Abstract: Systems and methods for prioritizing interview questions, including predicting answers to questions in a candidate question set using a neural network model, and generating a ranking for each of the questions in the candidate question set by determining answer confidence, completeness, and ambiguity for each of the answers, and incorporating user preferences using a personalized preference matrix. A top ranked question is automatically selected and presented to the user, and the personalized preference matrix is iteratively adjusted for subsequent ranking of questions based on an answer to the top ranked question by the user to reduce computational resources expended.

Abstract: A method for enhancing speech performance includes communicating, via an input/output (I/O) device, speech data of a patient with speech problems, segmenting the speech data, generating one or more feature vectors based on at least the segmented speech data, determining whether the one or more feature vectors match with one or more recognition objects pre-trained using clinical data of one or more other patients, determining a speech disorder based on a matched result between the one or more feature vectors and the one or more recognition objects, and communicating, via the I/O device, one or more ameliorative actions for mitigating the determined speech disorder.

Abstract: Techniques regarding using a combination of goals and context to allocate workspaces to worker entities are provided. For example, one or more embodiments described herein can comprise a system, which can comprise a memory that can store computer executable components. The system can also comprise a processor, operably coupled to the memory, and that can execute the computer executable components stored in the memory. The computer executable components can comprise a data evaluating component that can evaluate data received from a data collection device associated with a task to be performed by a worker entity, and a goal determining component that can determine a goal of the worker entity for the task, based on the evaluated data. The system can further comprise a matching component that can select a workspace resource for the task based on the goal and a context of the task.

Abstract: One embodiment of the invention provides a method for entity extraction, comprising determining a set of part-of-speech (POS) tags based on one or more documents, determining a concept in the one or more documents based on the set of POS tags, and extracting one or more phrases from the one or more documents based on the concept. The method further comprises generating a first set of rules corresponding to the concept based on the one or more phrases, generating a second set of rules specific to a domain based on the first set of rules, and learning, via an adapter grammar, a structure of one or more named entities in the one or more documents based on the second set of rules.

Abstract: Streamlining compliance reporting and remediation through clustering compliance deviations by receiving inspection scan compliance deviation report data, analyzing the inspection scan compliance deviation report data, in response to the analysis, creating normalized deviation report documents, comparing the normalized deviation report documents, in response to the comparisons, clustering the normalized deviation report documents, creating a common cluster deviation profile comprising clustered deviation reports, and generating a summary system asset compliance report comprising the common cluster deviation profile.

Abstract: A method for operating a cognitive monitor includes measuring a cognitive tone of a user, determining a categorization of the cognitive tone of the user, selecting an effector using the categorization of the cognitive tone of the user, and applying the at least one effector using a feedback mechanism of the cognitive monitor. The effector is selected to achieve a predicted future cognitive tone in the user.

Abstract: A method of inferring intent in a hybrid network includes monitoring communications in the hybrid network between a plurality of members, triggering an estimation of an intent of one or more members of the hybrid network, estimating the intent, determining a confidence level of the intent, and triggering an action based on the confidence level.

Abstract: A system, program product, and method for use with an artificial intelligence (AI) platform to dynamically amend a knowledge base responsive to query evaluating and processing. A received or detected query is subject to natural language processing to identify, annotate, and map one or more query tokens against a knowledge base. The query tokens are evaluated against the knowledge base to identify one or more query tokens absent from the knowledge base and leverage a neural network to predict a probability relationship between the query tokens absent from the knowledge base and one or more tokens populated in the knowledge base. The natural language (NL) query is translated to a structured query language (SQL) and the SQL query is executed and evaluated, and the knowledge base is selectively and dynamically amended subject to the SQL evaluation.

Abstract: Embodiments include techniques to generate alerts based at least in part on predicted mood responses to received electronic communications that include receiving, using a processor system, a communication, and analyzing, using the processor system, contents of the communication. The techniques also include based at least in part on results of the analysis, predicting, using a machine learning system, a cognitive response of a recipient of the communication, and based at least in part on the predicted cognitive response, executing an alerting operation.

Abstract: Techniques are described for providing live first aid response guidance using a machine learning based cognitive aid planner. In one embodiment, a computer-implemented method is provided that comprises classifying, by a system operatively coupled to a processor, a type of an injury endured by a patient. The method further comprises, employing, by the system, one or more machine learning models to estimate a risk level associated with the injury based on the type of the injury and a current context of the patient.

Abstract: A computer device may identify an interaction device that is capable of outputting a simulation representative of an identified aspect of an entity. The computer device may trigger the identified interaction device to output a simulation of the identified aspect.

Abstract: A method and system are provided. The method includes analyzing, by a hardware processor, one or more images to determine cognitive characteristics related to the one or more images and to a user. The method further includes forming, by the hardware processor, a composable template relating to the cognitive characteristics. The method also includes performing, by the hardware processor or another hardware processor, an amelioration action with respect to a displaying on a display device of at least one image from the one or more images, based on the composable template. The amelioration action is selected from a set of amelioration actions that include transmitting the at least one image to the disturbing image repository.

Abstract: In an electrical power outlet device, a processor and a memory are configured to execute an application within the outlet device, which computes a pattern of usage of the outlet device. A set of sensors in the outlet device includes a first sensor that is usable to detect an event in an environment in which the outlet device is supplying power. The environment includes elements that are not participating in an electrical circuit that receives power from the outlet device and the event is usable by the application to alter the pattern of usage. An autonomous modification of an operation of the outlet device is performed in response to the pattern of usage, the event, or both. The operation changes a power supplying state of the outlet device without using an external switching apparatus or an external logic implemented outside the outlet device.

Abstract: A method provides for controlling compliance remediation that includes performing compliance inspection runs by account nodes for multiple accounts. Inspection results of the inspection runs from each account node are aggregated by an account cognitive policy advisory (CPA) service. The inspection results from each account are aggregated. It is determined whether remediations are required by analyzing the inspection results combined with a current compliance mode of a server. Upon a determination that the current compliance mode of the server is a first mode, the account CPA service determines whether a policy fingerprint has changed. Upon a change to the policy fingerprint, compliance enforcement runs on the account nodes are temporarily suspended.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate compliance policy management and scheduling 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 a policy analyzer component that identifies one or more dependency relationships between a first compliance policy and one or more second compliance policies. The computer executable components can further comprise a scheduler component that generates a policy execution plan based on the one or more dependency relationships.

Abstract: A system, program product, and method for use with an information handling system to detect and resolve faults in a run-time environment. As faults are detected, one or more corresponding general query responses are identified and subject to a ranking based on relevance criteria. At least one modified response is transformed into a command, selectively blended with context, and encoded as a context aware instruction. The instruction is subject to testing with corresponding output being subject to measurement.

Abstract: Methods, systems and computer program products for providing automated script review utilizing crowdsourced inputs are provided. Aspects include receiving a new script including a script text and a script description. Aspects include comparing the new script to each of a plurality of previously classified scripts to determine a degree of similarity. Each of the previously classified scripts and the new script have an associated set of attributes. Responsive to determining that the degree of similarity is below a predetermined threshold, aspects include mapping the new script to a crowdsourcing platform to identify a similar script. Aspects also include receiving information indicative of one or more features from the crowdsourcing platform. Responsive to inputting the one or more features into an acceptance model, aspects include generating an acceptance recommendation associated with the new script.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate extraction of named entities from document data to support automation applications 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 entity extraction component that extracts, using a first machine learning process, a first data entity and a second data entity from document data indicative of a textual information. The computer executable components can further comprise a relation extraction component that determines, using a second machine learning process, a relation between the first data entity and the second data entity to generate a knowledge data graph used to execute an application associated with natural language processing for the document data.

Abstract: Generating workflows in response to new service requests. Process logs of different types of prior service requests are mined to extract workflows from the process logs of the prior service requests. The extracted workflows of the prior service requests are saved to a library of workflows. Upon receiving a new service request, one or more workflow recommendations are provided based on one or more of the extracted workflows of the library of workflows. A new workflow is generated for completing the new service request from the one or more workflow recommendations.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate computing environment migration plan recommendation based on one or more latent entity computing property preferences 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 analysis component that employs a model to discover a latent computing property preference of an entity operating in a first computing environment. The computer executable components can further comprise a recommendation component that recommends a computing environment migration plan to a second computing environment based on the latent computing property preference of the entity. In some embodiments, the recommendation component recommends discovered latent computing property preferences of the entity to construct the computing environment migration plan.