Kyndryl, Inc.

International Business Machines Corporation

Amol Bhaskar Mahamuni

Vidhya Shankar Venkatesan

Jinho Hwang

Larisa Shwartz

Awadesh Kumar Tiwari

Rafal Bigaj

Frank Bagehorn

Marcos Vinicius L Paraiso

Dorothea W Wiesmann Rothuizen

Kiran Kumar K

Sundaravelu Shanmugam

Archana Dixit

Debasisha Padhi

Nithyaraj G S

Yosha Singh Tomar

Niroop Sathyam Moses J

Nidhi Patel

Mahesh Sondkar

Kamalakanta Mishra

Joel Augustine George

A trained classification model is executed, causing a classification of a first set of file system usage data into a set of categories comprising a trend category and a periodicity category. Responsive to the first set of file system usage data being classified into the trend category, a time series of the first set of file system usage data is generated. Responsive to the first set of file system usage data being classified into the periodicity category, using an anomaly detection model, an anomaly within the first set of file system usage data is detected. Responsive to predicting that the time series will exceed a threshold, a first reconfiguring of a file system resource is caused, altering a capacity of the file system. Responsive to detecting the anomaly, a second reconfiguring of the file system resource is caused, altering a capacity of the file system.

Technique selection for file system utilization prediction

Some embodiments of the present disclosure are directed to systems, computer-readable media, and computer-implemented methods for multi-node failure processing in computer networks. In particular, some embodiments are directed to generating and displaying an impact area graph for a respective node from a plurality of nodes in a network, wherein the impact area graph depicts the relative predicted impact to each other node in the network from a failure of the respective node. Other embodiments may be disclosed or claimed.

Multi-node failure processing for computer networks

A computer-implemented method, in accordance with one embodiment, includes collecting data from a plurality of predefined functional areas in a particular geographical area in which a plurality of physical objects are located, at least some of the data relating to vandalism. Wrangling is performed on the data to correlate the data from the functional areas with respective ones of the physical objects. The wrangled data corresponding to each of the physical objects is transformed into features corresponding to a the functional areas. For each of the physical objects, the features are processed according to predefined rules for generating a rank for each of the functional areas. Dynamic weights are computed for at least some of the features to account for data drift by comparing historical data with latest data. The ranks and dynamic weights are transformed into a vandalism score for each of the physical objects, which is output.

Computation, prediction, and use of vandalism scores

A method is provided that includes configuring a cellular phone to function as a mobile debit card by installing an application for contactless interfacing with ATMs. The method supplements the application with a neural network (NN) based biometric verification process configured to reduce an incorrect user error value over time to increasingly harden the application to undesired intrusion. The NN based biometric verification process comprises: performing an initial face recognition; greeting the user with one of a plurality of questions in a specific language of the user and evaluating a pre-defined answer provided from the user in the specific language; and detecting, in an acoustic utterance having dialogue in support of an ATM session, a voice and a prosody style indicative of the user in combination with lip and face movements made by the user corresponding to and in synchronization with the acoustic utterance.

Secure and contactless debit transactions

A processor may receive authentication data related to inputs of a user to predetermined authentication prompts. The processor may select devices from a set of registered devices to use for providing a first password prompt to the user. The processor may identify one or more output formats for each of the selected devices. The processor may generate a first password prompt having two or more password prompt components, where each password prompt component has an output format. The processor may send the two or more password prompt components to respective selected devices.

Personalized password prompting system

Systems, computer-implemented methods, and computer program products that can facilitate refinement of a predicted event based on explainability data are provided. According to an embodiment, a system can comprise a memory that stores computer executable components and a processor that executes the computer executable components stored in the memory. The computer executable components can comprise an interpreter component that identifies a probable cause of a predicted event based on explainability data. The computer executable components can further comprise an enrichment component that executes a diagnostic analysis based on the probable cause.

Refinement of a predicted event based on explainability data

Systems, methods, and computer programming products for predicting, preventing and remediating failures of batch jobs being executed and/or queued for processing at future scheduled time. Batch job parameters, messages and system logs are stored in knowledge bases and/or inputted into AI models for analysis. Using predictive analytics and/or machine learning, batch job failures are predicted before the failures occur. Mappings of processes used by each batch job, historical data from previous batch jobs and data identifying the success or failure thereof, builds an archive that can be refined over time through active learning feedback and AI modeling to predictively recommend actions that have historically prevented or remediated failures from occurring. Recommended actions are reported to the system administrator or automatically applied. As job failures occur over time, mappings of the current system log to logs for the unsuccessful batch jobs help the root cause analysis becomes simpler and more automated.

Predictive batch job failure detection and remediation

Anomaly detection using zonal parameter characteristics and non-linear scoring is provided. Anomalous behavior characteristics of a parameter and group of parameters are identified within time series data using an optimal artificial intelligence model of a plurality of artificial intelligence models. Anomalies are detected based on the anomalous behavior characteristics of the parameter and the group of parameters within the time series data. The anomalies are classified into a corresponding anomaly category. A root cause of the anomalies is determined based on the corresponding anomaly category. One or more action steps are performed to remediate the root cause of the anomalies.

Anomaly detection using zonal parameter characteristics and non-linear scoring

In an approach for generating hardware failure labels, a processor receives sensor data from a plurality of sensors associated with a hardware system. A processor calculates an adaptive stress factor, wherein the adaptive stress factor is a dynamic selection model. A processor calculates an adaptive stress time window, wherein the adaptive stress time window is a spatial distribution of the adaptive stress factor. A processor calculates a relative duty cycle, wherein the relative duty cycle is a first function of an internal state of the hardware system, a type of input to the hardware system, the adaptive stress factor, and the adaptive stress time window. A processor generates a failure label, wherein the failure label is calculated as a second function of the relative duty cycle and a design duty cycle.

Predicting hardware failures

A task identification, an operator key, and a supervisor key are generated. The task identification is associated with a system administration task request and can include information from the request to initiate the system administration task request such as the system name. The operator key and the supervisor key are encrypted. Via a secure network, the task identification and the operator key are sent to an operator computing device and the supervisor key is sent to a supervisor computing device. In response to determining that the task identification is valid, the operator key returned from the operator computing device is decrypted. In response to determining that the decrypted operator key is valid, the encrypted supervisor key returned from the supervisor computing device is decrypted. In response to determining that the decrypted supervisor key is valid, an indication of a successful validation of the system administration task is provided.

Growing community of inventors

Bengaluru, India

Amol Bhaskar Mahamuni