Cox Communications, Inc.

Thomson Licensing

Interdigital Ce Patent Holdings

Yousef Wasef Nijim

James Alan Strothmann

Jay Paul Langa

Anant Pralhad Patil

Eric S Roberts

Michael Paul Overcash

Izzat Hekmat Izzat

Lisa Ann Pickelsimer

Anthony Joseph Insinga

Terry Douglas Lee

Francisco J Gonzalez

Mike Arthur Derrenberger

Catherine Elizabeth Thompson

Daniel D Lam

Ion Vizireanu

Shu Lin

Dong-Qing Zhang

Edwin Arturo Heredia

Ahmet Mursit Eskicioglu

Stephen Kent Necessary

Joshua Paul Bernard Sommer

Len Barlik

William Wesley Beyers

Mark Alan Schultz

David J Duffield

Douglas David Gravino

Muhammad Asif Raza

Pujan K Roka

Mary Lafuze Comer

Craig M Smithpeters

Charles Bryan Hunt

Jayasri Devalapalli

Michael Lawrence Smith

David Adam Taylor

Hui Zhao

Michael Colin Jaccino

Megan Walls Dover

Charlotte Lee McLure

Carol Jeanette Ansley

Matthew Wayne Chapell

Matthew Wayne Chappell

Jenna Meushaun Taneak Smith

According to aspects disclosed herein, a method of using machine learning as part of creating avatars while watching video content is provided. According to an aspect, a method is configured for receiving a request to create an avatar based on the video content and, in response to receiving the request to create the avatar based on the video content, determining one or more processing resources to use to create the avatar based on an output of a machine learning engine, wherein the one or more processing resources include a cloud-based processing resource, an edge-based processing resource, and a local processing resource. The method includes allocating avatar processing operations to the one or more processing resources to create the avatar based on the output from the machine learning engine. The method further includes creating the avatar using the one or more processing resources, and storing the avatar in an avatar database.

Machine learning and distributed processing for creating avatars while watching video content

Automated communication channel selection is provided. A method, system, and computer readable storage device automatically perform a discovery process of a MoCA® network, to determine a topology of the network, perform a spectrum analysis of a DOCSIS® network of which a portion of the frequency range may be shared, apply one or more business rules to the collected network and spectrum usage data, and determine an optimized channel configuration for transmitting data to end devices in a local network. For example, the channel configuration may be configured for optimal bandwidth allocation, transmission speeds, signal quality, etc., without interferences within the shared frequency spectrum range. A gateway device may include a filter that can be reconfigured as an all-pass filter or as a variable low-pass filter based on the channel configuration determination. The MoCA® network may be reconfigured to operate within a defined frequency range based on the determined channel configuration.

Automated communication channel selection

Aspects of the present disclosure improve wireless networking performance by reducing or limiting performance issues caused by undetected or unknown interference sources and/or attenuation sources. Feedback from client devices can be utilized to reduce or limit wireless network performance issues caused by varying interference parameters and/or attenuation parameters observed by each client device. The feedback, associated with wireless communication conditions of corresponding client devices, in conjunction with a machine learning algorithm can be used to enable a dynamic selection of one or more particular operating bands, channels, and/or channel widths to avoid or limit signal interference and/or signal attenuation observed by each client device. Feedback from a plurality of client devices can be used to recommend one or more channels and/or one or more channel widths of one or more operating bands to use that reduces latency, CCI, and/or ACI and improves speed, throughput, and/or QoS.

Wireless channel control using client feedback

Aspects of the present disclosure provide a failover service in part by utilizing a smartphone when a business or home modem is inoperable or otherwise unable to provide adequate internet service. Once the smartphone is paired with a communication bridge, the smartphone may be used to provide internet services to wired and wireless devices associated with a first network. The smartphone can utilize its cellular network interface to connect to the internet and provide internet connectivity via the communication bridge to a router or gateway which, in turn, enables devices connected to the router or gateway to access the internet without having to connect directly to a separate network provided by the smartphone. Aspects of the disclosure may rely on machine learning to optimize network and/or device communications, configurations, and/or other failover parameters.

Failover to cellular service for seamless internet connectivity

Optimized automated access network connectivity is provided. A network connecting device (NCD) may perform an optimized access network setup process upon boot-up to connect to an access network. The optimized process may be determined by a cloud-based machine-learning system based on learned connecting and network usage behaviors. The optimized process may include a sequence of network connectivity evaluations configured to minimize the setup time associated with discovering and connecting to an access network. The optimized process may further reduce or eliminate the probability of device failure due to an erroneous access network implementation by establishing communications with a test server prior to committing an access operating mode to non-volatile memory. The NCD may be configured to modify the device's master configuration settings to include the optimized process such that when a master reset is performed, the device may utilize the optimized process to discover and connect to the access network.

Access network connectivity optimization engine

Aspects of the present disclosure provide for adaptively allocating processing operations according to an edge-only processing mode, a hybrid edge-cloud processing mode, and/or cloud-only processing mode, but are not so limited. In one aspect, the disclosure describes adaptively managing processing of applications or application modules by using machine learning in part to direct how the processing operations are to be performed whether using edge-only resources, hybrid edge-cloud resources, and/or cloud-only resources. Other aspects are described in detail herein.

Adaptive edge processing

Combining a plurality of video feeds of various modulation formats and from a variety of sources for providing a unified interface and an extension of services across the plurality of video feeds is provided. An integrated video feed system located at least in part at a subscriber premises is configured to receive a plurality of video content broadcast feeds (e.g., cable television, over the air television, satellite television, Internet Protocol television), generate a combined data feed comprising video content signals included in the plurality of video content feeds, identify and decode the video content signals, obtain additional data associated with each of the plurality of video content feeds, provide a unified interface for displaying an aggregation of data and services associated with the plurality of video content feeds, and to provide requested video content included in the plurality of video content broadcast feeds for playback on a display device.

Combining video content feeds

Intelligent bandwidth prioritization and allocation are provided. Data about a local network and devices connected to the network may be collected, monitored, measured, and tracked over time for generating a profile about a subscriber. For example, the profile may comprise a data-based representation of the data transmission capabilities and data usages and behaviors associated with the subscriber network that can be used for identifying network performance issues, to determine traffic classification, classification criteria, and priority values for automatically classifying traffic flows, and to determine bandwidth allocation rules, optimizations, and other traffic management instructions that can be automatically implemented by the access point to optimize performance of data flows.

Local network traffic prioritization for improved quality of service

Telematics-based device troubleshooting, self-repair, and optimization are provided. A system, method, and computer readable storage device collect telemetry data associated with the health of networked CPE devices, service provider data, and service and repair data associated with CPE devices, analyze the collected information, and detect and predict issues that can affect the functioning and operation of CPE devices. Analysis of collected data can be based on self-check rules. In some implementations, troubleshooting steps or rules can be executed by a server device or communicated to a CPE device for enabling self-troubleshooting and self-correction of an issue. Self-check and troubleshooting rules can be configured according to insights derived from machine learning techniques applied to collected data (e.g., telemetry data, service provider data, and service and repair data (troubleshooting and repair feedback data collected in association with customer calls, field technician visits, and self-healing checks and actions performed on/by CPE devices)).

Telematics-based network device troubleshooting and repair

Aspects of the present disclosure provide for the detection and/or use of countermeasures to prevent and/or limit unauthorized devices from accessing and/or using another's communication network. An exemplary system includes a cloud controller and a gateway device that communicate via the infrastructure provided by a service provider communication network, wherein the gateway device operates in part to execute a device discovery algorithm to detect devices that are connected to a network facilitated by the gateway device and/or employ countermeasures to thwart further access by any unauthorized device. An exemplary method executes a device discovery algorithm to apply one or more of a plurality of device discovery protocols to detect devices that are connected to a network facilitated by a gateway device and/or implement countermeasures to block further access. Other aspects are described in detail herein.

System to detect and/or prevent unauthorized access to a communication network

Information about and access to available third party content are provided via a primary service provider programming guide. A primary service provider may allow its customers/subscribers to access third party content through the systems of the primary service provider upon selection of a given third party content item from the primary service provider programming guide. The third party content may be provided as a full screen overlay over content presently being displayed and viewed from the primary service provider, or the third party content may be provided via a picture-in-picture inset either on the full screen or inside the displayed programming guide. Third party content offered via the primary service provider programming guide may be based on a recommendation of content in view of preferences and profile information for the customer/subscriber.

Providing third party content information and third party content access via a primary service provider programming guide

Systems and methods are described for enabling quantum computing at an edge node of a network. For example, a machine learning component residing on each of a plurality of edge nodes of the network may be implemented to distribute application processing by network location and processing type, including distribution among classical processing at a central cloud, classical processing at an edge node, and quantum processing at a quantum edge node including a quantum computing device. By distributing certain applications, such as latency-sensitive applications of a higher order of complexity, to an edge node, and particularly a quantum edge node, latency may be reduced and complex application code may be processed more quicky using quantum computations. For applications to be processed using quantum processing, the machine learning component may further identify qubits for the quantum processing and define containers based on the qubits for deployment by the quantum computing device.

Edge quantum computing

A URL personalization system allowing a television service provider to dynamically associate multiple URLs with the video content item being viewed by the customer is provided. The associated URLs point to additional content that may be of interest to different customer demographics. A generic URL linking to the associated URLs may be inserted into the video content item. The system may personalize the generic URL by replacing or modifying the generic URL with a personalized URL based on information specific to the customer viewing the content before streaming the content or when additional content is requested. The customer is redirected to the personalized URL to obtain the additional content. This allows the television service provider to send a single video content item to all customers or large groups of customers while providing individual customers with an enhanced interactive television viewing experience.

Dynamic URL personalization system for enhancing interactive television

A system, method, and computer readable storage device are provided for collecting data associated with a WiFi signal profile of an area of interest (AOI), analyzing the collected data, and generating a dataset from the data representative of the signal profile. The dataset includes value information and location information, wherein value information include signal data that are to be displayed in a visual representation. The dataset includes values of measured WiFi signal strengths, and in some examples the values are weighted based on one or a combination of device data, interference data, and business-related data. This can enable generation and display of a visual representation that includes a representation of signal strength values based on assessed signal strengths needed to support particular services on particular user devices. The visual representation can be a heatmap that shows color-coded variations in WiFi signal values associated with locations or devices in the AOI.

Automated wireless local area networking topology mapping

Growing community of inventors

Roswell, GA, United States of America

Yousef Wasef Nijim