Electronic asset management

Patent metadata

Field	Value
Publication number	US-12094019-B1
Application number	US-202016944812-A
Country	US
Kind code	B1
Filing date	Jul 31, 2020
Priority date	Aug 1, 2019
Publication date	Sep 17, 2024
Grant date	Sep 17, 2024

Abstract

Various implementations manage an electronic asset by creating a representation of an electronic asset and its variants. This may be accomplished by identifying variants of an electronic asset, identifying a portion of a feature space associated with the asset and variants, and providing a representation corresponding to that portion of feature space. A fixed function classifier may be used to determine the points in the feature space for the electronic asset and its variants. The set of points produced for an asset and its variants using such a fixed function classifier will be near one another in feature space. Moreover, the area around such points will also represent points for other similar variations of the asset and thus, the portion of the feature space around the points can be considered the area of ownership for the electronic asset, e.g., it defines a boundary of what the creator is asserting is his or her creation.

First claim

What is claimed is:

1. A non-transitory computer-readable storage medium, storing program instructions executable on a device to perform operations comprising: identifying, via a variant unit, variants of an electronic asset, wherein the variants are determined by applying modifications to portions of the electronic asset such that the variants are similar to the electronic asset but differ from the electronic asset based on the modifications; identifying, via an asset-to-feature space unit, points in a feature space for the electronic asset and the variants of the electronic asset, wherein the points are identified by applying a machine learning model such that distances of the points from one another in the feature space corresponds to magnitudes of variation amongst the asset and the variants; and providing, via an assigning unit, a representation of a portion of the feature space defined by a boundary around both the points in the feature space identified for the electronic asset and the points in the feature space identified for the variants of the electronic asset, the boundary defining what is asserted to be owned by a content creator or content owner, wherein the representation comprises a token representing an assertion of ownership by the content creator or content owner in all electronic assets corresponding to points within the boundary.

2. The non-transitory computer-readable storage medium of claim 1 , wherein the feature space is an n dimensional mathematical space capable of uniquely representing electronic assets as a combination of coordinates.

3. The non-transitory computer-readable storage medium of claim 1 , wherein identifying the points comprises applying a fixed function classifier.

4. The non-transitory computer-readable storage medium of claim 3 , wherein the fixed function classifier is configured such that small variations in assets correspond to relatively close points in the feature space while large variations in assets correspond to relatively distant points in the feature space.

5. The non-transitory computer-readable storage medium of claim 3 , wherein the fixed function classifier was trained via machine learning using a loss function that minimizes distance of points in the feature space produced for similar inputs and maximizes distance of points in the feature space produced for dissimilar inputs.

6. The non-transitory computer-readable storage medium of claim 1 , wherein the operations further comprise identifying an asset-to-feature space point model to use to identify the points based on a category, type, or complexity of the electronic asset.

7. The non-transitory computer-readable storage medium of claim 1 , wherein identifying the variants of the electronic asset comprises automatically performing a transform on the electronic asset to produce a variant.

8. The non-transitory computer-readable storage medium of claim 7 , wherein the transform comprises a twist, a rotation, a stretch, a scale, a skew, a resize, a recoloring, a texture change, a material change, a sub-components scaling, a substitution, a removal, a mesh tessellation, a mesh subdivision, a noise addition, a noise removal, an audio pitch change, cutting off a part, or adding a part.

9. The non-transitory computer-readable storage medium of claim 7 , wherein the transform is determined based on a category, type, or complexity of the electronic asset.

10. The non-transitory computer-readable storage medium of claim 7 , wherein the transform is determined based on user input specifying: a type of transform; a transform parameter; a portion of the electronic asset to transform; a portion of the asset to fix without transformation; or an amount of transformation.

11. The non-transitory computer-readable storage medium of claim 1 , wherein the token comprises an identifier of a database record that stores a feature manifold corresponding to the portion of the feature space, wherein the database record identifies a person or entity claiming ownership of the electronic asset and all variations corresponding to points in the feature space within the portion.

12. A non-transitory computer-readable storage medium, storing program instructions executable on a device to perform operations comprising: identifying a point in a feature space for an electronic asset; comparing the point to a boundary defining a portion of the feature space already claimed for a second electronic asset, wherein the portion of feature space is represented by a representation generated by: identifying, via an asset-to-feature space unit, points in the feature space for the second electronic asset and variants of the electronic asset, wherein the points are identified by applying a machine learning model such that distances of the points from one another in the feature space corresponds to magnitudes of variation amongst the second electronic asset and the variants; and providing, via an assigning unit, a representation of the portion of the feature space defined by the boundary around both the points in the feature space identified for the second electronic asset and the points in the feature space identified for the variants of the second electronic asset, wherein the representation corresponds to an assertion of ownership in the second electronic asset and all variations corresponding to points within the portion of the feature space, the boundary defining what is asserted to be owned by a content creator or content owner, wherein the representation comprises a token representing an assertion of ownership by the content creator or content owner in all electronic assets corresponding to points within the boundary; and providing output based on the comparing, the output identifying whether the electronic asset is owned by the content creator or content owner.

13. The non-transitory computer-readable storage medium of claim 12 , wherein the representation comprises a digital signature representing authorization from an authority that manages the feature space or database.

14. The non-transitory computer-readable storage medium of claim 12 , wherein the operations further comprise initiating a sale of the electronic asset or license to use the electronic asset based on determining that the electronic asset is owned by the person or entity claiming ownership in the second electronic asset and all variations corresponding to points within the portion of the feature space.

15. The non-transitory computer-readable storage medium of claim 12 , wherein the comparing is initiated by a third party separate from the person or entity claiming ownership in the second electronic asset and all variations corresponding to points within the portion of the feature space.

16. The non-transitory computer-readable storage medium of claim 15 , wherein the output is provided to the third party and identifies that the electronic asset is owned by the person or entity claiming ownership in the second electronic asset and all variations corresponding to points within the portion of the feature space.

17. The non-transitory computer-readable storage medium of claim 15 , wherein the output is provided to the third party and identifies that the electronic asset is not owned by another person or entity.

18. The non-transitory computer-readable storage medium of claim 17 , wherein the operations further comprise generating a representation of ownership in the electronic asset and variants thereof, wherein the representation identifies that the electronic asset and all variations within a second portion of the feature space are owned by the third

Assignees

• Apple Inc

Inventors

• Greasley Jack R
• Ulbricht Daniel
• Verma Eshan

Classifications

• G06Q50/184 Primary

  Intellectual property management · CPC title

• G06F16/23 Primary

  Updating · CPC title