International Business Machines Corporation

Daniela Rosu

Shang Qing Guo

Frederick Y Wu

Arun Kwangil Iyengar

Ruchi Mahindru

Sai Zeng

Anuradha Bhamidipaty

Mithkal M Smadi

Nikolaos Anerousis

Richard Pervin King

Laura Zaihua Luan

Karen A Witting

Winnie Wing-Yee Cheng

Srikanth Govindaraj Tamilselvam

Daniel Manuel Dias

Asit Dan

James Randal Moulic

Aliza Rivka Heching

Abhijit Bose

Rajeev Puri

Anshu Narendra Jain

Dennis Anthony Perpetua, Jr

Atul Kumar

Jia Liu

Mitesh H Vasa

Anubha Verma

Suman K Pathapati

Ramesh S Palakodeti

Cashchakanithara Venugopal

Sang Kyum Kim

Murthy V Devarakonda

Yu Deng

Renu Tewari

Christopher Ward

Vijay Krishnarao Naik

Robert Filepp

Giovanni Pacifici

Andrew Neil Trossman

Shu Tao

Marcel Catalin Rosu

Nithya Rajamani

Marcel-Catalin Rosu

Atri Mandal

Winnie W Cheng

Graeme Neville Dixon

Allen M Gilbert

Lakshmish Macheeri Ramaswamy

Kavitha Ranganathan

Daniel Scanteianu

Mircea Simion Ioan Avram

Zhiyu Chen

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. The method further provides for updating/refining the data model over time using continuous learning based on evaluating whether and how implemented solutions impact the relevant performance metrics.

Evaluating effects of an artificial intelligence model on enterprise performance objectives

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.

Natural language enrichment using action explanations

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.

Virtual dialog system performance assessment and enrichment

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.

Term-cluster knowledge graph for support domains

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.

Method and system for improving training data understanding in natural language processing

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.

Building confidence of system administrator in productivity tools and incremental expansion of adoption

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.

Recommending server management actions for information processing systems

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.

Leveraging user-to-tool interactions to automatically analyze defects in IT services delivery

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.

Automated, controlled distribution and execution of commands and scripts

An approach is presented for identifying related problem tickets in an information technology (IT) environment. User interactions with a computer program are stored. The user interactions include inputs to the computer program to search for problem tickets issued in the IT environment that have the same characteristics. One or more user interaction patterns within the user interactions are recognized. A user interaction pattern of the one or more user interaction patterns is selected based on an evaluation of effectiveness of each of the one or more user interaction patterns. Based on the user interaction pattern, a rule is generated for determining which problem tickets in the IT environment share a common characteristic. The rule is applied to additional problem tickets issued in the IT environment to identify which of the additional problem tickets share the common characteristic.

Leveraging user-to-tool interactions to automatically analyze defects in it services delivery

Aspects of the present invention dynamically reduce a frequency at which IT infrastructure automatically generates alerts. Historical data across a plurality of data sources in the IT infrastructure is analyzed. An opportunity to reduce the frequency at which the IT infrastructure automatically generates the alerts is identified. A new alert policy addressing the opportunity to reduce alert frequency is generated. An impact of the new alert policy on a set of predefined service level objectives (SLOs) and service level agreements (SLAs) is evaluated. The new alert policy is deployed in the IT infrastructure.

Reduction of alerts in information technology systems

A method for problem determination and resolution in an information technology (IT) system includes receiving a problem ticket, searching a database for a plurality of problem features based on data included in the problem ticket, extracting the plurality of problem features from the database, and generating a problem signature corresponding to the problem ticket, wherein the problem signature comprises at least one non-textual feature extracted from the plurality of problem features.

Problem record signature generation, classification and search in problem determination

Growing community of inventors

Ossining, NY, United States of America

Daniela Rosu