International business machines corporation (20240095577). MACHINE-DERIVED INSIGHTS FROM TIME SERIES DATA simplified abstract

MACHINE-DERIVED INSIGHTS FROM TIME SERIES DATA

Organization Name

international business machines corporation

Inventor(s)

Sumanta Mukherjee of Bangalore (IN)

Bhanukiran Vinzamuri of Long Island City NY (US)

Vikas C. Raykar of Bangalore (IN)

Arindam Jati of Bengaluru (IN)

Nupur Aggarwal of Bangalore (IN)

MACHINE-DERIVED INSIGHTS FROM TIME SERIES DATA - A simplified explanation of the abstract

This abstract first appeared for US patent application 20240095577 titled 'MACHINE-DERIVED INSIGHTS FROM TIME SERIES DATA

Simplified Explanation

The patent application abstract describes a method for deriving insights from time series data by generating a model template based on subject matter expert input and using a machine learning model to determine the contribution of different components to a decision.

• Rule-based translator used to generate model template from SME input
• Machine learning model based on model template, such as a multilayer neural network
• Component-wise contribution of components to decision determined
• Output includes component-wise contribution of components

Potential Applications

The technology described in the patent application could be applied in various fields such as finance, healthcare, and manufacturing for analyzing time series data to make informed decisions.

Problems Solved

This technology helps in extracting meaningful insights from complex time series data, allowing for better decision-making and problem-solving based on the contributions of different components.

Benefits

The benefits of this technology include improved accuracy in decision-making, enhanced understanding of time series data, and the ability to identify key factors influencing outcomes.

Potential Commercial Applications

The technology could be utilized in industries such as financial trading, predictive maintenance, and healthcare diagnostics for optimizing processes and improving outcomes.

Possible Prior Art

One possible prior art for this technology could be traditional statistical methods for analyzing time series data, which may not be as efficient or accurate as the machine learning approach described in the patent application.

How does the rule-based translator handle complex SME input?

The abstract does not provide details on how the rule-based translator specifically processes and translates complex subject matter expert input into a model template.

What types of decisions can the machine learning model make based on the time series data input?

The abstract does not specify the range or types of decisions that the machine learning model can generate based on the time series data input.

Original Abstract Submitted

deriving insights from time series data can include receiving subject matter expert (sme) input characterizing one or more aspects of a time series. a model template that specifies one or more components of the time series can be generated by translating the sme input using a rule-based translator. a machine learning model based on the model template can be a multilayer neural network having one or more component definition layers, each configured to extract one of the one or more components from time series data input corresponding to an instantiation of the time series. with respect to a decision generated by the machine learning model based on the time series data input, a component-wise contribution of each of the one or more components to the decision can be determined. an output can be generated, the output including the component-wise contribution of at least one of the one or more components.