers, directors, musicians, a theme, a title, the provider(s) of the media content, etc. The UMP 158 may provide the media content item and the metadata associated as an input data stream to the parsing module 122. The parsing module 122 may parse the input stream to identify and associate the individual metadata items with the media content item. The parsing module 122 may provide the individual metadata items for the associated media content item to the AI module 194 for use by the generative AI engine 146 when generating the personalized media content recommendation for the user.

[0270] A generative AI system may generate a personalized media content recommendation for two or more users that may recommend the same media content item toAtty Docket No.0120-705WO1 each user though the recommendation may be based on different criteria or indicated user preferences. The generative AI system may generate a recommendation for the same media content item for multiple different users based on an affinity between the item and the preferences of each user. For example, referring to FIG. 7, the first user 602 may prefer or have an interest in media content in a first genre such as comedy. The first user 602 may prefer or have an interest in media content items associated with a first actor (e.g., John Doe). The second user 604 may prefer or have an interest in media content in a second genre such as action. The second user 604 may prefer or have an interest in media content items associated with a second actor (e.g., Jane Doe). For example, the generative AI engine 146 may recommend the same media content item (e.g., movie 1) to the first user 602 and the second user 604 because a genre associated with the media content item (the movie) is comedy (a preference of the first user 602) and an actor associated with the media content item (e.g., the movie) is Jane Doe (a preference of the second user 604). Therefore, though the first user 602 and the second user 604 may have different preferences for or interests in preferred media content, in some implementations, the generative AI system may recommend the same media content item to both the first user 602 and the second user 604 based on an affinity of the item with the preferences of each user.

[0271] In some implementations, though the AI module 194 may recommend the same media content to multiple different users, the generative AI engine 146 may generate different descriptive text for the recommended media content item for each user based on the preferences or interests of the user for the media content item. For example, descriptive text 702 for the movie for the first user 602 reflects the interest or preference of the user for comedies. Descriptive text 704 for the movie for the second user 604 reflects the interest or preference of the user for the actor, Jane Doe.

[0272] Referring to FIG.1B, in some implementations, the server computer 106 may include a topic server module164. The topic service 164 may receive information and data related to preferences and interests of a user. For example, the topic service 164 may receive the preferences of a user for media content from the server-side TV application 116. The information and data may include but is not limited to preferences and interests of the user as they relate to the genres, actors, actresses, musicians, themes, and other metadata associated with media content. The UMP 158 may gather and receive media content. The UMP 158 may determine metadata associated with a media content item that may include but is not limited to a type of the media content (e.g., movie, TV show, music video, etc.), a category or genre associated with the media content item (e.g., comedy, action, romance,Atty Docket No.0120-705WO1 documentary, etc.), actors, actresses, musicians, directors, producers, cinematographers and other individuals or cast members involved with the production, sale and distribution of the media content item, characters (e.g., comic book character, cartoon character, etc.), and one or more themes associated with the media content item (e.g., holiday movie, summer music video, etc.).

[0273] The generative AI engine 146 may receive the metadata for the media content item from the UMP 158. In addition, or in the alternative, the generative AI engine 146 may receive the information and data related to the preferences and interests of individual users. The generative AI engine 146 may match preferences and interests for a user with metadata for at least one media content item for recommendation to the user by the unified television application 130. The generative AI engine 146 may create or generate a customized description of the recommended media content item based on the preferences and interests of the user that are matched with the metadata of the media content item.

[0274] The generative AI engine 146 may generate an output text string that is a description of the recommended media content item based on the preferences and interests of the user that match the metadata for the media content item. The generative AI engine 146 may send the customized or personalized description of the media content item to the unified television application 130. The unified television application 130 may display the text of the personized description of the media content item along with a selectable information item in a user interface of the unified television application 130. For example, the unified television application 130 may display the descriptive text 702 along with a selectable information item for the media content item (e.g., a watch now button 706) in a user interface 708 of the unified television application 130 for the first user 602. The unified television application 130 may display the descriptive text 704 along with a selectable information item for the media content item (e.g., a watch now button 710) in a user interface 712 of the unified television application 130 for the second user 604.

[0275] FIG. 8 is a diagram showing a description of an example process 800 for generating customized descriptive text for a media content recommendation. Referring to FIG. 1B, the example process 800 may be performed by the server computer 106. The process 800 is for generating the customized descriptive text (e.g., descriptive text 702) for the first user 602. Referring to FIG. 1B, the topic service 164 may receive user interests and preferences from the server-side TV application 116. The server-side TV application 116 may receive the user interests and preferences from the unified television application 130.Atty Docket No.0120-705WO1

[0276] In a first step 802, the topic service 164 may determine that the first user 602 is interested in media content in the action genre category. The generative AI engine 146 may receive or obtain the user interest(s) from the topic service 164. In a second step 804, the generative AI engine 146 may receive or obtain media content metadata from the UMP 158. For example, the media content item may be a movie. The UMP 158 may receive one or genres the media content item may be categorized or associated with, one or more actors the media content item may be associated with. In a third step 806, the generative AI engine 146 may match interest or preferences of the first user 602 with the metadata for the media content. In a fourth step 808, the generative AI engine 146 may generate or create a unique hook or association from the first user 602 to the media content item. In a fifth step 810, the generative AI engine 146 may create or generate the descriptive text 702 that may be, for example, a sixty character synopsis for the recommended media content item that reflects the affinity of the first user 602 (the preferences or interest of the first user 602). In some implementations, the character length may be more than sixty (e.g., eighty, one hundred). In some implementations, the character length may be less than sixty (e.g., fifty, forty).

[0277] FIG.9 is a block diagram 900 of an example process (e.g., the example process 800) for generating customized descriptive text for a media content recommendation for one or more users as performed by, for example, the system 100 as shown in FIG.1B. For example, referring to FIGS.1B, 7, 8, and 9, the topic service 164 may determine that the first user 602 is interested in movies in the comedy genre or category with actor John Doe. The topic service 164 may determine that the second user 604 is interested in movies in the action genre or category with actor Jane Doe. The topic service 164 may determine that the third user 606 is interested in movies in the cyberpunk genre or category with actor Jack Smith.

[0278] The UMP 158 may receive media content metadata for the media content item that is the movie titled “John Doe’s Adventures” (e.g., movie title 714). The UMP 158 may associate one or more genres and one or more actors with the media content item. For example, the UMP 158 may associate the action genre and the actor John Doe with the movie titled “John Doe’s Adventures” (e.g., movie title 714) based on metadata associated with the movie. The AI module 194 may receive output of the topic service 164 and the output of the UMP 158. The AI module 194 may receive the metadata about the movie “John Doe’s Adventures” from the UMP 158. The AI module 194 may match the interest of the first user 602 in movies with the actor John Doe with the metadata for the movie “John Doe’s Adventures.” The AI module 194 may match the interest of the second user 604 in action movies with the metadata for the movie “John Doe’s Adventures.”Atty Docket No.0120-705WO1

[0279] The AI module 194 may generate a request 902 and provide the request 902 to the generative AI engine 146. The generative AI engine 146 may generate a sixty character long synopsis for the movie “John Doe’s Adventures” in the action genre highlighting the actor John Doe. The generative AI engine 146 may create or generate an output text string 904 as a personalized description of the recommended media content item (e.g., the movie “John Doe’s Adventures”) for the second user 604 and for the first user 602 based on the received input from the AI module 194. The output text string 904 may highlight the preferences and interests for the first user 602 and the second user 604 that match the metadata for the recommended media content item. For example, the generative AI engine 146 may create or generate the output text string 904 to read: “John Doe as a tough cop who fights corruption in this action movie.” The output text string generated by the generative AI engine 146 may include the name of the actor of interest to the first user 602 (e.g., John Doe) and the genre of interest to the second user 604 (e.g., action). The unified television application 130 may display the output text string 904 along with a selectable information item for the movie “John Doe’s Adventures” in the user interface 708 of the unified television application 130 for the first user 602 as the descriptive text 702. The unified television application 130 may display the output text string 904 along with a selectable information item for the movie “John Doe’s Adventures” in the user interface 712 of the unified television application 130 for the second user 604 as the descriptive text 704.

[0280] In some implementations, the AI module 194 may match preferences and interests for more than one user (two, three, or more users) with metadata for a single media content item for recommendation to each user by the server-side TV application 116. The AI module 194 may create a request for the generative AI engine 146 to generate a different customized descriptions of the recommended media content item that is personalized for each user based on the preferences and interests of each user that are matched with the metadata of the media content item. The generative AI engine 146 may generate an output text string that may be a different description of the same recommended media content item. The generative AI engine 146 may send the customized or personalized description of the media content item to the server-side TV application 116 for each user. The server-side TV application 116 may provide the unified television application 130 with the description. The unified television application 130 may display the text of the personized description of the media content item along with a selectable information item in the user interface 112 of the unified television application 130 for the user.

[0281] For example, the topic service 164 may determine that first user 602 isAtty Docket No.0120-705WO1 interested in comedy movies with actor John Doe, and that second user 604 is interested in action movies with actress Jane Doe. The UMP 158 associates the action genre, the comedy genre, the actor John Doe, and the actress Jane Doe with the movie “John Doe’s Adventures” based on metadata associated with movie. The AI module 194 receives the information and data associated with the first user 602 from the topic service 164. The AI module 194 receives the information and data associated with the second user 604 from the topic service 164. The AI module 194 receives the metadata about the movie “John Doe’s Adventures” from the UMP 158. The AI module 194 may match the interest of the first user 602 in movies with the actor John Doe with the metadata for the movie “John Doe’s Adventures”. The AI module 194 may match the interest of the second user 604 in action movies with the metadata for the movie “John and Jane’s Funny Adventures.”

[0282] The AI module 194 may create a request for the generative AI engine 146 to generate a sixty character long synopsis for the movie “John Doe’s Adventures” highlighting the actor John Doe for sending to the first user 602. The AI module 194 may create a request for the generative AI engine 146 to generate a sixty character long synopsis for the movie “John Doe’s Adventures” highlighting the action genre for sending to the second user 604. The generative AI engine 146 may generate two different output text strings as a personalized description of the recommended “John Doe’s Adventures” based on the received input requests.

[0283] The descriptive text 702 may highlight the preferences and interests of the first user 602 that matched the metadata for the recommended media content item. For example, the generative AI engine 146 may generate a first output text string “John Doe and his friends team up as advocates to fight the engineering college system.” The first output text string generated by the generative AI module includes the name of the actor of interest to the first user 602 (e.g., John Doe). The unified television application 130 may display the first output text string for the movie “John Doe’s Adventures” as the descriptive text 702. For example, the generative AI engine 146 may generate a second output text string “Three friends fight the engineering college system in this action movie.” The second output text string generated by the generative AI engine 146 includes the genre of interest to the second user 604 (e.g., action). The unified television application 130 may display the second output text string for the movie “John Doe’s Adventures” as the descriptive text 704.

[0284] FIG.10 illustrates a flowchart 1000 depicting example operations of generating a personalized description of a media content item. Although the flowchart 1000 of FIG.10 illustrates the operations in sequential order, it will be appreciated that this is merely anAtty Docket No.0120-705WO1 example, and that additional or alternative operations may be included. Further, operations of FIG.10 and related operations may be executed in a different order than that shown, or in a parallel or overlapping fashion. The operations may define a computer-implemented method. Although the flowchart 1000 is described with reference to the system 100 of FIG. 1B, the flowchart 1000 may be executed according to any of the figures discussed herein. In some examples, the operations of the flowchart 1000 are executed by the server computer 106.

[0285] Operation 1002 includes receiving, by a server computer, information and data related to preferences of a user for media content.

[0286] Operation 1004 includes identifying metadata associated with a media content item.

[0287] Operation 1006 includes determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item.

[0288] Operation 1008 includes generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content.

[0289] Operation 1010 includes sending, by the server computer and to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

[0290] In some examples, the techniques described herein relate to a method including: receiving, by a server computer, information and data related to preferences of a user for media content; identifying metadata associated with a media content item; determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and sending, by the server computer and to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

[0291] In some examples, the techniques described herein relate to a method, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.Atty Docket No.0120-705WO1

[0292] In some examples, the techniques described herein relate to a method, wherein the personalized description is a text string.

[0293] In some examples, the techniques described herein relate to a method, wherein the method further includes generating a request for the personalized description for the media content item, the request specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

[0294] In some examples, the techniques described herein relate to a method, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

[0295] In some examples, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0296] In some examples, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0297] In some examples, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0298] In some examples, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations including: receiving information and data related to preferences of a user for media content; identifying metadata associated with a media content item; determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and sending, to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

[0299] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

[0300] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the personalized description is a text string.

[0301] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include generating a request for the personalized description for the media content item, the request specifying: a characterAtty Docket No.0120-705WO1 length for the personalized description; and at least one preference from the preferences of the user for media content.

[0302] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

[0303] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0304] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0305] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0306] In some examples, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receiving information and data related to preferences of a user for media content; identify metadata associated with a media content item; determine that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generate a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and send, to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

[0307] In some examples, the techniques described herein relate to a system, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

[0308] In some examples, the techniques described herein relate to a system, wherein the personalized description is a text string.

[0309] In some examples, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to generate a request for the personalized description for the media content item, the requestAtty Docket No.0120-705WO1 specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

[0310] In some examples, the techniques described herein relate to a system, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

[0311] In some examples, the techniques described herein relate to a system, wherein the computing device is a network-connected display device.

[0312] In some examples, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0313] In some examples, the techniques described herein relate to a system, wherein the computing device is a mobile computing device.

[0314] These examples can be combined in any suitable combination.

[0315] FIGS.11A-J are illustrations of example user interfaces for an interactive trivia game between a user and a TV application, according to implementations described throughout this disclosure. FIGS.11A-J are described with reference to FIGS.1A-B.

[0316] A user may interface with a user interface on a TV application, selecting to participate in trivia games related to selected media content items. For example, using the remote control device 105, the user may select or click on an icon or text entry to open a user interface to begin a trivia game with the TV application. For example, referring to FIG.11A, the user may launch the unified television application 130 on the network-connected display device 104. The unified television application 130 may display a first user interface 1100 on the display 132. The user may use the remote control device 105 to interact with the first user interface 1100. The user may click on or select a “Trivia Game” text entry 1102. As shown in FIG. 11A, the trivia game questions will be for trivia associated with a first media content item 1104.

[0317] Responsive to the selection of the “Trivia Game” text entry 1102, referring to FIG.11B, the unified television application 130 may display a second user interface 1105 on the display 132. The second user interface 1105 may present the user with one or more trivia questions (e.g., three questions, five questions, etc.) for the selected media content item. For example, the second user interface 1105 includes a first trivia question 1106. In some implementations, the user interface may present the user with at least two choices for possible answers to a trivia question. For example, the second user interface 1105 includes a first answer choice (e.g., answer 1 button 1108a) and a second answer choice (e.g., answer 2 button 1108b).Atty Docket No.0120-705WO1

[0318] In some implementations, the user interface may request the user enter an answer to the trivia question. The user may enter a text response using a mobile computing device (e.g., the mobile computing device 102) interfaced with the unified television application 130. The mobile computing device 102 may act as a virtual remote control for the network-connected display device 104. The mobile computing device 102 may present a virtual keyboard for entering the answer in the second user interface 1105. In some implementations, a user may interface with a television voice assistant (e.g., the voice-based TV assistant application 118) and may speak the answer into a remote control device (e.g., the remote control device 105). The voice-based TV assistant application 118 may facilitate providing a text version of the spoken answer to the unified television application 130 as described herein.

[0319] Responsive to the selection of the button 1108a, referring to FIG. 11C, the unified television application 130 may display a third user interface 1110 on the display 132. The third user interface 1110 may provide an indication as to whether the answer selected by the user to the first trivia question 1106 is the correct answer. For example, the third user interface 1110 indicates that the first answer choice selected by the user is the wrong answer (e.g., indication 1112). The third user interface 1110 may also include a game progress indicator 1114. In the example shown in FIG. 11C, the user has answered a first of three possible trivia questions. The user may select or click on a next button 1113 to continue to play the trivia game.

[0320] Responsive to the selection of the next button 1113, referring to FIG.11D, the unified television application 130 may display a fourth user interface 1115 on the display 132. The fourth user interface 1115 may present the user with a second trivia question 1116. In some implementations, the user interface may present the user with at least two choices for possible answers to a trivia question. For example, the fourth user interface 1115 includes a first answer choice (e.g., answer 1 button 1118a) and a second answer choice (e.g., answer 2 button 1118b).

[0321] Responsive to the selection of the answer 1 button 1118a, referring to FIG. 11E, the unified television application 130 may display a fifth user interface 1120 on the display 132. The fifth user interface 1120 may provide an indication as to whether the answer selected by the user to the second trivia question 1116 is the correct answer. For example, the fifth user interface 1120 indicates that the second answer choice selected by the user is the correct answer (e.g., indication 1122). The fifth user interface 1120 may also include a game progress indicator 1124. In the example shown in FIG.11E, the user has answered a two ofAtty Docket No.0120-705WO1 three possible trivia questions. The user may select or click on a next button 1123 to continue to play the trivia game.

[0322] Responsive to the selection of the next button 1123, referring to FIG.11F, the unified television application 130 may display a sixth user interface 1125 on the display 132. The sixth user interface 1125 may present the user with a third trivia question 1126. In some implementations, the user interface may present the user with at least two choices for possible answers to a trivia question. For example, the sixth user interface 1125 includes a first answer choice (e.g., answer 1 button 1128a) and a second answer choice (e.g., answer 2 button 1128b).

[0323] Responsive to the selection of the answer 1 button 1128a, referring to FIG. 11G, the unified television application 130 may display a seventh user interface 1130 on the display 132. The seventh user interface 1130 may provide an indication as to whether the answer selected by the user to the third trivia question 1126 is the correct answer. For example, the seventh user interface 1130 indicates that the first answer choice selected by the user is the correct answer (e.g., indication 1132). The seventh user interface 1130 may also include a game progress indicator 1134. In the example shown in FIG. 11G, the user has answered a three of three possible trivia questions. The user may select or click on a next button 1133 to continue to play the trivia game.

[0324] In some implementations, a TV application may use generative AI to help generate questions for the trivia game. For example, referring to FIGS. 1B and 11A-G, the unified television application 130 may request information for a selected media content item (e.g., first media content item 1104). The request may be for information (e.g., facts) related to characteristics of the media content item such as cast members, geographic location, genre, plot twists, scene content, dialog, etc. The server-side TV application 116 may receive the request from the unified television application 130). The server-side TV application 116 may interface with the AI module 194 to have the generative AI engine 146 suggest facts for trivia questions. For example, the AI module 194 may receive a request from the server-side TV application 116 to generate a question about the first media content item 1104 as it relates to a particular characteristic of the media content item, such as an actor. The server-side TV application 116 may also request a number of possible answers for the question that include the correct answer. The AI module 194 may receive the request from the server-side TV application 116 and provide the request to the generative AI engine 146. The generative AI engine 146 may gather the information and data needed to formulate the trivia question for the media content item that is related to the actor and to provide additional answers to theAtty Docket No.0120-705WO1 trivia question that are not the correct answer but that would make sense to someone with knowledge of the media content item and the actor as being a possible correct answer.

[0325] The generative AI engine 146 may interface with the trivia question generator 148. The trivia question generator 148 may receive the information from the generative AI engine 146 for use in formulating a question. The trivia question generator 148 may formulate the trivia question, including at least two possible answers to the question that include the correct answer. The trivia question generator 148 may provide or send the trivia questions and possible answers to the unified television application 130 to present in one or more user interfaces (e.g., UI 112) on the display 132 as described herein.

[0326] The unified television application 130 may receive the answer of the user to the trivia questions. The unified television application 130 may send or provide the answers to the trivia question to the server-side TV application 116. The server-side TV application 116 may generate a score to the user for the trivia game, The score may take into consideration additional answers to other trivia questions for the same media content item. The server-side TV application 116 may calculate an overall score of the trivia games the user has completed. The server-side TV application 116 may provide or send this score to the unified television application 130 for display in a user interface (e.g., the UI) of the display 132.

[0327] FIG.11H is an illustration of an example eighth user interface 1135 provided by the unified television application 130 that includes a score button 1136 and a leader board button 1138. For example, when a user has completed a trivia game, the unified television application 130 may display the eighth user interface 1135. The user may select or click on the score button 1136. Responsive to the selection of the score button 1136, referring to FIG. 11I, the unified television application 130 may display a ninth user interface 1140 on the display 132. The ninth user interface 1140 may present the score of the last trivia game played by the user and the overall score of the user for trivia game play in a score indicator area 1142. The ninth user interface 1140 may include a done button 1143 and a leader board button 1144. The user may select the done button 1143 to return to the first user interface 1100. The user may select the leader board button 1144.

[0328] In addition, or in the alternative, referring to FIG.11H, the user may select the leader board button 1138. Responsive to the selection of the leader board button 1144 or the leader board button 1138, referring to FIG. 11J, the unified television application 130 may display a tenth user interface 1145 on the display 132. The tenth user interface 1145 may provide a trivia score leader board 1146. For example, the server-side TV application 116 may create or generate the trivia score leader board 1146. The server-side TV application 116 mayAtty Docket No.0120-705WO1 provide or send the trivia score leader board 1146 to the unified television application 130 for presenting in the tenth user interface 1145 on the display 132. The trivia score leader board 1146 may show a user how the overall score of the user for trivia games compares to other users or players of the trivia games.

[0329] The tenth user interface 1145 may include a done button 1147 and a scores button 1148. The user may select the done button 1147 to return to the first user interface 1100. The user may select the scores button 1148. Selecting the scores button 1148 may direct the user to the ninth user interface 1140.

[0330] FIG. 12 illustrates a flowchart 1200 depicting example operations of the implementation of a trivia game for media content items of interest to a user. Although the flowchart 1200 of FIG.12 illustrates the operations in sequential order, it will be appreciated that this is merely an example, and that additional or alternative operations may be included. Further, operations of FIG.12 and related operations may be executed in a different order than that shown, or in a parallel or overlapping fashion. The operations may define a computer- implemented method. Although the flowchart 1200 is described with reference to the system 100 of FIG.1B, the flowchart 1200 may be executed according to any of the figures discussed herein. In some examples, the operations of the flowchart 1200 are executed by the server computer 106.

[0331] Operation 1202 includes receiving, by a server computer, a request for a trivia question for a media content item.

[0332] Operation 1204 includes sending, by the server computer and to a computing device, a trivia question for display in a user interface on the computing device.

[0333] Operation 1206 includes receiving an answer to the trivia question.

[0334] Operation 1208 includes determining whether the answer is a correct answer.

[0335] Operation 1210 includes sending a message as to whether the answer is the correct answer for display in the user interface.

[0336] In some examples, the techniques described herein relate to a method including: receiving, by a server computer, a request for a trivia question for a media content item; sending, by the server computer and to a computing device, a trivia question for display in a user interface on the computing device; receiving an answer to the trivia question; determining whether the answer is a correct answer; and sending a message as to whether the answer is the correct answer for display in the user interface.Atty Docket No.0120-705WO1

[0337] In some examples, the techniques described herein relate to a method, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

[0338] In some examples, the techniques described herein relate to a method, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

[0339] In some examples, the techniques described herein relate to a method, further including sending along with the trivia question at least two answers to the trivia question for display in the user interface.

[0340] In some examples, the techniques described herein relate to a method, wherein the computing device is a network-connected display device.

[0341] In some examples, the techniques described herein relate to a method, wherein the network-connected display device is a smart television.

[0342] In some examples, the techniques described herein relate to a method, wherein the computing device is a mobile computing device.

[0343] In some examples, the techniques described herein relate to a non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations including: receiving, by the server computer, a request for a trivia question for a media content item; sending a trivia question to a computing device for display in a user interface on the computing device; receiving an answer to the trivia question; determining whether the answer is a correct answer; and sending a message as to whether the answer is the correct answer for display in the user interface.

[0344] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

[0345] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

[0346] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the operations further include sending along with the trivia question at least two answers to the trivia question for display in the user interface.Atty Docket No.0120-705WO1

[0347] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a network-connected display device.

[0348] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the network-connected display device is a smart television.

[0349] In some examples, the techniques described herein relate to a non-transitory computer-readable medium, wherein the computing device is a mobile computing device.

[0350] In some examples, the techniques described herein relate to a system including: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receive a request for a trivia question for a media content item; send a trivia question to a computing device for display in a user interface on the computing device; receive an answer to the trivia question; determine whether the answer is a correct answer; and send a message as to whether the answer is the correct answer for display in the user interface.

[0351] In some examples, the techniques described herein relate to a system, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

[0352] In some examples, the techniques described herein relate to a system, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

[0353] In some examples, the techniques described herein relate to a system, wherein the instructions when executed by the at least one processor further cause the system to send along with the trivia question at least two answers to the trivia question for display in the user interface.

[0354] In some examples, the techniques described herein relate to a system, wherein the computing device is a network-connected display device.

[0355] In some examples, the techniques described herein relate to a system, wherein the network-connected display device is a smart television.

[0356] In some examples, the techniques described herein relate to a system, wherein the computing device is a mobile computing device.

[0357] These examples can be combined in any suitable combination.

[0358] Various implementations of the systems and techniques described here can be realized in digital electronic circuitry, integrated circuitry, specially designed ASICsAtty Docket No.0120-705WO1 (application specific integrated circuits), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0359] These computer programs (also known as programs, software, software applications or code) include machine instructions for a programmable processor and can be implemented in a high-level procedural and / or object-oriented programming language, and / or in assembly / machine language. As used herein, the terms “machine-readable medium” “computer-readable medium” refers to any computer program product, apparatus and / or device (e.g., magnetic discs, optical disks, memory, Programmable Logic Devices (PLDs)) used to provide machine instructions and / or data to a programmable processor, including a non-transitory machine-readable medium that receives machine instructions as a machine- readable signal. The term “machine-readable signal” refers to any signal used to provide machine instructions and / or data to a programmable processor.

[0360] To provide for interaction with a user, the systems and techniques described here can be implemented on a computer having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0361] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a client computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or non-transitory medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (“LAN”), a wide area network (“WAN”), and the Internet.Atty Docket No.0120-705WO1

[0362] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other.

[0363] In this specification and the appended claims, the singular forms "a," "an" and "the" do not exclude the plural reference unless the context clearly dictates otherwise. Further, conjunctions such as “and,” “or,” and “and / or” are inclusive unless the context clearly dictates otherwise. For example, “A and / or B” includes A alone, B alone, and A with B. Further, connecting lines or connectors shown in the various figures presented are intended to represent example functional relationships and / or physical or logical couplings between the various elements. Many alternative or additional functional relationships, physical connections or logical connections may be present in a practical device. Moreover, no item or component is essential to the practice of the embodiments disclosed herein unless the element is specifically described as “essential” or “critical”.

[0364] Terms such as, but not limited to, approximately, substantially, generally, etc. are used herein to indicate that a precise value or range thereof is not required and need not be specified. As used herein, the terms discussed above will have ready and instant meaning to one of ordinary skill in the art.

[0365] Moreover, use of terms such as up, down, top, bottom, side, end, front, back, etc. herein are used with reference to a currently considered or illustrated orientation. If they are considered with respect to another orientation, it should be understood that such terms must be correspondingly modified.

[0366] Further, in this specification and the appended claims, the singular forms "a," "an" and "the" do not exclude the plural reference unless the context clearly dictates otherwise. Moreover, conjunctions such as “and,” “or,” and “and / or” are inclusive unless the context clearly dictates otherwise. For example, “A and / or B” includes A alone, B alone, and A with B.

[0367] Although certain example methods, apparatuses and articles of manufacture have been described herein, the scope of coverage of this patent is not limited thereto. It is to be understood that terminology employed herein is for the purpose of describing particular aspects and is not intended to be limiting. On the contrary, this patent covers all methods, apparatus and articles of manufacture fairly falling within the scope of the claims of this patent.Atty Docket No.0120-705WO1

[0368] Further to the descriptions above, a user may be provided with controls allowing the user to make an election as to both if and when systems, programs, or features described herein may enable collection of user information (e.g., a user’s preferences, a user’s current location, a user’s credentials, etc.), and if the user is sent content or communications from a server. In addition, certain data may be treated in one or more ways before it is stored or used, so that personally identifiable information is removed. For example, a user’s identity may be treated so that no personally identifiable information can be determined for the user, or a user’s geographic location may be generalized where location information is obtained (such as to a city, ZIP code, or state level), so that a particular location of a user cannot be determined. Thus, the user may have control over what information is collected about the user, how that information is used, and what information is provided to the user.

Claims

Atty Docket No.0120-705WO1 WHAT IS CLAIMED IS:

1. A method comprising: receiving, by a computing device, an indication to launch a voice-based television assistant; and in response to receiving the indication, launching the voice-based television assistant comprising: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

2. The method of claim 1, wherein launching the voice-based television assistant further comprises: sending, by the computing device and to the server computer, the second voice data for the second query, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the method further comprises displaying, by a television application executing on the computing device, a selectable information item in a user interface of the television application, the selectable information item being associated with the at least one media content recommendation.

3. The method of claim 2, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.Atty Docket No.0120-705WO1 4. The method of claim 2, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

5. The method of claim 1, wherein the received first voice data and the received second voice data are included in a conversation between a user of the computing device and the voice-based television assistant.

6. The method of claim 1, further comprising receiving, by a microphone of the computing device, the verbal input.

7. The method of claim 1, wherein the computing device is a network-connected display device.

8. The method of claim 7, wherein the network-connected display device is a smart television.

9. The method of claim 1, wherein the computing device is a mobile computing device.

10. A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a computing device cause the at least one processor to execute operations, the operations comprising: receiving, by the computing device, an indication to launch a voice-based television assistant; and in response to receiving the indication, launching the voice-based television assistant comprising: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending, by the computing device and to a server computer, the first voice data for the first query; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional informationAtty Docket No.0120-705WO1 being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

11. The non-transitory computer-readable medium of claim 10, wherein launching the voice-based television assistant further comprises: sending, by the computing device and to the server computer, the second voice data for the second query, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; and wherein the operations further comprise displaying, by a television application executing on the computing device, a selectable information item in a user interface of the television application, the selectable information item being associated with the at least one media content recommendation.

12. The non-transitory computer-readable medium of claim 11, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

13. The non-transitory computer-readable medium of claim 11, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

14. The non-transitory computer-readable medium of claim 10, wherein the received first voice data and the received second voice data are included in a conversation between a user of the computing device and the voice-based television assistant.

15. The non-transitory computer-readable medium of claim 10, further comprising receiving, by a microphone of the computing device, the verbal input.

16. The non-transitory computer-readable medium of claim 10, wherein the computing device is a network-connected display device.Atty Docket No.0120-705WO1 17. The non-transitory computer-readable medium of claim 16, wherein the network- connected display device is a smart television.

18. The non-transitory computer-readable medium of claim 10, wherein the computing device is a mobile computing device.

19. A system comprising: at least one processor; and a non-transitory computer-readable medium storing executable instructions that execute a unified television application on a network-connected display device, the unified television application configured to: receive an indication to launch a voice-based television assistant; and in response to receiving the indication, launch the voice-based television assistant comprising: displaying a user interface including a prompt for receiving verbal input; receiving first voice data for a first query related to a media content recommendation; sending the first voice data for the first query to a server computer; receiving a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; and in response to receiving the response, receiving second voice data for a second query related to the media content recommendation.

20. The system of claim 19, wherein launching the voice-based television assistant further comprises: sending the second voice data for the second query to the server computer, the second query being responsive to the response; and receiving at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information, or the context for the queries; andAtty Docket No.0120-705WO1 wherein the unified television application is further configured to display a selectable information item in a user interface of the unified television application, the selectable information item being associated with the at least one media content recommendation.

21. The system of claim 20, wherein the at least one media content recommendation includes at least one of text, video assets, games, or images.

22. The system of claim 20, wherein the first query, the response to the first query, the second query, and the response to the second query train a deep learning algorithm for use by a generative artificial intelligence engine.

23. The system of claim 19, wherein the received first voice data and the received second voice data are included in a conversation between a user of the system and the voice-based television assistant.

24. The system of claim 19, wherein the unified television application is further configured to receive, by a microphone of the system, the verbal input.

25. The system of claim 19, wherein the network-connected display device is a smart television.

26. A method comprising: receiving, by a server computer and from a computing device, first voice data for a first query related to a media content recommendation; generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; sending, by the server computer and to the computing device, the response to the computing device; receiving second voice data for a second query responsive to the response; generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; andAtty Docket No.0120-705WO1 sending the at least one media content recommendation to the computing device.

27. The method of claim 26, further comprising: generating a text string for the first voice data; and providing the text string to a generative artificial intelligence engine in the server computer.

28. The method of claim 27, further comprising: generating, by the generative artificial intelligence engine, the response based on the text string; and parsing the response to identify at least one media content item associated with the media content recommendation.

29. The method of claim 28, further comprising: fetching at least one of the media content item and a description of the media content item; and sending the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

30. The method of claim 29, wherein generating the response comprises creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

31. The method of claim 26, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the method further comprises storing a context for the conversation session, the context for use in determining future media content recommendations for the user.

32. The method of claim 26, wherein the computing device is a network-connected display device.

33. The method of claim 32, wherein the network-connected display device is a smart television.Atty Docket No.0120-705WO1 34. The method of claim 26, wherein the computing device is a mobile computing device.

35. A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations comprising: receiving, by the server computer and from a computing device, first voice data for a first query related to a media content recommendation; generating a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query; sending, by the server computer, the response to the computing device; receiving second voice data for a second query responsive to the response; generating at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and sending the at least one media content recommendation to the computing device.

36. The non-transitory computer-readable medium of claim 35, wherein the operations further comprise: generating a text string for the first voice data; and providing the text string to a generative artificial intelligence engine in the server computer.

37. The non-transitory computer-readable medium of claim 36, wherein the operations further comprise: generating, by the generative artificial intelligence engine, the response based on the text string; and parsing the response to identify at least one media content item associated with the media content recommendation.

38. The non-transitory computer-readable medium of claim 37, wherein the operations further comprise:Atty Docket No.0120-705WO1 fetching at least one of the media content item and a description of the media content item; and sending the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

39. The non-transitory computer-readable medium of claim 38, wherein generating the response comprises creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.

40. The non-transitory computer-readable medium of claim 35, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the operations further comprise storing a context for the conversation session, the context for use in determining future media content recommendations for the user.

41. The non-transitory computer-readable medium of claim 35, wherein the computing device is a network-connected display device.

42. The non-transitory computer-readable medium of claim 41, wherein the network- connected display device is a smart television.

43. The non-transitory computer-readable medium of claim 35, wherein the computing device is a mobile computing device.

44. A system comprising: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receive first voice data for a first query related to a media content recommendation from a computing device; generate a response to the first query, the response including a request for additional information related to the first query, the request for the additional information being based on at least one of previous queries, previous responses, or a context for the first query;Atty Docket No.0120-705WO1 send the response to the computing device; receive second voice data for a second query responsive to the response; generate at least one media content recommendation in response to the second query, the at least one media content recommendation being based on at least one of the previous queries, the previous responses, the request for additional information related to the first query, or the context for the first query and the second query; and send the at least one media content recommendation to the computing device.

45. The system of claim 44, wherein the instructions when executed by the at least one processor further cause the system to: generate a text string for the first voice data; and provide the text string to a generative artificial intelligence engine in the system.

46. The system of claim 45, wherein the instructions when executed by the at least one processor further cause the system to: generate, by the generative artificial intelligence engine, the response based on the text string; and parse the response to identify at least one media content item associated with the media content recommendation.

47. The system of claim 46, wherein the instructions when executed by the at least one processor further cause the system to: fetch at least one of the media content item and a description of the media content item; and send the media content item and the description of the media content item to the computing device as a selectable information item for display in a user interface of a television application executing on the computing device.

48. The system of claim 47, wherein generating the response comprises creating a JavaScript Object Notation response that includes the media content item and the description of the media content item.Atty Docket No.0120-705WO1 49. The system of claim 44, wherein the first query, the response, and the second query are included in a conversation session of a user; and wherein the instructions when executed by the at least one processor further cause the system to store a context for the conversation session, the context for use in determining future media content recommendations for the user.

50. The system of claim 44, wherein the computing device is a network-connected display device.

51. The system of claim 50, wherein the network-connected display device is a smart television.

52. The system of claim 44, wherein the computing device is a mobile computing device.

53. A method comprising: receiving, by a server computer, information and data related to preferences of a user for media content; identifying metadata associated with a media content item; determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and sending, by the server computer and to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

54. The method of claim 53, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

55. The method of claim 53, wherein the personalized description is a text string.

56. The method of claim 53, wherein the method further comprises generating a request for the personalized description for the media content item, the request specifying:Atty Docket No.0120-705WO1 a character length for the personalized description; and at least one preference from the preferences of the user for media content.

57. The method of claim 56, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

58. The method of claim 53, wherein the computing device is a network-connected display device.

59. The method of claim 58, wherein the network-connected display device is a smart television.

60. The method of claim 53, wherein the computing device is a mobile computing device.

61. A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations comprising: receiving information and data related to preferences of a user for media content; identifying metadata associated with a media content item; determining that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generating a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and sending, to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.

62. The non-transitory computer-readable medium of claim 61, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

63. The non-transitory computer-readable medium of claim 61, wherein the personalized description is a text string.Atty Docket No.0120-705WO1 64. The non-transitory computer-readable medium of claim 61, wherein the operations further comprise generating a request for the personalized description for the media content item, the request specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

65. The non-transitory computer-readable medium of claim 64, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

66. The non-transitory computer-readable medium of claim 61, wherein the computing device is a network-connected display device.

67. The non-transitory computer-readable medium of claim 66, wherein the network- connected display device is a smart television.

68. The non-transitory computer-readable medium of claim 61, wherein the computing device is a mobile computing device.

69. A system comprising: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receiving information and data related to preferences of a user for media content; identify metadata associated with a media content item; determine that the information and data related to at least one preference of the user for media content matches at least one data value of the metadata for the media content item; generate a personalized description for the media content item, the personalized description based on the preferences of the user for media content; and send, to a computing device, a selectable information item for the media content item along with the personalized description for the media content item for display in a user interface of a TV application executing on the computing device.Atty Docket No.0120-705WO1 70. The system of claim 69, wherein the preferences are at least one of preferred media content types, genres, actors, cast members, or themes.

71. The system of claim 69, wherein the personalized description is a text string.

72. The system of claim 69, wherein the instructions when executed by the at least one processor further cause the system to generate a request for the personalized description for the media content item, the request specifying: a character length for the personalized description; and at least one preference from the preferences of the user for media content.

73. The system of claim 72, wherein generating the personalized description for the media content item is in response to the request for the personalized description for the media content item.

74. The system of claim 69, wherein the computing device is a network-connected display device.

75. The system of claim 74, wherein the network-connected display device is a smart television.

76. The system of claim 69, wherein the computing device is a mobile computing device.

77. A method comprising: receiving, by a server computer, a request for a trivia question for a media content item; sending, by the server computer and to a computing device, a trivia question for display in a user interface on the computing device; receiving an answer to the trivia question; determining whether the answer is a correct answer; and sending a message as to whether the answer is the correct answer for display in the user interface.Atty Docket No.0120-705WO1 78. The method of claim 77, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

79. The method of claim 78, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

80. The method of claim 77, further comprising sending along with the trivia question at least two answers to the trivia question for display in the user interface.

81. The method of claim 77, wherein the computing device is a network-connected display device.

82. The method of claim 81, wherein the network-connected display device is a smart television.

83. The method of claim 77, wherein the computing device is a mobile computing device.

84. A non-transitory computer-readable medium storing executable instructions that when executed by at least one processor of a server computer cause the at least one processor to execute operations, the operations comprising: receiving, by the server computer, a request for a trivia question for a media content item; sending a trivia question to a computing device for display in a user interface on the computing device; receiving an answer to the trivia question; determining whether the answer is a correct answer; and sending a message as to whether the answer is a correct answer for display in the user interface.

85. The non-transitory computer-readable medium of claim 84, wherein the media content item is selected by a user for a trivia game associated with the trivia question.Atty Docket No.0120-705WO1 86. The non-transitory computer-readable medium of claim 85, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.

87. The non-transitory computer-readable medium of claim 84, wherein the operations further comprise sending along with the trivia question at least two answers to the trivia question for display in the user interface.

88. The non-transitory computer-readable medium of claim 84, wherein the computing device is a network-connected display device.

89. The non-transitory computer-readable medium of claim 88, wherein the network- connected display device is a smart television.

90. The non-transitory computer-readable medium of claim 84, wherein the computing device is a mobile computing device.

91. A system comprising: at least one processor; and a non-transitory computer-readable medium storing instructions that when executed by the at least one processor cause the system to: receive a request for a trivia question for a media content item; send a trivia question to a computing device for display in a user interface on the computing device; receive an answer to the trivia question; determine whether the answer is a correct answer; and send a message as to whether the answer is the correct answer for display in the user interface.

92. The system of claim 91, wherein the media content item is selected by a user for a trivia game associated with the trivia question.

93. The system of claim 92, wherein based on determining that the answer is a correct answer, incrementing a score of the user for the trivia game.Atty Docket No.0120-705WO1 94. The system of claim 91, wherein the instructions when executed by the at least one processor further cause the system to send along with the trivia question at least two answers to the trivia question for display in the user interface.

95. The system of claim 91, wherein the computing device is a network-connected display device.

96. The system of claim 95, wherein the network-connected display device is a smart television.

97. The system of claim 91, wherein the computing device is a mobile computing device.

Images