Comcast Cable Communications, LLC

Autonom8, Inc.

Ranjit Padmanabhan

Bernard Burg

Tyler Kareeson

Ryan March

Balakrishnan Kavikkal

Paresh Saxena

George Mammen Jacob

Thekkethalackal Mammen Kurien

Disclosed are systems and methods for behavioral modeling based on content genre and utilizing results for content recommendation and other network handling and storage of the content. Viewing events with respect to a content item are aggregated. An affinity is calculated based on the viewing events. Additional viewing events occurring during the delivery of the content item and associated with other content items are also selected. A sampling bonus is added to the affinity if these additional viewing events have a duration below a threshold and the other content items share a same genre as the content item.

Behavior modeling based on content genre

A system for autonomous workflow management and execution is disclosed. The system includes a workflow builder module to create a workflow based on directed acyclic graphs, conversational submodules and a defined process. The system includes a data stream module to enable the workflow from the workflow builder module to achieve objectives based on a workflow specification, constraints and security considerations. The system includes a stream processor module including a data ingestion and processing submodule to fetch data from the data stream module and process the data based on operations to define and evaluate rules, heuristics and models with the workflow. The system includes a learning module to continuously recompute potential objectives and outcomes based on analysis of the optimized data. The processing subsystem includes a workflow orchestrator module to make decisions for automation of the workflow execution by triangulating data from a user, the data sources and the desired outcomes.

System and method for autonomous workflow management and execution

Systems and methods for automation of a customer support sorting process are described. A probability that a call from a potential caller will be received by a call system may be determined based at least in part on historical status information and call history information. The historical status information may indicate one or more past operational states of a service network. The call history information may indicate one or more calls received by the call system, as well as a subject matter of each of the one or more calls. If the determined probability satisfies a threshold, a notification to the potential caller may be transmitted. The notification may inform the potential caller of a current operational state of the service network.

Automation of customer support sorting process

A semantic textual information recognition system is provided. The system includes a memory configured to receive a plurality of text elements along with respective text element coordinates. The system includes a processor operatively coupled to the memory, wherein the processor includes a spatial reconstruction module configured to identify the plurality of text elements on an information axis based on the text element coordinates. The processor also includes a semantic clustering module configured to determine a plurality of semantic clusters of the plurality of text elements by calculating a proximity matrix using the plurality of text elements on the same information axis and a semantic data model. The processor further includes a rank clustering module configured to generate a plurality of rank clusters by ranking the plurality of semantic clusters. The processor further includes a machine learning module configured to update the semantic data model based on the feature set.

System and method for semantic textual information recognition

A system and method for generating a virtual assistant is disclosed. The system for generating a virtual assistant includes a configuration subsystem configured to receive one or more parameters from a document. The configuration subsystem is also configured to serialize the one or more parameters automatically extracted from the document and generate a structured object based on the one or more serialized parameters. The configuration unit is further configured to embed all validation criteria specified in the document. The system for generating a virtual assistant also includes a virtual assistant generator operatively coupled with the configuration subsystem and configured to analyze the structured object. The virtual assistant generator is also configured to automatically generate a virtual assistant based on an analyzed structured object.

Growing community of inventors

Saratoga, CA, United States of America

Ranjit Padmanabhan