Abstract: A graph-based novelty detection system processes a stream of observations by storing a compressed representation of the observations in a graph. Each node of the graph represents a component of an observation and a count of a number of times that component has been observed. The system calculates a novelty score based, at least in part, on a conditional probability of one or more components of the observation.

Abstract: A graph comprising nodes and edges is stored by a distributed system as a collection of nodes and half-edges stored with their respective nodes. A message processor is associated with a node as needed to process messages passed between nodes, such that a given node has zero or one message processor assigned to it at a given time. Queries of the graph are resolved by processing a first portion of the query at a first node, and forwarding the results with the remaining portions of the query to a node linked by an edge to the present node.

Abstract: A graph comprising nodes and edges is stored by a distributed system as a collection of nodes and half-edges stored with their respective nodes. A message processor is associated with a node as needed to process messages passed between nodes, such that a given node has zero or one message processor assigned to it at a given time. Queries of the graph are resolved by processing a first portion of the query at a first node, and forwarding the results with the remaining portions of the query to a node linked by an edge to the present node.

Abstract: A graph comprising nodes and edges is stored by a distributed system as a collection of nodes and half-edges stored with their respective nodes. A message processor is associated with a node as needed to process messages passed between nodes, such that a given node has zero or one message processor assigned to it at a given time. Queries of the graph are resolved by processing a first portion of the query at a first node, and forwarding the results with the remaining portions of the query to a node linked by an edge to the present node.

Abstract: A graph comprising nodes and edges is stored by a distributed system as a collection of nodes and half-edges stored with their respective nodes. A message processor is associated with a node as needed to process messages passed between nodes, such that a given node has zero or one message processor assigned to it at a given time. Queries of the graph are resolved by processing a first portion of the query at a first node, and forwarding the results with the remaining portions of the query to a node linked by an edge to the present node.

Abstract: A container for a food product generally includes a tray and a cover attached to the tray by ultrasonic bonds. The tray includes a bottom having a perimeter and a sidewall extending along the perimeter of the bottom to form a cavity sized to receive the food product. The sidewall defines an opening for the food product to be placed into the cavity. The tray also includes a flange extending from an edge of the sidewall and around the opening. The flange has a single layer first area with a first thickness and a second area comprised of at least two layers with a second thickness. The second thickness is at least twice as thick as the first thickness. The ultrasonic bonds extend along the entire sidewall of the container to form a continuous, hermetic seal between the cover and the tray around the opening.

Abstract: A graph-based novelty detection system processes a stream of observations by storing a compressed representation of the observations in a graph. Each node of the graph represents a component of an observation and a count of a number of times that component has been observed. The system calculates a novelty score based, at least in part, on a conditional probability of one or more components of the observation.

Abstract: A container for a food product generally includes a tray and a cover attached to the tray by ultrasonic bonds. The tray includes a bottom having a perimeter and a sidewall extending along the perimeter of the bottom to form a cavity sized to receive the food product. The sidewall defines an opening for the food product to be placed into the cavity. The tray also includes a flange extending from an edge of the sidewall and around the opening. The flange has a single layer first area with a first thickness and a second area comprised of at least two layers with a second thickness. The second thickness is at least twice as thick as the first thickness. The ultrasonic bonds extend along the entire sidewall of the container to form a continuous, hermetic seal between the cover and the tray around the opening.

Abstract: A system for packaging a food product in a container generally includes a conveyance apparatus operable to move trays in a machine direction, a delivery apparatus operable to deposit the food product into cavities of the trays, and a positioning apparatus operable to position covers relative to the trays. The positioning apparatus is configured to position each cover on a respective tray to overlap a flange of the respective tray. The system also comprises an ultrasonic bonding apparatus configured to receive the flange and the cover of each container in the nip between a first bonding module and a second bonding module. At least one of the first bonding module and the second bonding module vibrates at an ultrasonic frequency and delivers ultrasonic energy to at least one of the cover and the flange to seal the container.

Abstract: A graph comprising nodes and edges is stored by a distributed system as a collection of nodes and half-edges stored with their respective nodes. A message processor is associated with a node as needed to process messages passed between nodes, such that a given node has zero or one message processor assigned to it at a given time. Queries of the graph are resolved by processing a first portion of the query at a first node, and forwarding the results with the remaining portions of the query to a node linked by an edge to the present node.

Abstract: A system for packaging a food product in a container generally includes a conveyance apparatus operable to move trays in a machine direction, a delivery apparatus operable to deposit the food product into cavities of the trays, and a positioning apparatus operable to position covers relative to the trays. The positioning apparatus is configured to position each cover on a respective tray to overlap a flange of the respective tray. The system also comprises an ultrasonic bonding apparatus configured to receive the flange and the cover of each container in the nip between a first bonding module and a second bonding module. At least one of the first bonding module and the second bonding module vibrates at an ultrasonic frequency and delivers ultrasonic energy to at least one of the cover and the flange to seal the container.

Abstract: Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products for assessing a performance and/or determining a programmatically expected performance of a marketing campaign. In one embodiment a method for creating a unified data set from a plurality of data sets received from third-party service providers is disclosed. In one embodiment, a graphical user interface is used to facilitate user access to visual representation of the unified data set. In one embodiment, the unified data set may be used to train a machine learning model. In some implementations, the machine learning model may predict an expected performance for marketing campaigns. In one embodiment, the machine learning model may adjust one or more parameters of the marketing campaign in order to increase the effectiveness of the marketing campaign and the associated revenue.

Abstract: Embodiments of the present disclosure provide methods, systems, apparatuses, and computer program products for assessing a performance and/or determining a programmatically expected performance of a marketing campaign. In one embodiment a method for creating a unified data set from a plurality of data sets received from third-party service providers is disclosed. In one embodiment, a graphical user interface is used to facilitate user access to visual representation of the unified data set. In one embodiment, the unified data set may be used to train a machine learning model. In some implementations, the machine learning model may predict an expected performance for marketing campaigns. In one embodiment, the machine learning model may adjust one or more parameters of the marketing campaign in order to increase the effectiveness of the marketing campaign and the associated revenue.