International Business Machines Corporation

Moninder Singh

Xuan Liu

Paul Andrew Moskowitz

Sastry Duri

Edith Gail Schonberg

Jung-Mu Tang

Charles Philippe Tresser

Ronald Perez

Erik Thomas Mueller

Jayant R Kalagnanam

Marco O Gruteser

Leora Morgenstern

Ghassan Chidiac

Leiguang Gong

Jeffrey G Elliott

Sudhir Verma

Fabio Dennis White

Michael D Patek

Yuk Wah Wong

Doug Riecken

George V Salmi

Jianying Hu

Tsuyoshi Ide

Jiri Navratil

Aleksandra Mojsilovic

Amit Dhurandhar

Naoki Abe

Kathryn Ann Bohrer

John Karat

Robert Hoch

Dogan Kesdogan

Catherine Anne Chess

A computer-implemented method, a computer program product, and a computer system for diagnosing anomalies detected by a black-box machine learning model. A computer determines a local variance of a test sample in a test dataset, where the local variance represents uncertainty of a prediction by the black-box machine learning model. The computer initializes optimal compensations for the test sample, where the optimal compensations are optimal perturbations to test sample values of respective components of a multivariate input variable. The computer determines local gradients for the test sample. Based on the local variance and the local gradients, the computer updates the optimal compensations until convergences of the optimal compensations are reached. Using the optimal compensations, the computer diagnoses the anomalies detected by the black-box machine learning model.

Diagnosing anomalies detected by black-box machine learning models

The invention includes various systems, architectures, frameworks and methodologies that can securely enforce a privacy policy. A method is included for securely guaranteeing a privacy policy between two enterprises, comprising: creating a message at a first enterprise, wherein the message includes a request for data concerning a third party and a privacy policy of the first enterprise; signing and certifying the message that the first enterprise has a tamper-proof system with a privacy rules engine and that the privacy policy of the first entity will be enforced by the privacy rules engine of the first enterprise; sending the message to a second enterprise; and running a privacy rules engine at the second enterprise to compare the privacy policy of the first enterprise with a set of privacy rules for the third party.

Secure system and method for enforcement of privacy policy and protection of confidentiality

A system, method and computer program product provides a solution to a class of categorization problems using a semi-supervised clustering approach, the method employing performing a Soft Seeded k-means algorithm, which makes effective use of the side information provided by seeds with a wide range of confidence levels, even when they do not provide complete coverage of the pre-defined categories. The semi-supervised clustering is achieved through the introductions of a seed re-assignment penalty measure and model selection measure.

System and method for adaptive categorization for use with dynamic taxonomies

Automated mapping of part numbers associated with parts in a bill of materials (BOM) submitted by a BOM originator to internal part numbers assigned to those parts by a BOM receiver is performed by one or more computers connected to one or more networks through one or more network interfaces. A first receive component receives one or more data sets containing historical data on bills of materials received in the past by the BOM receiver. A second receive component receives one or more data sets containing known mappings between internal part numbers used by the BOM receiver, and part numbers used by various BOM originators. A third receive component receives one or more data sets containing information of various parameters and their values describing the parts to which the BOM receiver has assigned internal part numbers. A fourth receive component receives one or more methods of automatically learning models for predicting internal part numbers from the above mentioned historical BOM data, mapping data and part parametric data. A learning component learns the models from the data. A fifth receive component receives a BOM from a requesting process. The BOM has one or more parts with a missing internal part number. A mapping component applies the learned models to the received BOM to automatically determine internal part numbers for all unmapped BOM originator part numbers. A release process assigns internal part numbers to all unmapped parts in the BOM and releases the BOM to the requesting process.

System and method for automated part-number mapping

A system and method for reasoning about concepts, relations and rules having a semantic network comprising at least one node from a predetermined set of node types, at least one link from a predetermined set of link types, and zero or more rules from a predetermined set of rule types, a subset of the rule types being matching rule types, each node and each link being associated with a set of zero or more rules; a network reasoning data structure having a reasoning type database having at least one regular expression, each of the regular expressions being a class of sequences having at least three node types and two link types, wherein the network reasoning data structure further has a context being a set of rules; and a reasoning engine having an activator for activating one or more activated paths in the semantic network, the set of activated paths having a common starting node in the semantic network, wherein the reasoning engine further has a validator for selecting a subset of the activated paths being valid paths, each rule from the set of rule matching types that is associated with one or more path elements on each valid path being matched by one or more rules in the context and wherein the reasoning engine further has a legal inferencer for selecting a subset of the set of valid paths being legal and valid paths, the legal and valid paths matching at least one of the regular expressions.

Method and knowledge structures for reasoning about concepts, relations, and rules

A method of sharing telematics data for a vehicle with service providers can include receiving the telematics data for the vehicle, where the telematics data dynamically changes over time, and comparing the telematics data with a privacy policy associated with the vehicle. The privacy policy can specify rules for selectively releasing items of the telematics data to one or more service providers. Data items of the telematics data can be selectively provided to the service providers according to the comparing step.

Method, system, and apparatus for dynamic data-driven privacy policy protection and data sharing

Automated mapping of part numbers associated with parts in a bill of materials (BOM) to internal part numbers assigned by a BOM receiver. Historical data on bills of materials, known part number mappings, and parametric data describing the parts associated with bills of materials re received. Prediction models, for predicting BOM receiver internal part numbers, are learned from the historical BOM data, known part number mappings data and parametric data. The learned models are applied to unmapped BOM originator part numbers to assign BOM receiver internal part numbers.

System for automated part-number mapping

An exemplary embodiment of the present invention includes a method to enforce privacy preferences on exchanges of personal data of a data-subject. The method comprises the steps of: specifying data-subject authorization rule sets having subject constraints, receiving a request message from a requester and a requester privacy statement, comparing the requester privacy statement to the subject constraints, and releasing the data-subject data in a response message to the requester only if the subject constraints are satisfied. The requester privacy statement includes purpose, retention, recipient, and access information, wherein the purpose information specifies the purpose for which the requested data is acquired, the retention information specifies a retention policy for the requested data, the recipient information specifies the recipients of the requested data, and the access information specifies whether the requested data should be accessing to the data-subject after the data has been released.

System, method, and business methods for enforcing privacy preferences on personal-data exchanges across a network

The invention includes various systems, architectures, frameworks and methodologies that can securely enforce a privacy policy. A method is include for securely guaranteeing a privacy policy between two enterprises, comprising: creating a message at a first enterprise, wherein the message includes a request for data concerning a third party and a privacy policy of the first enterprise; signing and certifying the message that the first enterprise has a tamper-proof system with a privacy rules engine and that the privacy policy of the first entity will be enforced by the privacy rules engine of the first enterprise; sending the message to a second enterprise; and running a privacy rules engine at the second enterprise to compare the privacy policy of the first enterprise with a set of privacy rules for the third party.

Growing community of inventors

Middletown, CT, United States of America

Moninder Singh