Back to results
US 11,379,731 B2Granted
Relating complex data
AssigneeThe Regents of the University of California
InventorsErik Hill, Sheldon Brown, Wesley Hawkins
Life of this patent
Estimating the term…
Abstract
A data analysis and processing method includes forming an initial assembly of datasets comprising multiple entities, where each entity is a collection of variables and relationships that define how entities interact with each other, simulating an evolution of the initial assembly by performing multiple iterations in which a first iteration uses the initial assembly as a starting assembly, and querying, during the simulating, the evolution of the initial assembly, for datasets that meet an optimality criterion.
Claims20
A computer-implemented data processing method, comprising:
- forming an initial assembly of datasets and algorithmic relationships by instantiating in a colony of assemblies that have a range in variations of their dataset and algorithmic conditions;
- associating at least one contextual condition with the colony;
- comparing individual assemblies in the colony against each other and with the at least one contextual condition to find optimizations provided by the individual assemblies;
- simulating an evolution of the initial assembly by performing multiple iterations in which a first iteration uses the initial assembly as a starting assembly, including:
- causing the starting assembly to evolve by having each dataset in the starting assembly to (1) interact with other datasets in the starting assembly using corresponding algorithmic relationships;
- or (2) change values of at least some datasets using a randomization technique;
- culling, at an end of an nth iteration, assemblies in the colony that failed to meet a target objective function for the nth iteration;
- and
- replacing, selectively based on finality of the multiple iterations, the starting assembly to include remaining datasets and algorithmic relationships after the culling;
- and
- providing, based on a query during the evolution of the initial assembly, datasets that meet an optimality criterion.
8 more elements
A computer implemented data processing method, comprising:
- forming an initial assembly of datasets comprising multiple entities, where each entity is a collection of variables and relationships that define how entities interact with each other;
- simulating an evolution of the initial assembly by performing multiple iterations in which a first iteration uses the initial assembly as a starting assembly, including:
- causing the starting assembly to evolve by having the multiple entities in the starting assembly (1) interact with other entities in the starting assembly using the relationships;
- or (2) change values of variables using a randomization technique;
- culling, at an end of an iteration, a number of multiple entities that fail to meet a target objective function for that iteration;
- and
- replacing, selectively based on finality of the multiple iterations, the starting to include remaining entities after the culling;
- and
- querying, during the simulating, the evolution of the initial assembly, for datasets that meet an optimality criterion.
6 more elements
A computing system comprising one or more hardware platforms configured to implement a method, comprising:
- forming an initial assembly of datasets and algorithmic relationships by instantiating in a colony of assemblies that have a range in variations of their dataset and algorithmic conditions;
- associating at least one contextual condition with the colony;
- comparing individual assemblies in the colony against each other and with the at least one contextual condition to find optimizations provided by the individual assemblies;
- simulating an evolution of the initial assembly by performing multiple iterations in which a first iteration uses the initial assembly as a starting assembly, including:
- causing the starting assembly to evolve by having each dataset in the starting assembly to (1) interact with other datasets in the starting assembly using corresponding algorithmic relationships;
- or (2) change values of at least some datasets using a randomization technique;
- culling, at an end of an nth iteration, assemblies in the colony that failed to meet a target objective function for the nth iteration;
- and
- replacing, selectively based on finality of the multiple iterations, the starting assembly to include remaining datasets and algorithmic relationships after the culling;
- and
- providing, based on a query during the evolution of the initial assembly, datasets that meet an optimality criterion.
8 more elements
A computer program product having code stored thereon, the code, when executed by a processor, causing the processor to implement a method, comprising:
- forming an initial assembly of datasets comprising multiple entities, where each entity is a collection of variables and relationships that define how entities interact with each other;
- simulating an evolution of the initial assembly by performing multiple iterations in which a first iteration uses the initial assembly as a starting assembly, including:
- causing the starting assembly to evolve by having the multiple entities in the starting assembly (1) interact with other entities in the starting assembly using the relationships;
- or (2) change values of variables using a randomization technique;
- culling, at an end of an iteration, a number of multiple entities that fail to meet a target objective function for that iteration;
- and
- replacing, selectively based on finality of the multiple iterations, the starting to include remaining entities after the culling;
- and
- querying, during the simulating, the evolution of the initial assembly, for datasets that meet an optimality criterion.
6 more elements
Dependencies are inferred from the claim text.