International Business Machines Corporation

Kyndryl, Inc.

James David Cleaver

Michael James McGuire

Thuy Luong

Stefan Harrer

Laurence J Plant

Seema Nagar

Pramod Vadayadiyil Raveendran

Michael Sean Brown

Sean Rory Costello

Kuntal Dey

Mary Kathryn Aldridge

Louise A McGuire

Gregory D Lee

Carlos Felipe F Da Fonseca

Ronald George Gottschalk

Mike McGuire

Mark Donovan

Christopher J De Vaney

Vikramsihn Ashok Desai

Stephen J Lea

Dallas McGuire Hindle

Malwina Bajsarowicz

Maria Virginia Williams

A system, method, and computer program product for implementing artificial intelligence module communication is provided. The method includes generating models associated with communications between real-time artificial intelligence modules. Classifiers associated with the models are generated and a master real-time artificial intelligence module associated with the modules and classifiers is detected. Real-time artificial intelligence modules are detected and communications between the master real-time artificial intelligence module and the real-time artificial intelligence modules are initiated. Updated classifiers, updated models, and updated self learning software are generated. The updated self learning software is executed and a resulting query associated with a Web search is executed.

Artificial intelligence module communication

In an approach to improve multi-data center environments by minimizing the environmental impact of workloads in multi-data center environments embodiments migrate at least a portion of one or more workloads between one or more data centers automatically to maximize a usage of renewable energy based on a predetermined threshold score of input power and a combination of renewal energy sources. Further, embodiments dictate, by a policy engine, where at least a portion of the one or more workloads can be hosted. Additionally, embodiments control, by a scheduling engine, how, when, and where at least a portion of the one or more workloads will migrate, and perform data replication to migrate data between a plurality of data center locations.

Minimizing the environmental impact of workloads

Monitoring and enhancing performance of containers using a calibration technique is implemented using a computer. Performance of a new container as part of an application running on the computer is checked by comparing a current performance of the new container with baseline data corresponding to the new container. The baseline data is derived from a calibration container corresponding to the new container. The new container is categorized in a category of performance based on the checking of the performance of the new container. An alert can be sent to a device of an administrator regarding the new container meeting a threshold of performance, in response to the new container meeting the threshold of performance. The alert can be sent to the device of the administrator for the administrator to initiate an action pertaining to the new container in response to receiving the alert.

Calibration technique using computer analysis for ascertaining performance of containers

Methods, systems, and computer program products for pre-packaging and pre-configuring software products using chatbot message exchanges with users are described. Embodiments may include receiving a user inquiry, initiating a first chat session comprising a primary chatbot within a user interface, receiving user request data corresponding to a first string of communications, and determining a product based on the user request data. Responsive to determining the product, embodiments may include initiating a second chat session comprising a secondary chatbot configured to elicit product feature information about the product within the user interface; receiving product data corresponding to a second string of communications comprising the product feature information; determining product package parameters based on product information; determining executables to provide the product based on user request data, product feature information, and product package parameters; and compiling the executables in respective groups based user requirements and user characteristics.

Pre-packaging and pre-configuration of software products using chatbots

Machine logic for causing a computer system to perform the following operations (not necessarily in the following order): (i) receiving, by a historical decisions and opinions data store, decisions and opinions that have been communicated, propagated and/or otherwise espoused by a first entity; (ii) receiving, by an influencer data store, a plurality of influencer data sets, with each influencer data set including information indicative of opinions expressed by a respectively corresponding influencer; (iii) performing, by reverse chain engine, reverse chaining using the following inputs: (a) data of the historical decisions and opinions data store, and (b) the plurality of influencer data sets; and (iv) predicting, by a prediction engine, a likely future decision of the first entity using output of the reverse chaining operation.

Predictive decision making based on influence identifiers and learned associations

A method and system for automatically removing undesirable vegetation is provided. The method includes receiving by a first vehicle, data describing a specified geographical area for scanning. The specified geographical area is divided into a plurality of sectors and a second vehicle is directed to a first sector of the plurality of sectors. First geographical coordinates associated with areas of undesirable vegetation growth located within the first sector are receiving from the second vehicle and an optimal travel path from a current location of the first vehicle to the areas of undesirable vegetation growth located within first sector are determined based on analysis of the first geographical coordinates. The first vehicle is directed to the areas of undesirable vegetation growth via the optimal travel path and a process for eliminating the areas of undesirable vegetation growth is executed.

Automated vegetation removal

A method, apparatus, system, and computer program product for managing a network data processing system. Digital twins of physical devices in the network data processing system are run by a computer system. The digital twins process workloads and the digital twins communicate with each other. An impact on a number of parameters for a first set of the digital twins that a second set of the digital twins has on the first set of the digital twins is identified by the computer system. A set of actions is performed by the computer system based on the impact on the number of parameters.

Data center management using digital twins

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining a style feed including a plurality of original works by an author. An author-style model for the author is built based on the style feed by use of a selected neural network, and a publication is generated in the style of the author based on the author-style model.

Cognitive natural language generation with style model

A method includes receiving, by a backend application, a request for a transaction from a frontend application, and determining, by the backend application, that the request is approved according to an approval policy. The method also includes creating, by the backend application, a single-use account, and requesting, by the backend application, a single-use code for the single-use account from a financial institution. The method also includes receiving, by the backend application, the single-use code, and sending, by the backend application, the single-use code to the frontend application.

Shared voting for accounting

A method and system for improving a machine learning technical support applicant selection process is provided. The method includes retrieving and analyzing, in real time, job role data, resume based data, and sensor data associated with a plurality of individuals. A specialized memory repository is generated within a specified portion of a hardware memory device and results of the analysis are stored within the specialized memory repository. Self-learning software code for executing a job applicant selection process is generated and a plurality of current resumes and previously generated time-based resumes are retrieved for current job applicants for a specified position. The current resumes are analyzed with respect to the previously generated time-based resumes and associated inconsistencies are determined. A first job applicant is selected and the self-learning software code is modified.

Machine learning technical support selection

A cognitive coaching method; detecting one or more real-time specific action occurrences during one or more game phases; generating, with a heat map generator, one or more real-time heat maps with one or more specific action label based on the detected one or more real-time specific action occurrences; training a heat map image classifier with an analytics module; transposing one or more historical heat maps comprised in a historical heat map library onto the one or more generated real-time heat maps, in real time, to generate strategic insight on one or more opposing teams; analyzing, using a predictive module, a future potential outcome based on the one or more transposed heat maps; and signaling, to a user, a recommended corrective action deployment strategy based on the analysis of the future potential outcome.

In-game strategic insight with real-time heat map generation and historical heat maps

Computerized devices search each of a group of different calendars of a group of attendees of a proposed event for an available timeslot within each of the calendars that meets boundary conditions specified for the proposed event. In response to failing to find an available time slot in common to all attendee calendars that meets the boundary conditions, the devices autonomously identify a common existing event scheduled within the calendars of the attendees that can accommodate the boundary conditions and add the new event to the existing event, or reschedule a previously scheduled event of one or more of the attendees to create a common, free timeslot for the new event where the event cannot be accommodated within an existing event.

Autonomous event generator

Described herein are techniques for transmitting data to an offline Internet of Things (IoT) device using a transient device. The techniques including a method comprising receiving, at a transient device in a first location that is communicatively coupled to a base station by a first network at a first time, a first portion of a plurality of portions of data for delivery to an offline IoT device. The method further including connecting the transient device in a second location to the offline IoT device using a short-range network at a second time after the first time. The method further including transferring the first portion of the plurality of portions of data from the transient device to the offline IoT device using the short-range network.

Offline device management

Methods, computer program products, and systems are presented. The methods include, for instance: obtaining sample essays, sample annotations corresponding to the sample essays, and a subject content for building a subject domain comprehension model and an essay annotation model, by use of one or more neural network. The nodes of the subject domain comprehension model and the essay annotation model are interconnected based on respective relevancies for automatically annotating student works according to a standard of review corresponding to submitting students.

Cognitive essay annotation

According to one embodiment, a method, computer system, and computer program product for decoying poachers away from an animal equipped with a tracking device is provided. The present invention may include generating, based on machine learning and movement patterns of the tracked animal, one or more decoy paths; transmitting instructions to one or more decoy transmitters to simulate characteristics of the tracking device, and to simulate the decoy paths by moving to and/or transmitting decoy signals at sequential locations at corresponding times to imitate signals from the tracking device; and, responsive to determining that the one or more decoy transmitters are not capable of simulating all of the decoy paths, removing one or more decoy paths.

Growing community of inventors

Grose Wold, Australia

James David Cleaver