International Business Machines Corporation

Kyndryl, Inc.

Anuradha Bhamidipaty

Debasisha Padhi

Kalapriya Kannan

Daniela Rosu

Anshu Narendra Jain

Ashish Kundu

Vibha Singhal Sinha

Sreekrishnan Venkateswaran

Moncef Benboubakeur

Arun Kwangil Iyengar

Biplav Srivastava

Yaoping Ruan

Shang Qing Guo

Srikanth Govindaraj Tamilselvam

Nianjun Zhou

Sai Zeng

Krishna Kummamuru

James Randal Moulic

Constantin Mircea Adam

Garfield Winston Vaughn

Gopal Sarma Pingali

Mark Edward Podlaseck

Nikolaos Anerousis

Frederick Y Wu

Elham Khabiri

Mithkal M Smadi

Aliza Rivka Heching

Dhavalkumar C Patel

Shubhi Asthana

Alan Hartman

Parul Alok Mittal

Saiprasad Kolluri Venkata Sesha

Julija Narodicka

Karthik Sivakumar

Jia Liu

Shrey Shrivastava

Shailabh Nagar

Nidhi Rajshree

Frederick Y-f Wu

Mitesh H Vasa

Bhanukiran Vinzamuri

Anubha Verma

Suman K Pathapati

Winnie Wing-Yee Cheng

Jayan Nallacherry

Clifford A Pickover

James R Kozloski

Erik Rueger

Peter Hans Westerink

Evelyn Duesterwald

Karthik Visweswariah

Robert J Baseman

Michael Starkey

Rema Ananthanarayanan

Nanjangud C Narendra

Debdoot Mukherjee

Ramendra K Sahoo

Wesley M Gifford

Andrew Lawrence Frenkiel

Deepak S Padmanabhan

Chandrasekhara K Reddy

Nam H Nguyen

Firas Bouz

Sarin Kumar Thayyilsubramanian

Virendra K Varshneya

Srideepika Jayaraman

Virendra K Varshney

Jiri Nehybka

A computer-implemented method in accordance with one embodiment includes, in response to a submission of an input dataset to an artificially intelligent application, receiving an explanation from each module of the application. The modules are configured within the application in a serial sequence in which each module, upon receiving the input dataset and any input generated by an immediately preceding module of the serial sequence, generates output that is forwarded as input to a next module, if any, in the sequence. A determination is made that at least two of the received explanations are semantically inconsistent.

Semantic consistency of explanations in explainable artificial intelligence applications

A computer implemented method of administering a complex system includes receiving multivariate data from a plurality of sensors of the system in an ambient state. Event sequences in the received multivariate data are identified. The multivariate event sequences are projected to a lower stochastic latent embedding. A temporal structure of the sequences is learned in a lower latent space. A probabilistic prediction in the lower latent space is provided. The probabilistic prediction in the lower stochastic latent space is decoded to an event prediction in the ambient state.

Event time characterization and prediction in multivariate event sequence domains to support improved process reliability

Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises ingesting tabular data from at least one modality of a plurality of modalities; simultaneously extracting data and generating a prediction model for a task of a computing device from the extracted data from at least two modalities in the plurality of modalities; generating a data signature based on the generated prediction model from the at least two modalities by leveraging the generated prediction model for ingested tabular data and extracted data; comparing the generated data signature to identified data signatures stored in at least one modality in the plurality of modalities; and performing a task based on the generated data signature and a validation of the comparison of identified data signatures.

Multi-modal data explainer pipeline

A computing device includes a processor and a storage device. A wafer asset modeling module is stored in the storage device and is executed by the processor to configure the computing device to perform acts identifying and clustering a plurality of assets based on static properties of a wafer asset using a first module of the wafer asset modeling module. The clustered plurality of assets is determined based on dynamic properties of the wafer asset using a second module of the wafer asset modeling module. Event prediction is performed by converting a numeric data of the clustered plurality of assets to a natural language processing (NLP) domain by a third module of the wafer asset modeling module. One or more sequence-to-sequence methods are performed to predict a malfunction of a component of the wafer asset and/or an event based on past patterns. Prediction information is stored in the storage device.

Wafer asset modeling using language processing methods

An actuator to execute on a server may be automatically selected based on risk of failure and damage to the server. Requirement specification and environment parameters may be received. A subset of actuators may be selected based on a risk threshold from an actuator catalog database storing actuator information and actuator risk metadata associated with a plurality of actuators. The actuator risk metadata may be augmented with risk information. A ranked list of the subset of actuators may be generated based on the actuator risk metadata associated with each actuator in the subset. An actuator in the ranked list may be executed on the server.

Action recommendation to reduce server management errors

An explainable artificially intelligent (XAI) application contains an ordered sequence of artificially intelligent software modules. When an input dataset is submitted to the application, each module generates an output dataset and an explanation that represents, as a set of Boolean expressions, reasoning by which each output element was chosen. If any pair of explanations are determined to be semantically inconsistent, and if this determination is confirmed by further determining that an apparent inconsistency was not a correct response to an unexpected characteristic of the input dataset, nonzero inconsistency scores are assigned to inconsistent elements of the pair of explanations. If the application's overall inconsistency score exceeds a threshold value, the system forwards information about the explanation, the offending modules, and the input dataset to a downstream machine-learning component that uses this information to train the application to better respond to future input that shares certain characteristics with the current input.

Aspects of the present invention disclose a method, computer program product, and system for multi-factor authentication. In response to a request for an action, the method includes one or more processors whether a first authentication credential passes validation. In response to determining that the first authentication credential does pass validation, the method further includes one or more processors determining a second authentication credential, wherein the second authentication credential includes an indication of a wireless connection between a first computing device and a second computing device. The method further includes one or more processors determining whether the second authentication credential passes validation. In response to determining that the second authentication credential passes validation, the method further includes one or more processors allowing execution of the requested response.

Multi-factor authentication utilizing device pairing

Embodiments of the invention are directed a computer-implemented method for efficiently assessing data quality metrics. A non-limiting example of the computer-implemented method includes receiving, using a processor, a plurality of updates to data points in a data stream. The processor is further used to provide a plurality of data quality metrics (DQMs), and to maintain information on how much the plurality of DQMs are changing over time. The processor also maintains information on computational overhead for the plurality of DQMs, and also updates data quality information based on the maintained information.

Efficient real-time data quality analysis

Embodiments of the present invention provide notification management across a plurality of electronic communication devices based on the present situational context of the intended communication recipient. Some types of relevant situational context information include the geographic location of the intended recipient, what electronic communication devices they may have in their possession, calendar or schedule information, the presence of other people, the identity of other people present in their vicinity, their relationship to the communication sender, and context information concerning the sender, such as how frequently the sender has attempted to communicate with the intended recipient and news information relevant to the known or assumed location of the sender. Notifications are managed by adjusting which electronic communication devices emit notifications and what type of notifications are emitted.

Management of communication notifications based upon geographic location

Embodiments of the invention are directed a computer-implemented method for assessing data quality. A non-limiting example of the computer-implemented method includes using a processor to receive a plurality of updates to data points in a data stream. The processor is further used to compute instances of a data quality metric (DQM) from the data points in the data stream. The instances of the DQM are configured to differentiate the data points in the data stream by time and assign a higher weight to the instances of the DQM computed from more recent data points in the data stream. The instances of the DQM are continuously updated as more of the data points are received by the processor while limiting cycles of the processor consumed by updating the instances of the DQM to a threshold.

Real-time data quality analysis

An approach is provided for storing a snapshot of an execution image of a virtual machine (VM) instance. Based on VM, application, criticality, and change parameters, and based on a recommendation model trained on historical data about effects that changes caused by VM execution had on a capacity of a storage system that stores execution images of VM instances in first datastores, a tier is selected from multiple tiers of the storage system as the tier recommended for storing the snapshot. A datastore is selected for storing the snapshot so that the selected datastore is associated with the selected tier and selected from second datastores dedicated to storing only snapshots. The snapshot is created in the selected datastore and in the selected tier and unused space in a portion of the storage system for storing the first datastores is reduced.

Space management for snapshots of execution images

Aspects of the present invention provide an approach for customizing media content being consumed at a location. For each of the viewers in a group consuming the media content at the location, a media profile having a set of media content preferences is created. These media profiles are aggregated to generate a composite profile that has a set of content restriction preferences for the group. As the media content is provided to and being consumed by the group, the media content is analyzed to identify any elements that have attributes that may be unsuitable to some viewers. If an element has a suitability attribute that violates the content restriction preferences for the group, the media content is modified to filter out the element.

Filtering of content in near real time

A system, method and program product for providing cognitive behavior security control (CBSC). A system is disclosed that includes: a repository having a plurality of challenges each including an interactive graphical task; a user interface for graphically presenting challenges to users; an enrollment system for assigning challenges to users and determining an authentic response for each user; an authentication system that collects an observed response from a user presented with an assigned challenge and determines a security control result based on a closeness of the observed response with the authentic response of the user.

Cognitive behavioral security controls

One or more embodiments identify server management actions for resolving problems associated with one or more nodes in information technology infrastructure. In one embodiment, a node-ticket record for an information processing node associated with at least one problem ticket is generated. A set of node-ticket clusters is queried based on the node-ticket record. Each of the set of node-ticket clusters maps a set of server management actions to set of historical node-ticket records associated with the node-ticket cluster. The set of server management actions was previously performed to resolve at least one operational problem associated with at least one information processing node. At least one set of server management actions associated with at least one of the set of node-ticket clusters corresponding to the node-ticket record within a given threshold is identified based on the querying.

Recommending server management actions for information processing systems

Growing community of inventors

Bengaluru, India

Anuradha Bhamidipaty