Fmr Corp.

Intuit, Inc.

Sunil Madhani

Anu Sreepathy

Bahram Omidfar

Jordan Donofrio

Tobias Donath

Valentine Foti

Fabrizio Machado

Christopher A McDermott

William Metzler

Samir Kakkar

Methods and apparatuses are described for of recognizing handwritten characters in digital images using context-based machine learning. A server captures an image of a document that comprises one or more handwritten data fields, the document associated with a user identifier. The server identifies a field type for each handwritten data field in the image. The server creates a pixel intensity array for each character in each handwritten data field and determines whether a user-specific character map exists for the user identifier. If a map exists, the server retrieves the map and generates digital form data by executing a user-specific handwriting classifier using the map, the pixel intensity arrays, and the field types. If a map does not exist, the server builds a map based upon the pixel intensity arrays and generates digital form data by executing a baseline handwriting classifier using the map, the pixel intensity arrays, and the field types.

Recognition of handwritten characters in digital images using context-based machine learning

Methods and apparatuses are described for monitoring usage and adjusting operational characteristics of physical assets. Asset sensors capture temperature data and x-y-z coordinate displacement data associated with a physical asset. A reference sensor captures temperature data of a defined physical area. For each asset sensor, a server computing device monitors the temperature data and the x-y-z coordinate displacement data. The server applies triggers to the temperature data and the displacement data to determine whether a change event occurred. The server records the temperature data and the displacement data when a change event occurred for the physical asset. The server generates instructions comprising a change to: an operational state or an availability of the physical asset. The server transmits the instructions to a remote device associated with the physical asset. The remote device executes the instructions to change: the operational state or the availability of the physical asset.

Monitoring usage and adjusting operational characteristics of physical assets

Methods, systems and apparatuses, including computer program products, are described for detecting a proximity of a mobile computing device during a user session. The mobile computing device enters a first operational mode during the user session and obtains sensor data from at least one sensor responsive to a property of the location. The mobile computing device forwards to a server computing device, a baseline profile including the sensor data and a time stamp indicating a time the sensor data was obtained. The mobile computing device receives from the server computing device, a differential trigger threshold including a range of permissible values for sensor data obtained from the at least one sensor. The mobile computing device obtains updated sensor data from the at least one sensor. The mobile computing device enters a second operational mode when the updated sensor data is outside of the differential trigger threshold.

Proximity and movement detection of a mobile computing device during a user session

Methods, systems and apparatuses, including computer program products, are described for detecting movement of a mobile computing device based upon geospatial data about a property location of the mobile computing device. The mobile computing device generates a baseline geospatial profile including baseline altitude data, baseline pressure data, and a predetermined pressure range. The mobile computing device enters a first operational mode permitting a user to establish a user session on the mobile computing device. The mobile computing device obtains altitude data from a first sensor and pressure data from a second sensor, and generates a geospatial signature based upon the altitude data and the pressure data. The mobile computing device compares the geospatial signature and the baseline geospatial profile, and enters a second operational mode if a difference between one or more corresponding values of the baseline geospatial profile and the geospatial signature exceeds a predetermined threshold.

Geospatial-based detection of mobile computing device movement

Methods, systems and apparatuses, including computer program products, are described for determining a performance metric of a mobile computing device application. A test computing device captures a plurality of images displayed on a mobile computing device based on execution of a mobile computing device application. The test computing device determines a first property for first and second images of the plurality of images. A first performance parameter is set based on a difference between the first properties of the first and second images. The test computing device determines a first property for third and fourth images of the plurality of images. A second performance parameter is set based on a difference between the first properties of the third and fourth image. A performance metric is determined based on a difference between the first performance parameter and the second performance parameter.

Automated measurement of mobile device application performance

Methods, systems and apparatuses, including computer program products, are described for monitoring a presence of an authorized user of a mobile computing device during a user session based upon motion of the mobile computing device. The mobile computing device enters a first operational mode based upon a user session established by a user. The mobile computing device generates a first motion signature based upon first motion data obtained from a plurality of sensors during the user session, the first motion signature corresponding to the user. The mobile computing device generates a second motion signature based upon second motion data obtained from the plurality of sensors during the user session. The mobile computing device enters a second operational mode if a difference between the first motion signature and the updated motion signature exceeds a predetermined threshold.

Growing community of inventors

Cary, NC, United States of America

Sunil Madhani