US 2018/0018585 A1 · DATA EVALUATION AS A SERVICE

Abstract

An evaluation platform receives a data set and a description of an outcome, such as predicting results of trends, recognizing patterns, and evaluating options according to specified criteria. The description is evaluated to select candidate evaluators that may be capable of achieving the outcome, and to translate the outcome into a goal for each selected candidate evaluator. The evaluator candidate set is trained using a training data set, and an initial evaluator is selected that exhibits the highest performance to achieve the outcome over the data set. The initial evaluator is applied to achieve the requested outcome over the data set. Optionally, the performance of the initial evaluator may be monitored to detect performance drift. In this event, the evaluator candidate set is reevaluated to identify a substitute evaluator exhibiting higher performance than the initial evaluator, which replaces the initial evaluator in the continued evaluation of the data set.

Claims20

Dependent claims

A device that achieves an outcome over a data set, the device comprising:

a processor, and
a memory storing:
an evaluator set comprising at least two evaluators;
and
instructions that, when executed by the processor, cause the device to:
from the evaluator set, choose an evaluator candidate set of evaluators that are capable of achieving the outcome over the data set;
translate the outcome into a goal for respective evaluators of the evaluator candidate set;
train the evaluators of the evaluator candidate set using a training data set;
measure a performance score for the respective evaluators during the training;
from the evaluator candidate set, identify an initial evaluator that exhibits a highest performance score;
and
apply the initial evaluator to the data set.

9 more elements

A method of achieving an outcome over a data set using a device comprising a processor and an evaluator set, the method comprising:

executing, by the processor, instructions that cause the device to:
from the evaluator set, choose an evaluator candidate set of evaluators that are capable of achieving the outcome over the data set;
translate the outcome into a goal for respective evaluators of the evaluator candidate set;
train the evaluators of the evaluator candidate set using a training data set;
measure a performance score for the respective evaluators during the training;
from the evaluator candidate set, identify an initial evaluator that exhibits a highest performance score;
apply the initial evaluator to the data set to achieve the outcome.

4 more elements

Dependencies are inferred from the claim text.

Data evaluation as a service

Life of this patent

Data evaluation as a service

Life of this patent

Abstract

Claims20