International Business Machines Corporation

Hubert Kompanowski

Piotr Kalandyk

Grzegorz Piotr Szczepanik

Pawel Tadeusz Januszek

Lukasz Jakub Palus

Piotr P Godowski

Agnieszka Tkaczyk-Walczak

Metadata can be generated for documentation accessed from at least one knowledge source. Intents for main topics of the documentation can be generated using content structure information for the documentation. Dialogs for the intents can be generated. Sub-dialogs can be created for each of the dialogs based, at least in part, on the metadata for the documentation. The dialogs can be configured to be used to modify existing dialogs of a problem-solution data set.

Creating dialogs for a problem-solution data set

A method, system and computer program product for light-weight software license compliance management. One embodiment of the method comprises accessing a set of software logs from a target device, analyzing the set of software logs to generate a license violation probability score, determining the license violation probability score satisfies a predetermined threshold, and notifying a user of a need to scan the target device for software license compliance.

License scan triggering system

At least one knowledge source for use in updating a first problem-solution data set can be selected. From data provided by the at least one knowledge source, a plurality of dialogs can be automatically generated. Existing dialogs in the first problem-solution data can be updated set using the plurality of dialogs that are generated.

Leveraging knowledge records for chatbot local search

A computer-implemented method, computer system, and computer program product for measuring a quality of a chatbot response. The present invention may include receiving one or more classifications, receiving a set of questions in a chatbot to be analyzed, filtering any question from the received set of questions that is not related to an area of expertise of the chatbot, matching at least two questions from the received set of questions to each other, and applying at least one of the one or more classifications to the at least two matched questions. The one or more classifications may be based on a similarity of words and synonyms used in the at least two matched questions. The one or more classifications may be based on a similarity of intents of the at least two matched questions.

Measuring quality of a chatbot response

A set of virtual machines is deployed on a hypervisor. At each virtual machine, one or more local scans is performed to generate a set of computing resource consumption data. In response to receiving a set of hypervisor resource consumption data, a stability factor is generated. Based on the set of resource consumption data, the set of hypervisor resource consumption data, and the stability factor, a determination is made that a default consumption metric exceeds a threshold. In response to the determination, a custom consumption metric is generated, based on at least the set of computing resource consumption data. A user is notified of the custom consumption metric.

Automatic evaluation of virtual machine computing power

In an approach to improve chatbot workspaces by updating chatbot workspaces through documentation updating and chatbot skill updating. Embodiments determine a chatbot knowledge base contains a set of updated information and updates a chatbot dialog decision tree based on one or more identified new topics in a set of updated information using natural language processing techniques to determine a set of intents, a set of entities, and a set of keywords. Further, embodiments identify a starting decision for traversing the chatbot dialogue decision tree based on the updated set of entities and the updated set of keywords. Additionally, embodiments interact, via a user interface, with an end user according to one or more interactions traversing the chatbot dialogue decision tree for a response.

Updating chatbot workspaces

A method, system, and computer program product for implementing automated software application bundling is provided. The method includes detecting first software scanners installed within computing devices associated with a hardware device. Licensed software applications and second software scanners installed within a group of computing devices are detected and configuration files associated with initiating execution of the licensed software applications are retrieved from a database. Operational data is retrieved and an associated list describing operational attributes of the computing devices is generated. Likewise, a list of licensed software applications installed within the group of computing devices and a graph presenting communication connections between the computing devices and the hardware device are generated and the licensed software applications are executed with respect to enabling operational functionality for the group of computing devices.

Growing community of inventors

Cracow, Poland

Hubert Kompanowski