Awarepoint Corporation

Corelogic Solutions, LLC

Clinical Patents, LLC

Wei Geng

Matthew R Perkins

Jon Arthur Wierks

Bin He

Gary Jorgensen

John Taylor

Kien Trong Trinh

Roderick Maclan

Tricia J Murray

Dipal Kashipara

Mark A Spieckerman

Sankar Bokka

Bryan Byron Craver

Anthony Truscott

Howard A Botts

Matt Delmage

David Stiff

Brian Costabile

Duncan Chen

Systems and methods for property valuation using automated valuation models are described herein, which involve a complex series of workflows for data processing, automated valuation modeling, and error detection—each of which are capable of leveraging machine learning algorithms/techniques and can be combined and operated together in a specific manner in order to improve data availability and data quality, improve the accuracy of generated property value estimates, improve the performance of the models over time, and allow the property value estimation to be adapted to various use cases. Estimation of property value may involve an ensemble model which reconciles the outputs of different sub-models based on a use case, with the sub-models using different approaches that have their own strengths and weaknesses.

Artificial intelligence model surveillance system

Systems and methods for property valuation using automated valuation models are described herein, which involve a complex series of workflows for data processing, automated valuation modeling, and error detection&#x2014;each of which are capable of leveraging machine learning algorithms/techniques and can be combined and operated together in a specific manner in order to improve data availability and data quality, improve the accuracy of generated property value estimates, improve the performance of the models over time, and allow the property value estimation to be adapted to various use cases. Estimation of property value may involve an ensemble model which reconciles the outputs of different sub-models based on a use case, with the sub-models using different approaches that have their own strengths and weaknesses.

Multi-use artificial intelligence-based ensemble model

A computer system and associated processes are disclosed for grouping similar real estate properties into contiguous neighborhoods, and for generating neighborhood-specific models capable of estimating property values within their respective neighborhoods. A clustering component uses various sources of property-level data to group properties based on measures of property similarity. For example, the clustering component may use features extracted from property images to identify properties with similar characteristics. As another example, the clustering component may measure property similarity based on how frequently specific properties are designated as comparable in appraisal reports. A model generator uses a machine learning process to determine, for specific neighborhoods, correlations between property attributes and values, and uses these correlations to generate the neighborhood specific models.

Computer processes for clustering properties into neighborhoods and generating neighborhood-specific models

A BLE location system and method are disclosed. The BLE system may provide accurate location of a BLE enabled object in a three dimensional space. The three dimensional space may be a building and the BLE system and method permits accurate location at a room, bay, and bed level in the three dimensional space to be determined. In some embodiments, the BLE system may determine if a BLE enabled object crosses a boundary and the boundary may be, for example, a boundary to a room, such as a door, a boundary to a space, such as a hallway or meeting area, or a boundary to a particular location identified by set of coordinates (X,Y or X,Y,Z for example). The determination of the boundary crossing of the BLE enabled object or the location of the BLE enabled object may be used for staff and patient locating and their associated workflows as well as high accuracy asset tracking in a hospital embodiment.

Bluetooth low energy location system and method

A system and method for rapid room entry are provided in which at least two Bluetooth low energy (BLE) beacons may be used to determine when a BLE enabled object has crossed a boundary. The BLE enabled object may sense the signals from BLE beacon and a location engine may determine the crossing of the boundary based on the sensed signals from each BLE beacon. Each BLE beacon may have a directional antenna so that a portion of the signal having a strong strength is directed towards the boundary and a portion of the signal having a weaker strength is directed away from the boundary.

Bluetooth low energy rapid room entry system and method

A method and system for determining a real-time location of an object or person in a facility using low frequency magnetic induction positioning is disclosed herein. Each of the plurality of low frequency receivers is configured to receive a signal packet from a low-frequency magnetic induction transmitter, decode the signal packet, and estimate a distance from the low-frequency magnetic induction transmitter to the low-frequency receiver based on the decoded signal packet.

Low frequency magnetic induction positioning system and method

The present invention provides a method and system for determining a near-field communication interaction in a wireless tracking mesh network. The present invention preferably utilizes near-field communication devices in conjunction with tracking tags to transmit signals for reception by sensors stationed throughout a facility which form a mesh network and forward the signals to an information engine for analysis. Bearers of the near-field communication devices preferably include individuals, objects, assets and rooms of the facility.

Wireless tracking system and method utilizing near-field communication devices

The present invention provides a solution to mistaken location calculations based on multipath effects. The present invention determines a real-time location of an object in a facility using a combination of location algorithms, with a signal characteristic for a wireless signal from a communication device attached to the object received at a sensor of a mesh network. The location algorithms preferably include at least two of a proximity algorithm, a radial basis function algorithm, a maximum likelihood algorithm, a genetic algorithm, a minimum mean squared error algorithm, a radiofrequency fingerprinting algorithm, a multilateration algorithm, a time difference of arrival algorithm, a signal strength algorithm, a time of arrival algorithm, an angle of arrival algorithm, a spatial diversity algorithm, and a nearest neighbor algorithm.

Growing community of inventors

San Diego, CA, United States of America

Wei Geng