Abstract: Methods and systems are provided herein for providing media asset recommendations to a user based on user input in real time and using a reinforcement learning model or media asset recommendation model. The model includes a plurality of states, each having a set of media asset recommendations, a plurality of available user input options, and a state value. During a browsing session, a first set of media asset recommendations is provided to a user based on a current state corresponding to the browsing session. The user then selects a user input option, and a second set of media asset recommendations is determined based on the received user input option. The second set of media asset recommendations is then provided to the user during the browsing session.

Abstract: Systems and methods are described for generating for display a media asset, and receiving a query regarding an object depicted in the media asset at a first time point within a presentation duration of the media asset. The system and methods may, based on receiving the query, determine one or more second presentation points within the presentation duration of the media asset related to the object, identify the one or more second presentation points as supplemental content, and generate for display the supplemental content while the media asset is being generated for display.

Abstract: Methods and systems are described for improved delivery of foveated rendering streams for media content delivery. Received video data is separated into a high acuity (HA) stream and a low acuity (LA) stream. The HA stream is marked to indicate HA transmission. A communication device that retransmits the HA stream based on the marking transmits the HA stream at a lower latency and a higher reliability than the LA stream. A receiving device receives the HA stream and the LA stream. A display device generates for display a combined stream including the HA stream and the LA stream. Artificial intelligence systems, including neural networks, are trained for improving the foveated rendering. Models are developed for the foveated rendering. Related apparatuses, devices, techniques, and articles are also described.

Abstract: Systems and methods for generating a CAPTCHA challenge in a virtual environment are disclosed. The methods display a spatially anchored virtual 3D object in a virtual environment where certain features of the 3D object are hidden or occluded. The methods provide general, specific, or no instructions to a user for manipulating the displayed 3D virtual object. Upon determining that the manipulations performed follow the instructions, the occluded feature is revealed. Varying degrees of CAPTCHA challenges are provided that include moving real life objects, leveraging user background in generating customized CAPTCHA challenges, and camouflaging the virtual objects to make solving the CAPTCHA more challenging. The methods query the user to provide an input that reflects the revealed occluded feature, and, if the response to the query meets the predetermined response, access to the secured data requested in granted.

Abstract: Methods and systems are described for extended and mixed reality experience adaptation, processing, and handover from one computing or processing entity to another. In response to a change in a condition impacting resource usage, delivery of content is transferred from one edge node to another. One or more changes in a viewing client, a first edge node, a second edge node, a communication network, and content signal a handover. Artificial intelligence systems, including neural networks, and models are trained and developed for improving the adaptation, processing, and handover. Related apparatuses, devices, techniques, and articles are also described.

Abstract: The present application provides for delivering initiation of social rooms for a predicted future event by evaluating a probability of the future event occurring and pre-allocating server resources of the social network platform based on the evaluated probability and subscriptions for the social room. The social networking server may receive a request, from a device of a host user, to create a social room based on a predicted future event. The social networking server may transmit an invitation to user devices on the social network to subscribe to the social room and then receive subscriptions from the user devices to join the social room. Based on an evaluated probability and the number of subscribers, the social networking server may pre-allocate particular server resources for the social room. If the future event occurs, then the social networking server initiates the social room using the pre-allocated particular server resources and automatically joins the subscribers.

Abstract: An augmented reality (AR) device captures a first image frame of a first scene in a real world. The AR device compresses the first image frame using a same bitrate across an entirety of the first image frame to generate a first compressed image frame. The AR device wirelessly sends, to a server, the first compressed image frame. The AR device receives, from the server, object detection results that identify locations of objects depicted in the first image frame.

Abstract: Systems and methods are provided for utilizing historic user consumption of media assets to manage the resources associated with streaming further media asset. tracking, at a computing device, A consumption of a plurality of media assets within a preset time period are tracked at a computing device, and a first resource value associated with the plurality of media assets is identified. A consumption velocity associated with the consumption of the plurality of media assets is identified, and the consumption velocity is weighted based on the first resource value. It is determined that the weighted consumption velocity is above a threshold consumption velocity, and a user interface element comprising a recommendation for a media asset is generated for output, wherein a second resource value associated with the recommended media asset is lower than the first resource value.

Abstract: Methods and systems are described for identity verification and deepfake prevention. A first video of a person is captured during an in-person interaction, the person's identity is verified, and the video is associated with the verified identity. In a subsequent electronic interaction, information about a second person is accessed, a second video of the second person is captured, and a trained neural network model is used to determine if the second person is attempting to identify as the first person. If the second person is not attempting to identify as the first person, the electronic interaction proceeds. If the second person is attempting to identify as the first person, the model determines if the first person is likely the same as the second person, transmitting a positive indicator if likely the same, and a negative indicator if not. Related networks, models, apparatuses, devices, techniques, and articles are also described.

Abstract: Systems and methods are disclosed for generating a fueling plan based on navigation data for the trip, fuel type data for the vehicle, and fuel price data for fuel locations within a geographic threshold of the trip. The fueling plan may include a selected fuel location. For instance, the system may determine, based on the fuel type data, that the vehicle cannot reach the selected fuel location. In response to this determination, the system may automatically configure the vehicle to reduce fuel consumption.

Abstract: There are provided systems and methods for resuming a media content item. A user watch history of the media content item is determined. The user watch history comprises a pause point and a pause duration. A media content summary is determined based on the user watch history. The media content summary is generated for consumption by the user.

Abstract: Depth sensing measurements are performed for an area in all directions surrounding a user. Based on the depth sensing measurements, a horizontal plane the area, as well as a plurality of obstructions in the area are identified. A three-dimensional shape representing the maximum volume of contiguous open space is generated based on the horizontal plane and the plurality of obstructions. The three-dimensional shape is then truncated to create a maximally sized convex shape. The largest possible play area is then constructed using the convex shape.

Abstract: Systems and methods are described for receiving a first request to access a media asset; identifying a first portion of the media asset to be provided for display based on the first request, wherein the first portion of the media asset corresponds to a first timepoint of the media asset; identifying a second portion of the media asset corresponding to a second timepoint of the media asset, wherein the second timepoint occurs prior to the first timepoint of the media asset; receiving a second request to cause simultaneous display of the first portion of the media asset corresponding to the first timepoint and the second portion of the media asset corresponding to the second timepoint; and in response to receiving the second request, providing for simultaneous display the first portion of the media asset and the second portion of the media asset.

Abstract: Systems and methods for simultaneously being present in multiple extended reality (XR) apps running on the same XR device are disclosed. The methods concurrently run multiple XR apps on the user's XR device and use an avatar to represent the user's presence in each app. The methods determine whether the user is actively present in a first app or a second app. When the user is not actively present in a first app, activity in the first app is monitored, the avatar is configured to provide auto-responses based on AI, ML, or preprogrammed responses for relevant queries to simulate the user's presence. Notifications and summary of the activities in the first app are provided to the user while they are actively present in the second app. Instead of rendering the first app, back-end simulations of the activities in the first app are processed and made available when rendering is resumed.

Abstract: Systems and methods for managing coverage in a high-density wireless environment are disclosed. A client device detects low signal strength from its assigned router. The signal strength of a neighboring router is determined to be higher than that of the assigned router. Based on the determination, the neighboring router is configured with a customer-specific SSID of the client device. The client device uses its customer-specific SSID to connect with the neighboring router. Upon determining that the neighboring router has available bandwidth to support a bandwidth request of the client device, the bandwidth is provisioned to the client device from the neighboring router. Routers with low signal strengths may be selectively disabled and collect signal strength data of neighboring routers. Active routers maybe configured with the respective customer-specific SSIDs of the disabled routers. A switch is installed at the front-end of all routers maintains LAN traffic within the LAN boundaries.

Abstract: Sensors disposed on a steering wheel sense contact of a user's hands with the steering wheel. The sensors are arranged into several zones that wrap around the steering wheel. Each zone is adjacent to at least two other zones. Data from the sensors is continuously received by input/output circuitry. Control circuitry determines a time series of pressures for each zone based on the data from the sensors. The time series of pressures for the zones are stored in a data structure that is looped. The time series of pressures of the data structure is compared to a time series of pressures of a reference data structure. An action to control at least one element of the vehicle is performed based on the comparison. In some embodiments, the steering wheel includes handlebars and the sensors are disposed in handlebar grips.

Abstract: Systems and methods for extending the span of content displayed in a first view frustum by virtually overlaying a virtual portion of the content on a display of an XR device are described. A composite image, which includes a primary image portion, and an enhanced image portion are requested. The primary image portion is to be displayed on a physical display having a first view frustum. Characteristics of the enhanced image portion are determined based on factors such as the user comfort, field of view from the XR device, and system rendering and encoding capabilities. The primary image portion is displayed in a first view frustum simultaneously and synchronized with the enhanced image portion in a second view frustum. The enhanced image portion is anchored, and color matched with the primary image portion to provide the appearance of one single composite display that has image and color continuity.

Abstract: Systems and methods are provided for generating an avatar collage based on a plurality of social network items posted by a plurality of social network accounts. A social network application identifies a plurality of social network items. The social network application determines a topic that is common to each social network item of the plurality of social network items. The social network application generates an avatar collage based on the plurality of social network items. The avatar collage comprises a plurality of avatar representations of the plurality of social network accounts that posted the plurality of social network items and at least one text portion of a particular social network item of the plurality of social network items.

Abstract: Systems and methods for obtaining metrics relating to an extended reality experience and using the obtained metrics to perform remedial actions, such as managing user motion sickness, determining user performance relating to a designed game difficulty, and performing home automation are disclosed. The methods include determining a starting and ending checkpoint in an extended reality experience. Data from a plurality of users as they navigate between the determined checkpoints is obtained and used to determine a metric, such as a median, average, or other representative data. The current user's navigation through the same checkpoints is monitored and compared with the metric. The results from the comparison are used to enhance extended reality experience, which includes customizing the experience for motion sickness, game difficulty level, and home automation.

Abstract: A first virtual display zone may be set as anchored in a first physical space. The zone may include one or more virtual displays rendered by extended reality (XR) equipment, such as a head mounted display (HMD). A first zone policy may be set for the first virtual display zone, defining what applications will have outputs rendered in the first virtual zone. A zone policy may specify that the output of applications that provide live communication will be generated for display in the first virtual display, or may specify which other XR devices, in the first physical space or remote, may access the virtual displays of the first. Location and policies for a second virtual display zone may be similarly set. Also, virtual displays anchored in the physical space may be de-anchored and re-anchored to the XR equipment if the XR equipment exits the first physical space.