Servicesource International, Inc.

Other

Falkonry Inc.

Greg Olsen

Ricardo Craft

Ganesh Bell

Lenin Subramanian

Manohar Raghunath

Zheng Chen

Abhinav Vohra

Kevin Smith

Chelliah Thirunavukkarasu

Elaine Garvey

Chellah Thirunavukkarasu

Nikunj R Mehta

Peter Nicholas Pritchard

Mohammad H Firooz

A method for determining specific conditions occurring on industrial equipment based upon received signal data from sensors attached to the industrial equipment is provided. Using a server computer system, signal data is received and aggregated into feature vectors. Feature vectors represent a set of signal data over a particular range of time. The feature vectors are clustered into subsets of feature vectors based upon attributes the feature vectors. One or more sample episodes are received, where a sample episode includes sample feature vectors and specific classification labels assigned to the sample feature vectors. A signal data model is created that includes the associated feature vectors, clusters, and assigned classification labels. The signal data model is used to assign classification labels to newly received signal data using the mapping information for the existing feature vectors, existing clusters and associated classification labels to determine the specific conditions occurring on the industrial equipment.

Machine learning of physical conditions based on abstract relations and sparse labels

In a recurring revenue management system, a first unit of data and a second unit of data is received. Content is extracted from the first unit of data and the second unit of data based on one or more parameters of a predefined data object that is part of an asset data model. The extracted content is added to an instance of the predefined data object, and a reference tag with identification information for its associated content is associated with the content extracted from each of the first unit of data and the second unit of data. A duplicate data condition can be detected and resolved by applying a predefined approach to conflict resolution based on the identification information in the reference tags of the content of the first unit of data and the second unit of data. Related methods, systems, and computer program products are also described.

Provenance tracking and quality analysis for revenue asset management data

In a recurring revenue management system, it can be determined that a unit of data received at the recurring revenue management system from an external client data system lacks at least one data aspect necessary to create a fully populated instance of the data object. An instance of a skeletal object is created in a repository of the recurring revenue management system, and the instance of the skeletal object is partially populated with at least some data extracted from the received unit of data. The instance of the skeletal object is made available for use in the recurring revenue management system. The instance of the skeletal object is then further populated with additional data extracted from a second unit of data received by the recurring revenue management system. Related methods, systems, and computer program products are also described.

Inbound and outbound data handling for recurring revenue asset management

Data relevant to a predefined data object of a set of predefined data objects can be extracted from a unit of date received at a recurring revenue management system. The extracted relevant data can be populated to an instance of the predefined data object. One or more relationships between the instance of the predefined data object and at least one other instance of the predefined data object or a second predefined data object. The defining occurs based on a set of parameters associated with the predefined data object and content of the extracted data. An opportunity can be generated for a sale or renewal of a recurring revenue asset based at least in part on the one or more relationships, and the generated opportunity can be presented to a user. Related methods, systems, and computer program products are also described.

Asset data model for recurring revenue asset management

Visual representations of recurring revenue management system data and predictions are disclosed. A user interface is generated for an electronic display, the user interface including a graphical representation of one or more recurring revenue assets, the graphical representation representing each of the one or more recurring revenue assets according to one or more metrics that define each of the one or more recurring revenue assets. A predicted outcome for at least one of the one or more recurring revenue assets is predicted, the calculating being from a predictive model that is based on aggregate historical information collected from one or more data sources. A graphical representation of the predicted outcome is generated according to one or more parameters related to the one or more metrics, for concurrent display in the user interface with the graphical representation of one or more recurring revenue assets.

Visual representations of recurring revenue management system data and predictions

Growing community of inventors

Menlo Park, CA, United States of America

Greg Olsen