Autonomous multi-dimension segmentation workflow
AssigneeBlue Yonder Group, Inc.
InventorsGanesh Muthusamy, Abhishek Singh
Life of this patent
Estimating the term…
Abstract
A system and method of autonomous multi-dimensional segmentation for a supply chain network. Embodiments include a supply chain network of one or more supply chain entities, a segmentation planner having a computer and memory, the segmentation planner configured to access input data relating to one or more supply chain entities, discover one or more features related to the input data, pre-process the input data and features, perform multi-dimension segmentation on the input data, compute the importance of the one or more features, generate a multi-dimension segmentation visualization, assign policy parameters to the multi-dimension segmentation performed on the input data.
Claims15
A system of autonomous multi-dimensional segmentation, comprising:
- a supply chain network comprising one or more supply chain entities;
- and
- a segmentation planner comprising a computer and memory, the segmentation planner configured to:
- access input data relating to the one or more supply chain entities;
- select an autonomous segmentation algorithm based on whether the input data is string-based or numerical-based;
- discover one or more features related to the input data, wherein the one or more features comprise geographic features, demographic features, behavioral features and psychological features;
- pre-process the input data and the one or more features;
- perform multi-dimension segmentation on the input data;
- compute a relative importance of the one or more features;
- discard any feature whose relative importance is lower than a defined threshold;
- generate a multi-dimension segmentation visualization;
- assign policy parameters comprising one or more service levels to the multi-dimension segmentation performed on the input data;
- and
- control manufacturing equipment to adjusting one or more levels of manufacturing based, at least in part, on the one or more service levels.
A computer-implemented method of autonomous multi-dimensional segmentation, comprising:
- accessing input data relating to one or more supply chain entities;
- selecting an autonomous segmentation algorithm based on whether the input data is string-based or numerical-based;
- discovering one or more features related to the input data, wherein the one or more features comprise geographic features, demographic features, behavioral features and psychological features;
- pre-processing the input data and the one or more features;
- performing multi-dimension segmentation on the input data;
- computing a relative importance of the one or more features;
- discarding any feature whose relative importance is lower than a defined threshold;
- generating a multi-dimension segmentation visualization;
- assigning policy parameters comprising one or more service levels to the multi-dimension segmentation performed on the input data;
- and
- controlling manufacturing equipment to adjusting one or more levels of manufacturing based, at least in part, on the one or more service levels.
A non-transitory computer-readable medium embodied with software providing autonomous multi-dimensional segmentation, the software when executed:
- accesses input data relating to one or more supply chain entities;
- selects an autonomous segmentation algorithm based on whether the input data is string-based or numerical-based;
- discovers one or more features related to the input data, wherein the one or more features comprise geographic features, demographic features, behavioral features and psychological features;
- pre-processes the input data and the one or more features;
- performs multi-dimension segmentation on the input data;
- computes a relative importance of the one or more features;
- discards any feature whose relative importance is lower than a defined threshold;
- generates a multi-dimension segmentation visualization;
- assigns policy parameters comprising one or more service levels to the multi-dimension segmentation performed on the input data;
- and
- controls manufacturing equipment to adjusting one or more levels of manufacturing based, at least in part, on the one or more service levels.
Dependencies are inferred from the claim text.