US 10,832,059 B2 · Feature identification or classification using task-specific metadata

Abstract

Innovations in the identification or classification of features in a data set are described, such as a data set representing measurements taken by a scientific instrument. For example, a task-specific processing component, such as a video encoder, is used to generate task-specific metadata. When the data set includes video frames, metadata can include information regarding motion of image elements between frames, or other differences between frames. A feature of the data set, such as an event, can be identified or classified based on the metadata. For example, an event can be identified when metadata for one or more elements of the data set exceed one or more threshold values. When the feature is identified or classified, an output, such as a display or notification, can be generated. Although the metadata may be useable to generate a task-specific output, such as compressed video data, the identifying or classifying is not used solely in production of, or the creation of an association with, the task-specific output.

Claims20

Dependent claims

A method for identifying or classifying a feature of a data set, the method comprising:

receiving the data set, the data set comprising data associated with the feature;
processing the data set with a task-specific processing component to generate task-specific metadata, the task-specific metadata indicating decisions or observations made by the task-specific processing component for production of a task-specific output, and wherein the task-specific metadata is different than the task-specific output;
with a metadata capture component, the metadata capture component being separate from the task-specific processing component, capturing at least a portion of the task-specific metadata to produce captured metadata;
and
identifying or classifying the feature based on analysis of the captured metadata, wherein the identifying or classifying is not carried out by the task-specific processing component and:
(1) the identifying or classifying is not used solely in the production of, or the creation of an association with, the task-specific output and the identifying or classifying is not the task-specific output;
and
(2) the identifying or classifying comprises one or both of (i) displaying at least a first portion of the task-specific metadata;
or (ii) submitting at least a second portion of the task-specific metadata to a machine learning algorithm to provide a classification result.

6 more elements

A computer system providing a feature identification or classification tool usable to identify or classify a feature of a data set, the computer system comprising one or more processors and one or more memories coupled to the one or more processors, the one or more memories comprising computer-executable instructions that, when executed on the one or more processors, cause the computer system to perform operations comprising:

receiving the data set, the data set comprising data associated with the feature;
processing the data set with a task-specific processing component to generate task-specific metadata, the task-specific metadata indicating decisions or observations made by the task-specific processing component for production of a task-specific output that metadata is captured by a component different than the task-specific processing component;
with a metadata capture component, the metadata capture component being separate from the task-specific processing component, capturing at least a portion of the task-specific metadata to produce captured metadata;
and
rendering for display a screen of a graphical user interface, the rendering comprising:
rendering one or more user interface elements useable to select metadata types of the captured metadata to be displayed on the screen;
and
rendering one or more metadata values for metadata types of the captured metadata selected to be displayed.

5 more elements

Dependencies are inferred from the claim text.

Feature identification or classification using task-specific metadata

Life of this patent

Feature identification or classification using task-specific metadata

Life of this patent

Abstract

Claims20