International Business Machines Corporation

Kyndryl, Inc.

John Robert Davis

Larisa Shwartz

Clea Anne Zolotow

Victoria Lee Guerra

Jinho Hwang

Amitkumar Manoharrao Paradkar

A method, computer system, and computer program product for optimizing a number of robots for operation of a process at a target system. The method may include providing a plurality of available robots to carry out tasks in the process at the target system. The method may monitor the target system by carrying out the process or part of the process with a varying number of robots to determine the processor utilization whilst the robots are executing a varying number of tasks. The method may balance process constraints of the execution of the process with physical system constraints of the target system by measuring a relationship between a number of tasks at a transactional level and the processor utilization. The method may output the optimized number of robots to be allocated for the process or part of the process.

Robotic management for optimizing a number of robots

A self-learning translation-engine brokering system characterizes a set of language-translation engines by associating each engine with values of a set of engine parameters. The system receives a request to translate text or speech input, along with a set of weightings that identify the relative importance of each engine parameter to the translation requester. The system formats the input into a quantifiable engine-agnostic form and performs an optimization procedure that finds the best fit between the source's weightings and the sets of engine parameters. The system directs the input to the best-fitting translation engine, receives the translated output from the selected engine, directs the output to the translation requester, and then determines how well the translated output meets user expectations. This feedback used to update the best-fitting engine's parametric values and to train the system to make more accurate selections in the future.

Self-learning input-driven brokering of language-translation engines

A technique relates to computer artifacts in a computer system. The technique includes creating a list of insights from artifacts, determining a similarity level between the insights of the artifacts and a predefined area of capability, comparing similarity level of insights for each of the artifacts to a threshold metric, removing artifacts having the similarity level below threshold metric such that artifacts remaining meet the threshold metric, and performing a pair-wise similarity comparison on the artifacts remaining which compares insights of the artifacts to each other to determine which ones are least common. The technique includes creating feature vectors for artifacts that are least common, determining a feature vector having a most variation in feature vectors, an artifact associated with the feature vector being determined to comprise a unique insight, and generating a unique message using the artifact associated with the feature vector being the unique insight.

Computer structures for computer artifacts

Embodiments are directed to computer-implemented methods of operating a monitoring host of a performance management infrastructure. The method includes receiving, using natural language processing (NLP) algorithms, training data that includes operational data and functionality data. The operational data represents natural language descriptions of performance problems identified for an application computer program running a computing system. The functionality data represents natural language descriptions of functional capabilities of the application computer program. The NLP algorithms and a classifier are used to extract features of the training data. The extracted features are used to build a semantic correlation model that includes correlated data sets, wherein each of the correlated data sets includes functionality data and operational data having a semantic correlation to functionality data. One of the correlated data sets is selected and used to create an application monitoring algorithm configured to submit requests to and receive responses from the application computer program.

Growing community of inventors

Winchester, United Kingdom

John Robert Davis