Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: receiving, by a manager node, from a plurality of compute nodes metrics data, the manager node and the plurality of compute nodes defining a first local cluster of a first computing environment, wherein nodes of the compute nodes defining the first local cluster have running thereon container based applications, wherein a first container based application runs on a first compute node of the plurality of compute nodes defining the first local cluster, and wherein a second compute node of the plurality of compute nodes defining the first local cluster runs a second container based application; wherein the manager node has received from an orchestrator availability data specifying a set of compute nodes available for hosting the first application.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: creating a log data specific lexicon based on log data samples, each word in the log data specific lexicon corresponding to a weighted sentiment score with a binary polarity. A log message is obtained, and a sentiment value of the log message is assigned based on respective weighted sentiment scores of words appearing in the log message. The log message is classified for a class indicating an issue the log message addresses. An alert type for the log message is determined based on the sentiment value, the class, and a priority of the log message, and a system alert including a set of key performance indicators according to the alert type is produced to a user.

Abstract: A computer-implemented method to schedule special containers using a multi-queue scheduler. The method includes receiving, by a scheduler, a first pod including a first container including a first queue, a second queue, an event handler, and an error handler. The method further includes obtaining a set of characteristics for the first pod and determining that the first pod is a special pod. The method includes adding the first pod to the first queue, wherein the first queue is a special queue and includes a special function. The method also includes initiating the special function. The method further includes assigning, based on one or more placement rules, the first pod to a first node of a plurality of nodes.

Abstract: Disclosed embodiments provide techniques for log file manipulation detection. Log file terms are identified in a set of known good log files. A frequency metric is computed for the log file terms, and one or more clusters are formed that represent the terms and their corresponding frequency metric values within the set of known good log files. New log files are then obtained from an operational computer system. The frequency metric for those terms in the new log files are computed, and checked against the established clusters. A score is computed based on how similar the new log files are to the set of known good log files by comparing the frequency metric for terms in the new log file to the data in the previously obtained cluster(s). In response to a score exceeding a predetermined threshold, one or more mitigation actions are taken.

Abstract: Data security across data residency restriction boundaries is provided by obtaining and profiling a dataset on which a desired analysis is to be performed, with some results of the desired analysis to be transferred from one location to another, the dataset subject to data residency restrictions that restrict transfer of the dataset across a boundary to the another location, and the profiling identifying a profile level for the dataset, then automatically generating a container image based on the profile level and the data residency restrictions that restrict the transfer of the dataset across the boundary, the container image configured for instantiation and execution to process the dataset into a reformatted dataset not restricted by the data residency restrictions for transfer across the boundary, and storing the container image to a container registry.

Abstract: 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.

Abstract: A computer-implemented method, including: receiving, by the computing device, connecting device data from a connecting device associated with a participant of the video conference, wherein the connecting device data includes an audio quality data and a device connectivity data; determining, by the computing device, a conferencing readiness score based on the connecting device data; determining, by the computing device, the conferencing readiness score does not meet a threshold score; determining, by the computing device, an ameliorative action configured to raise the conferencing readiness score to meet the threshold score; and providing, by the computing device, the ameliorative action to the connecting device.

Abstract: A computer that identifies the video. The computer annotates the video using a deep learning tool. The computer analyzes the annotated video to highlight a dangerous condition. The computer identifies a video from a repository with the dangerous condition. The computer analyzes the video and the video from the repository using a similarity analysis. The computer determines a score based on the annotated video and based on comparing the video to the video from the repository and based on determining the score is above a threshold value, the computer generates an action.

Abstract: A computer-implemented method, a computer system and a computer program product enhance content submissions of support chats. The method includes acquiring a support request from a user, wherein the support request includes a content submission. The content submission is selected from a group consisting of audio data, image data and text data. The method also includes determining a classification of the support request based on a request type. The method further includes obtaining a set of requirements for the support request from a server based on the determined classification. In addition, the method includes determining that the content submission does not meet the set of requirements. Lastly, the method includes generating an augmented reality inspector to assist the user in adding content to meet the set of requirements in response to the set of requirements not being met by the content submission.

Abstract: Approaches for optimizing network demand forecasting models and network topology using hyperparameter selection are provided. An approach includes defining a pool of features that are usable in models that predict demand of network resources, wherein the pool of features includes at least one historical forecasting feature and at least one event forecasting feature. The approach also includes generating, using a computer device, an optimal model using a subset of features selected from the pool of features. The approach further includes predicting future demand on a network using the optimal model. The approach additionally includes allocating resources in the network based on the predicted future demand.

Abstract: A method includes executing, by a computing device, a reorganization command within an environment; monitoring, by the computing device, unprocessed replication transactions within the environment; determining, by the computing device, whether the unprocessed replication transactions exceed a threshold; and pausing, by the computing device, the executing the reorganization command in response to determining the unprocessed replication transactions exceed the threshold.

Abstract: An indication associated with an AI mode enabled by an AI system is received from a user with an affirmative opt-in status. A first task request associated with the user is identified. One or more instructions associated with the first task request are contextually recognized. The first task request is completed based on the contextually recognized one or more instructions.

Abstract: A method of dynamically creating a change template based on a change request received from a user. A change request is assigned a category based on the specifics of the request. If at least one existing template for the category the change request is assigned does not exist, historical change requests are analyzed to identify similar changes in historical change requests to the change request and data is copied from a template used for a historical change that was similar to the change requested to create a draft template. The draft template is altered to remove information which is not relevant to the change request and is stored in a repository. The altered draft template is sent to a reviewer as a proposed template; and approved proposed templates from the reviewer are stored in the repository by category.

Abstract: Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: determining a current transportation mode of a user with use of data of a user passenger vehicle associated to the user and data of a user auxiliary passenger vehicle associated to the user, wherein the user passenger vehicle is capable of carrying the user auxiliary vehicle, and wherein the user auxiliary vehicle is configured to be hand carried by the user; evaluating a current route of the user in dependence on the current transportation mode of the user as determined by the determining; and providing one or more output in dependence on the evaluating.

Abstract: A system may receive a query for a patient evaluation. The system may then receive historical patient information or hospital data, current medical information, patient information, and testing information. The system may then use the received information to generate a set of rules using a neural network and uses the rules to process an evaluation for the patient.

Abstract: An AI firewall engine dynamically manages firewall ports of an enterprise network to increase security. The AI firewall engine may begin with a baseline port profile configuration and then add firewall rules derived from natural language processing and machine learning from vendor recommended port requirements for an application. The AI firewall engine builds a dynamic port profile with rules that are applied to the firewalls. The AI firewall engine may then monitor system changes and dynamically updates the port profile and configurations on the firewalls.

Abstract: An asset stored on a storage device of a computer system is detected to be omitted from an asset-specific access policy. Using a utilization history of the asset, a criticality of the asset is scored, generating a first criticality score for the asset. Using the first criticality score, the asset is classified into a policy category. A selected access policy selected from a set of access policies assigned to a set of assets in the policy category is applied to the asset, the selected access policy specifying an access restriction of the asset.

Abstract: A system and method for bandwidth management are provided. In embodiments, a method includes: training, by a computing device, a predictive machine learning (ML) model based on historic network usage data of software applications in a cloud environment and historic business context data; assigning, by the computing device, priority rankings to software application activities of the cloud environment using the predictive ML model based on predicted resource requirements for the software application activities of the cloud environment and predicted contextual scenarios that impact the predicted resource requirements using an input of real-time network usage data of the cloud environment and real-time business context data; and initiating, by the computing device, scheduling of the software application activities based on the priority rankings.

Abstract: Text is received from a user describing item(s) for migration to a computing environment with cloud feature(s), resulting in item description(s), the text including unstructured text that are processed separately. Text mining is performed on the unstructured text to extract item feature(s). For each listing a portion of the unstructured text is extracted, resulting in an extracted text portion for each listing from which an entity is identified. Each entity or item feature is mapped to cloud feature(s) available from solution(s) with cloud feature(s). Based on the cloud feature(s), recommendation(s) are made to the user regarding cloud feature(s) of the solution(s) for optional consideration by the user. Explanation(s) for the recommended cloud feature(s) from explainability model(s) may be provided to the user.

Abstract: Methods, computer program products, and systems are presented. The method, computer program products, and systems can include, for instance: receiving personal inputs regarding a first individual, the first individual previously having given informed consent, automatically generating a work profile for the first individual based on the plurality of personal inputs; based on the work profile of the first individual and a preexisting work profile of a second individual, predicting a work affinity indicator for the first individual and the second individual, the predicting including using an affinity model trained via ensemble learning; and providing the work affinity indicator to a user for optional consideration in making a work-related or employment-related decision.