Abstract: A system can obtain a first prompt as output from inputting an alert about a computer system to a first retrieval-augmented generation system (RAG). The system can obtain a first answer as output from inputting the first prompt to a first large language model (LLM). The system can obtain a value maintained by an entity associated with the computing system as output from inputting the alert to a second RAG. The system can obtain a second answer as output from inputting the first answer, the value, and a second prompt to a second LLM, wherein the second LLM comprises the first LLM or another LLM different from the first LLM. The system can obtain a third answer as output from inputting the second answer, user information associated with the entity, and a third prompt to a third LLM. The system can make the third answer available to the entity.

Abstract: Architectures and techniques are described that can encode temporal context into a prompt and/or a soft prompt associated with a natural language artificial intelligence (AI) model such as a large language model (LLM). For example, a group of alert messages generated by a rules-based engine can be received. Based on timestamp data associated with the alert messages temporal context can be retrieved from telemetry store or another store with time series data and/or temporal context data. The temporal context can be encoded into an embedding layer of the AI model that is configured to receive input according to a text modality rather than a temporal modality.

Abstract: A method for time series anomaly detection with rare event failure prediction includes determining, by a device including a processor and using a first machine learning model, a location of a data anomaly within sequential data. The method also includes determining, by the device and using a second machine learning model that is not the first machine learning model, whether a probability of a future failure event is at least a threshold probability based on the data anomaly and the sequential data.

Abstract: A data center monitoring and management operation. Ther data center monitoring and management operation includes receiving telemetry input data from a plurality of data center assets contained within a data center, the telemetry input data; accessing data center remediation information from a repository of data center remediation information; training a hierarchical classifier using the input data from the plurality of data center assets and data center remediation information; and, predicting an occurrence of a data center issue associated with a particular data center asset using the trained hierarchical classifier.

Abstract: A method for time series anomaly detection with rare event failure prediction includes determining, by a device including a processor and using a first machine learning model, a location of a data anomaly within sequential data. The method also includes determining, by the device and using a second machine learning model that is not the first machine learning model, whether a probability of a future failure event is at least a threshold probability based on the data anomaly and the sequential data.

Abstract: The technology described herein describes training an automatic semi-supervised labeler model, such as including a time series transformer with self-attention encoder, in conjunction with classifier training to produce more precise labels describing when anomalous, rare events occurred. The automatic labeler assigns a probability distribution parameterized by distribution parameters over a sample window. A classifier outputs an approximation of distribution parameters for an imprecise label (secondary event) correlated with the anomalous event. The approximation distribution along with the secondary event distribution are input into a loss function, which couples the automatic labeler to the classifier in a feedback loop. The loss function is optimized over iterations of the loop, with the loss minimized when the automatic labeler outputs the correct label. Once trained, additional labels can be automatically generated for further training.

Abstract: A system, method, and computer-readable medium for determining a root cause for a failure event. A failure of a product or system triggers a failure event. When the failure event is triggered, querying by one or more ML/DL path root cause engines is performed on stored failure incident data sets. The queried failure incident data sets are listed and ranked. Based on the ranking, a root cause is determined as to the failure event.