Abstract: Embodiments are provided that relate to a computer system, a computer program product, and a computer-implemented method for improving performance of a dialog system employing an automated virtual dialog agent. Embodiments involve utilizing an automated virtual agent to receive a natural language request and generate a corresponding response, automatically identifying and resolving a corresponding knowledge gap between the request and response, and refining the automated virtual agent with the resolved knowledge gap.

Abstract: Embodiments are provided that relate to a computer system, a computer program product, and a computer-implemented method for improving performance of a virtual dialog agent system employing an automated virtual dialog agent. Embodiments involve generating ground truth (GT) from a user's knowledge base, and leveraging the GT to evaluate how the virtual dialog agent performs with the GT. The evaluation measures quality of a multi-turn virtual dialog, and generates a remediation plan directed at an algorithmic improvement of the virtual dialog agent.

Abstract: Systems, computer-implemented methods, and/or computer program products facilitating a process to monitor and evaluate the effects of an artificial intelligence (AI) model on enterprise performance metrics are provided. According to an embodiment, a computer implemented method can comprise determining a technical issue of candidate technical issues associated with an artificial intelligence model that correlates to a change associated with a performance metric, wherein the determination is based on using a first data model that defines first relationships between the key performance metrics and candidate technical issues and second relationships between the candidate technical issues and candidate solutions. The method further comprises determining a solution for the technical issue using the data model and recommending or automatically implementing the solution.

Abstract: A computer implemented method for analyzing feedback with respect to a virtual assistant includes identifying a technical support problem and a corresponding resolution, wherein the technical support problem corresponds to a query, and wherein the corresponding resolution corresponds to the virtual assistant's response, collecting user feedback provided by one or more users corresponding to the technical support problem and the corresponding resolution, creating a set of user profiles corresponding to the one or more users, generating weighted user feedback according to the set of user profiles, identifying contradictory feedback patterns corresponding to the one or more users, adjusting the set of user profiles according to the identified contradictory feedback patterns, and recommending improvements to the identified corresponding resolution.

Abstract: An approach to ranking identified technical solutions summaries may be provided. The approach may include extracting data from technical tickets, subject matter expert reports, and online forum data. The approach may include receiving data relating to prior applications of one or more technical solutions. Steps associated with a technical solution may be included in the information from the prior application of the technical solutions and updated based on the information from prior applications of technical solutions. The approach may include generating a risk score and a cost score for the updated technical solution based on contextual factors associated with a user or machine. The approach may include enriching a static summary for the technical solution with the cost and risk score. The approach may include ranking the enriched summary against multiple potential technical solutions.

Abstract: Methods, systems, and computer program products for automatically classifying heterogeneous documents using machine learning techniques are provided herein. A computer-implemented method includes extracting multiple features from one or more sets of heterogeneous documents; arranging at least a portion of the extracted features into multiple hierarchically-defined classes; selecting one or more of the documents associated with each of the multiple hierarchically-defined classes; training at least one machine learning model using at least a portion of the selected documents; and automatically classifying at least one input document into one or more of the multiple hierarchically-defined classes by processing one or more portions of the at least one input document using the at least one trained machine learning model.

Abstract: Embodiments are provided that relate to a computer system, a computer program product, and a computer-implemented method for improving performance of a virtual dialog agent system employing an automated virtual dialog agent. Embodiments involve generating ground truth (GT) from a user's knowledge base, and leveraging the GT to evaluate how the virtual dialog agent performs with the GT. The evaluation measures quality of a multi-turn virtual dialog, and generates a remediation plan directed at an algorithmic improvement of the virtual dialog agent.

Abstract: Given a skeleton knowledge graph including first terms in respective nodes, wherein first terms in connected nodes have a predetermined relationship, an augmented knowledge graph is formed by a first computing device by extracting a second term from a domain corpus to form a term cluster linked with a respective node of the knowledge graph. The second term is associated with the first term of a respective node in the domain corpus while not meeting the predetermined relationship. A semantic feature between the second term and the associated first term is identified in the domain corpus and linked to the pair of the second term and the first term in the augmented knowledge graph. The augmented knowledge graph is useable by a second computing device, which may or may not be the same as the first computing device, to drive a conversation between a chatbot and user.

Abstract: Embodiments are provided that related to a computer system, a computer program product, and a computer-implemented method for improving performance of a dialog system employing an automated virtual dialog agent. Embodiments involve utilizing an automated virtual agent to receive a natural language request and generate a corresponding response, automatically identifying and resolving a corresponding knowledge gap between the request and response, and refined the automated virtual agent with the resolved knowledge gap.

Abstract: Given a skeleton knowledge graph including first terms in respective nodes, wherein first terms in connected nodes have a predetermined relationship, an augmented knowledge graph is formed by a first computing device by extracting a second term from a domain corpus to form a term cluster linked with a respective node of the knowledge graph. The second term is associated with the first term of a respective node in the domain corpus while not meeting the predetermined relationship. A semantic feature between the second term and the associated first term is identified in the domain corpus and linked to the pair of the second term and the first term in the augmented knowledge graph. The augmented knowledge graph is useable by a second computing device, which may or may not be the same as the first computing device, to drive a conversation between a chatbot and user.

Abstract: A method for natural language processing. Invalid data comprised of one of training data and query data is detected by a computer system. An invalidity level of the invalid data is determined by the computer system. In response to determining that the invalidity level meets predefined criteria, the computer system generates a revision recommendation based on the predefined criteria that are met. The revision recommendation is displayed for implementation and confirmation of the implementation.

Abstract: Systems, computer-implemented methods, and computer program products that can facilitate extraction of entities having defined lengths of text spans 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 configuration component that defines different hyperparameters of multiple artificial intelligence models, and determines target hyperparameters of an artificial intelligence model based on performance of the multiple artificial intelligence models. The computer executable components can further comprise an application component that employs the artificial intelligence model to extract one or more entities from a data source based on the target hyperparameters.

Abstract: A system management tool, with a risk assessment mode enabled, is executed within an execution infrastructure on a management computer system, to manage a target computer system in a production situation. When the execution of the tool reaches a risk segment which raises risk for the target system, a user is informed of at least one action to be executed in the risk segment. If the user agrees, the tool is allowed to execute in an automatic mode until an end of the risk segment is reached. Feedback is obtained from the user regarding safety of the risk segment; and the steps are repeated for a plurality of additional risk segments until the tool is deemed safe for all of the risk segments, after which the tool is transitioned from the risk assessment mode to an automatic mode of operation.

Abstract: One or more embodiments identify server management actions for resolving problems associated with one or more nodes in information technology infrastructure. In one embodiment, a node-ticket record for an information processing node associated with at least one problem ticket is generated. A set of node-ticket clusters is queried based on the node-ticket record. Each of the set of node-ticket clusters maps a set of server management actions to set of historical node-ticket records associated with the node-ticket cluster. The set of server management actions was previously performed to resolve at least one operational problem associated with at least one information processing node. At least one set of server management actions associated with at least one of the set of node-ticket clusters corresponding to the node-ticket record within a given threshold is identified based on the querying.

Abstract: A method for natural language processing. Invalid data comprised of one of training data and query data is detected by a computer system. An invalidity level of the invalid data is determined by the computer system. In response to determining that the invalidity level meets predefined criteria, the computer system generates a revision recommendation based on the predefined criteria that are met. The revision recommendation is displayed for implementation and confirmation of the implementation.

Abstract: A computer-implemented information verification method, system, and computer program product, include identifying an issue exists or is likely to emerge in a project plan of a project based on a predicted deviation between data extracted from a project input compared with a project trajectory, predicating a cause and a degree of severity of the issue, determining a solution option for the issue and an impact of the solution option with respect to a function and a cost, implementing the solution option to adjust the project plan to ameliorate the issue and gradually return to the project trajectory.

Abstract: One or more embodiments identify server management actions for resolving problems associated with one or more nodes in information technology infrastructure. In one embodiment, a node-ticket record for an information processing node associated with at least one problem ticket is generated. A set of node-ticket clusters is queried based on the node-ticket record. Each of the set of node-ticket clusters maps a set of server management actions to set of historical node-ticket records associated with the node-ticket cluster. The set of server management actions was previously performed to resolve at least one operational problem associated with at least one information processing node. At least one set of server management actions associated with at least one of the set of node-ticket clusters corresponding to the node-ticket record within a given threshold is identified based on the querying.

Abstract: One or more embodiments identify server management actions for resolving problems associated with one or more nodes in information technology infrastructure. In one embodiment, a node-ticket record for an information processing node associated with at least one problem ticket is generated. A set of node-ticket clusters is queried based on the node-ticket record. Each of the set of node-ticket clusters maps a set of server management actions to set of historical node-ticket records associated with the node-ticket cluster. The set of server management actions was previously performed to resolve at least one operational problem associated with at least one information processing node. At least one set of server management actions associated with at least one of the set of node-ticket clusters corresponding to the node-ticket record within a given threshold is identified based on the querying.

Abstract: An approach is presented for identifying related problem tickets in an information technology (IT) environment. A pattern of actions included in interactions with a computer program is determined to be effective at proactively preventing a problem in the IT environment based on a frequency at which user(s) performed the interactions which perform text and statistical analyses of content of historical problem tickets. A script based on the pattern of actions is generated. A root cause of the problem is determined based on the text and statistical analyses. Responsive to a receipt of a new problem ticket, the script is executed to automatically perform the pattern of actions. The new problem ticket is classified as being in a group of problem tickets which are related to the problem and included in the historical problem tickets. The new problem ticket is determined to specify the problem which has the root cause.

Abstract: Distributed execution of commands and scripts may comprise a script execution manager having access to a library of executable objects comprising at least one or more of commands or scripts or combination of commands and scripts. A script execution console may be operable to present a graphical user interface for selecting an executable object from the library to execute and for selecting one or more managed computers, on which to execute the selected executable object. The script execution console may be further operable to present a dynamically updated collation of results from execution of the selected executable object. One or more script execution agents may be operable to run on the selected respective one or more managed computers and further operable to communicate with the script execution manager.