Abstract: Embodiments relate to providing self-learning automated information technology change risk prediction. A processor inputs a change request to a first machine learning model, the first machine learning model determining at least one word pair in the change request, the change request being a modification in an IT environment. The processor classifies the at least one word pair into a change category for the IT environment using a second machine learning model, the change category identifying a type of the modification to be executed in the IT environment. The processor determines a likelihood of causing a problem in the IT environment as a result of executing the modification. The processor automatically performs an action to prevent the modification of the change request in the IT environment.

Abstract: Embodiments relate to dynamic creating a temporary isolated environment in an interactive communication environment for potential bots. In response to identifying that an avatar accessing the interactive communication environment is being controlled by a non-human entity, the avatar is dynamically placed in an isolated virtual environment. Permission of the avatar are disabled in the isolated virtual environment. An authentication inquiry is presented to the avatar identified as being controlled by the non-human entity. A location is transferred for the avatar identified as being controlled by the non-human entity, based on a user response to the authentication inquiry.

Abstract: A method, computer program product, and system include a processor(s) that continuously obtains data from the one or more sensor devices, generating, from the data, frames comprising images, identifies, utilizing the frames, entities within a pre-defined vicinity of a visual display unit at a first time, determines, based on applying the classification model, if each identified entity of the identified entities within the pre-defined vicinity at the first time is objectionable. When the processor(s) determined that at least one identified entity is objectionable, the processor(s) initiates a security action on the visual display unit to prevents the objectionable identified entity from viewing the content on the visual display unit.

Abstract: 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.

Abstract: A computer-implemented method, in accordance with one embodiment, includes collecting data relating to development of a software product, the collected data including a plurality of different types of data relating to the development of the software product. A portion of the collected data is selected based on a characteristic of an intended user, the portion of the collected data including a plurality of the types of data. The selected portion of the collected data is transformed into data visualizations representing the data, the different types of the data having different data visualizations relative to one another. The data visualizations are output in a single visual representation for display to the intended user.

Abstract: A universal serial bus device, including: a main body; a connection portion attached to the main body; a processor; a storage portion storing a hash function executable by the processor, the hash function producing a hash value; a non-changing visual code on the main body, the visual code being readable by an optical scanner and corresponding to the hash function; and an electronic display configured to display the hash value.

Abstract: A central electrical cabinet unit is designed and assembled as a pre-assembled unit for installation at a client site for designing/building a custom electronic data center cabinet design or layout. The pre-assembled unit includes a central patch panel in a central cabinet for electronic devices. The central patch panel includes specified connections for components using the specified connections. Central patch panel connecting cables with central patch panel connectors include reciprocal connectors are connectible to client specified connections in a client cabinet. Power cables and electrical cables have electrical connections to the central patch panel. The electrical cables are configured to have reciprocal connectors connectable to compatible client electrical connectors on client electrical cables in the client cabinet, thereby the central patch panels in the central cabinet are a pre-assembled unit for installation at a client site and for connecting client cabinets thereto.

Abstract: A method includes training a recurrent neural network by monitoring data in a memory of a first server as the first server executes jobs and by determining an amount of computing resources used by the first server while executing the jobs and applying the recurrent neural network to data in the memory to predict an amount of computing resources that the first server will use when executing a first future job. The method also includes, in response to determining that execution of the first future job did not meet a performance criterion, making a change to the first server. The method further includes further training the recurrent neural network using a reinforcement learning technique, applying the recurrent neural network to determine that the change should be made to a second server, and in response, making the change to the second server before the second server executes a second future job.

Abstract: Aspects of the present disclosure relate generally to three-dimensional (3D) printing and, more particularly, to robotic support for 3D prints. For example, a computer-implemented method includes identifying, by the computing device, at least one structure in the 3D object source file requiring support for printing the at least one structure by a 3D printer; adding, by the computing device, to a 3D print file an instruction to request deployment of a support structure at a particular location to support the at least one structure by the 3D printer; and providing to the 3D printer, by the computing device, the 3D print file with the instruction to request deployment of the support structure at a particular location to support the at least one structure by the 3D printer.

Abstract: A random password policy for a specific user associated with an entity is generated based on a global password requirement. A new password created by the specific user based on the generated random password policy is identified. That the new password complies with a set of requirements specified by the generated random password policy is confirmed.

Abstract: Interest of a user in a website is determined. One or more concepts associated with the website are determined. A version of the website is archived.

Abstract: Asset error remediation is provided. Risk and classification of an asset error are analyzed to prioritize asset error remediation for an asset based on risk criticality, risk context, and vulnerability level corresponding to the asset by detecting suspicious behavior and risk exposure to the asset in a heterogeneous distributed computing environment using artificial intelligence. A priority of the asset error remediation is determined to fix the asset within the heterogeneous distributed computing environment based on the risk and the classification of the asset error. A set of action steps is performed to fix the asset within the heterogeneous distributed computing environment based on the priority of the asset error remediation.

Abstract: Embodiments of the present invention provide a computer system, a computer program product, and a method that comprises receiving and storing input data from at least two users; calculating a risk score for each identified risk in the received data based on priority risk factors affecting respectively identified risks; dynamically optimizing a risk analysis of the received input for multiple users within a user interface of a computing device by recalculating risk scores based on the received data and identified risks; and generating a notification for the user interface of the computing device based on the dynamic optimization of the risk analysis of the received input.

Abstract: Methods, computer program products, and systems are presented. The methods include, for instance: obtaining communication data streams, extracting data relevant to a point of view of a user, and generating a point of view record in a knowledge base that may be utilized by another user communicating with the user.

Abstract: A voice signal in a headphone is detected. The voice signal includes a person speaking an audible command. Based on detecting the voice signal a first biometric signature of a user is retrieved. The first biometric signature is compared to one or more biometric features of the person. Based on comparing the first biometric signature to the one or more biometric features an authentication of the user is determined. An authentication action is performed based on the detected voice signal. The authentication action is performed in response to verifying the authentication.

Abstract: An approach is provided for augmenting text of a small class for text classification. An imbalanced dataset is received. A small class is identified. The small class includes initial text records in the imbalanced dataset. A balanced dataset is generated from the imbalanced dataset by augmenting the initial text records by using weighted word scores indicating respective measures of importance of words in classes in the imbalanced dataset. The balanced dataset is sent to a supervised machine learning model. The supervised machine learning model is trained on the balanced dataset. Using the supervised machine learning model which employs the augmented initial text records, a text classification of a new dataset is performed. The domain of the new dataset matches the domain of the imbalanced dataset.

Abstract: A server receives encrypted data from a protected-resource-requesting device that includes an encrypted combination of the device and user identification. The first server requests a most recent copy of data of a distributed ledger from a randomly selected logged-in workstation. The first server searches for a match of the encrypted data from the first device in the distributed ledger data received from the randomly selected workstation. In response to determining a match, the first server updates a table of a second server with a one-time-password (OTP) and a copy of the encrypted data received from the device. The first server sends the OTP and an instruction to the device to send the OTP and the encrypted data to the second server, which determines whether a match exists. In response to a confirmed match, the first server grants access to the device.

Abstract: Debris signature-based robotic cleaning device navigation includes operating the robotic cleaning device in a first mode as part of a vacuum cycle, the device including suction ports configurable for different suction power levels and each port having a suction path along which debris entering through the suction port is collected by the device. In the first operating mode the suction ports are operated at a first suction power level. The navigation also includes changing operation of the device to a second mode and in which the suction ports are operated at a greater suction power, measuring a respective amount of debris collected through each suction port, and selecting a direction in which to navigate the robotic cleaning device based on the debris measurements.

Abstract: A computer-implemented method according to one embodiment includes accessing a copy of a ledger that includes information associated with a plurality of potential recovery sites of a multi-site environment. The information of the copy of the ledger is stored on a blockchain by the potential recovery sites. A current threat to a production site of the multi-site environment is identified. The method further includes, analyzing, based on the current threat, the copy of the ledger to determine one of the potential recovery sites to use as a failover for the production site, and in response to a determination that the current threat has caused a disaster event on the production site, causing the production site to failover to the determined recovery site.

Abstract: A method, computer system, and a computer program product for a dynamic machine functionality is provided. The present invention may include setting a threshold for a machine. The present invention may include setting one or more features of the machine available to a user based on the set threshold. The present invention may include determining the machine is being operated. The present invention may include collecting a plurality of data based on the machine operation. The present invention may include transmitting the plurality of data to a machine learning (ML) module. The present invention may include analyzing the collected plurality of data using the ML module. The present invention may include determining that at least one machine functionality of the one or more features should be adjusted based on analysis of the collected plurality of data. The present invention may include adjusting the at least one machine functionality.