Bottomline Technologies Limited

International Business Machines Corporation

Jonathan Hewitt

Michael Marcinelli

John Canneto

Anne Baron

William Cashman

Flora Kidani

John Banks-Binici

Joseph T Wissmann

Sylvain P Galineau

Cobie Chin

A legal spend management solution is described herein, a solution that utilizes improved machine learning algorithms to match lines of a legal invoice to lines in a receipt from a set of receipts. The matching uses cosine similarity algorithms and Levenshtein distances to determine whether there is a match between the receipt and the invoice lines. The machine learning results are displayed using a novel set of icons that present the confidence score with a set of three squares below a document icon.

Machine learning comparison of receipts and invoices

A unique user interface for improving machine learning algorithms is described herein. The user interface comprises an icon with multiple visual indicators displaying the machine learning confidence score. When a mouse hovers over the icon, a set of icons are displayed to accept the teaching user's input. In addition, the words that drove the machine learning confidence score are highlighted with formatting so that the teaching user can understand what drove the machine learning confidence score.

Calibration of a machine learning confidence score

Visualization of a machine learning confidence score

Visualization of a machine learning confidence score and rationale

Machine learning visualization

Under the present invention, a central system in communication with a central directory is provided. The central system also communicates with one or more ancillary systems that each communicate with an ancillary storage unit. User account information is initially stored in the central directory according to unique identifiers. When a triggering event occurs (e.g., when he/she attempts to access an ancillary system, or when he/she is listed as an intended recipient of an electronic mailing message), the user's account information will be located within the central directory according to his/her unique identifier. Upon location, the account information is automatically communicated to the appropriate ancillary storage unit. Thus, the present invention provides 'just in-time' synchronization of account information between the central directory and the ancillary storage unit.

System, method and program product for managing user account information

Growing community of inventors

Exeter, NH, United States of America

Jonathan Hewitt