International Business Machines Corporation

Nuance Communications, Inc.

Kyndryl, Inc.

Ea-Ee Jan

Michael Bender

Rhonda L Childress

Evelyn R Anderson

David M Lubensky

Benoit Maison

Xiaolan Zhang

Osamuyimen Stewart

Niyu Ge

Xiang Yang Li

Vaibhava Goel

Karthik Visweswariah

Vasanth Bala

Lakshminarayanan Renganarayana

Yuk Lung Chan

Soumitra Sarkar

Ramesh Ambat Gopinath

Ye Wy Wang

Yixin Diao

Hong-Kwang Jeff Kuo

Amitkumar Manoharrao Paradkar

Darrell Christopher Reimer

Sarah White Eagle

Xiang Li

Yu Zhang

Jian Ni

Jayashree Vaidyanathan

Subrata Kumar Das

Jerome L Quinn

William J Ablondi

Zhi Ping Zhou

Wolfgang O H Richter

Chen Ch Bi

Raymond L Co

Andrzei Sakrajda

Katherine C Verbist

A method and system for improving an automated hardware apparatus failure prediction system is provided. The method includes automatically retrieving operational data associated with operation of a hardware device being monitored for potential failure. Differing time frame software windows associated with observing operational data and hardware device are determined and the operational data is analyzed. In response, an apparatus malfunction prediction software application and a component prediction software application is generated. Features associated with execution of the software applications are generated and a first group of features are added to software code of the apparatus malfunction prediction software application. A second group of features are additionally added to software code of the component prediction software application.

Automated hardware failure prediction framework

A method of providing a maintenance schedule that includes generating by a processor of a machine learning hardware device a predictive score for failure for each hardware device failure within a plurality of hardware devices to be serviced; determining by the processor a number of service misses for the hardware devices during a window of service; prioritizing by a processor of the machine learning hardware device each hardware device having a predictive score for failure by a business impact factor; and generating by the processor of the machine learning hardware device a maintenance schedule for the plurality of hardware devices to be serviced using the predictive score that has been prioritized by said business impact factor, wherein the service misses are selected for hardware devices having a lowest priority by the prioritizing of the predictive score by the business impact factor.

Cognitive prioritization model for hardware device prediction maintenance delivery

A computer-implemented method for generating a database of business cases correlated datasets includes receiving a text string indicating a business case topic. The processor isolates a plurality of data types in the dataset that are associated with the business case topic, and correlates the business case topic with the data types. The processor then determines data type links that associate the business case topic with the correlated data types. The processor evaluates each of the one or more data type links for a correlation to the business case topic, and assigns a confidence level value for the correlation. The processor next assigns a business value score for the correlated data type links based on the confidence level value and generates a business case database. The business case database is generated using the plurality of data types, the confidence level for each data type link and the business value scores.

Structured data correlation from internal and external knowledge bases

Systems, methods, and computer program products relating to clustering unstructured data. A set of unstructured documents is tokenized to produce a plurality of tokens. A frequency at which terms appear in the plurality of tokens is analyzed, to generate a vocabulary of terms. A vocabulary indices matrix is generated based on the generated vocabulary of terms. The matrix relates to the set of unstructured documents. A plurality of rows in the vocabulary indices matrix are matched to generate a plurality of clusters for the set of unstructured documents.

Unstructured data clustering of information technology service delivery actions

A tool for protecting outdoor objects from weather related damage. Responsive to a registration request, the tool registers an object and an originating location where the object is currently located. The tool determines whether a risk threshold for the object is exceeded based, at least in part, on weather conditions at the originating location. Responsive to a determination that the risk threshold for the object is exceeded, the tool instructs one or more drones to relocate the object from an originating location to a protected location that is protected from the weather conditions.

Weather based object protection using drones

A protective action system and method includes detecting the impending weather conditions for a geographic region, and in response to detecting the impending weather conditions, determining that an initial location of the autonomous vehicle is located in the geographic region affected by the impending weather conditions, calculating a current risk of damage to the autonomous vehicle based on the impending weather conditions in the geographic region and a current state of the autonomous vehicle, comparing the current risk of damage to a threshold of acceptable risk of damage, wherein, the current risk of damage exceeds a threshold of acceptable risk, assessing a user calendar to determine that taking a protective action by the autonomous vehicle is acceptable, and instructing the autonomous vehicle to take the protective action so that the current state of the autonomous vehicle is changed to a safe state to avoid damage from the impending weather conditions.

Protective action for protecting autonomous vehicles from impending weather conditions

A method and system to assist people traveling together through a transport hub. Access to personal data is provided for members of a group of people traveling together through the transport hub for a trip. A preferred route is mapped, from a current location of the group, for each person to travel through the transport hub. A group route, which is route to be commonly used by each person of the group, is selected. Sub-groups of members are selected to travel through the transport hub together in response to matching personal data. The personal data, travel data for the group, and transport hub data corresponding to the transport hub are monitored. Each person is alerted, in response to the monitored values, to begin moving from the current location towards a departure location along the selected group route to arrive at the departure location at a desired arrival time.

Leader directed coordination of navigation for a group traveling together in a transportation hub

Automatic teller machine network management control system executes a deterministic optimization process based on a deterministic forecasted withdrawal demand to determine a cash refill amount, and executes a stochastic simulation process to determine an overall automatic teller machine network management cost based on a stochastic forecasted withdrawal demand and the cash refill amount. The executing of the deterministic optimization process and the executing of the stochastic simulation process are iterated based on updated scaling parameter from the stochastic simulation process and the cash refill amount determined by the deterministic optimization process at current iteration until a termination threshold is met. A target scaling parameter that minimizes the overall automatic teller machine network management cost out of all iterations is determined, and target cash refill amount and time specification for refilling the automatic teller machine are determined based on executing the deterministic optimization process with the target scaling parameter.

Automated teller machine flow network and control system

The present invention is a method and system to assist a person traveling through a transport hub from a current location to a destination location with a smart portable computing device which provides personal data, travel data and transport hub data. The method maps a route according to personal preferences for the person to travel through the transport hub. Continuous monitoring of values provides an alert when the personal data, travel data, transport hub data, or predetermined parameters change.

Personal travel assistance system and method for traveling through a transport hub

As disclosed herein an information technology service ticket characterization method includes receiving tickets from one or more client devices during a time period, determining focus windows within the time period where each focus window includes an event window, identifying tickets received within the focus windows, determining a proportion of identified tickets that are related to a service event, and based on the proportion of identified tickets that are related to the service event, assessing the quality of the service event. A corresponding system and computer program product are also disclosed herein.

Characterization and assessment of information technology service events

The present invention is a method and system to assist people traveling together through a transport hub from a current location to a destination location using a smart portable personal computing devices which provide personal data, travel data and transport hub data. The method provides for sub-groups of traveler's having common travel preferences, and it maps routes according to those preferences for the group members to travel through the transport hub together. Continuous monitoring of values provides an alert on each sub-group member's personal computing device when the personal data, travel data, transport hub data, or predetermined parameters change.

Coordinating and providing navigation for a group of people traveling together in a transport hub

A parking assistance management system and method for assisting a parking of a vehicle based on a customized egress requirements is provided. The method includes the steps of identifying a user entering a vehicle, calculating a minimum egress space of the user, required for an egress of the user from the vehicle, detecting a parking space proximate at least one object, determining a viability of the parking space based on the minimum egress space, verifying that a distance between the vehicle and the at least one object is greater than the minimum egress space, when the vehicle is parked in the parking space, and broadcasting the minimum egress space to be received by other vehicles.

Vehicle parking assistance based on customized egress requirements

In an approach for detecting one or more applications in a VM, one or more processors establish a time duration. One or more processors detect two or more files, each file in the two or more files having a time stamp time that differs from a last modified time stamp time of at least one other file in the two or more files by no more than the time duration. One or more processors record an identifier for each file of the two or more files, a location, a name, and a last modified time stamp time of each file of the two or more files. One or more processors map the two or more files to an application installed on the VM.

Application discovery in virtual machines using temporal clustering of installation files

Access is obtained to a plurality of information technology services problem tickets. At least a first subset of the tickets include free text tickets with server names embedded in unstructured text fields. The server names are extracted from the first subset of the tickets via a statistical machine learning technique. Using the extracted server names, those of the first subset of the tickets from which the server names have been extracted are linked to corresponding server entries in a configuration information database to facilitate resolution of problems associated with the first subset of the tickets from which the server names have been extracted; and/or at least one of the extracted server names is identified as missing from a list of known server names.

Growing community of inventors

Ardsley, NY, United States of America

Ea-Ee Jan