Automated control of display devices
AssigneeGumGum, Inc.
InventorsJeffrey Benjamin Katz, Cambron Neil Carter, Brian Jongmin Kim
Life of this patent
Estimating the term…
Abstract
Systems and methods are provided for determining a media cost equivalent to attribute to the appearance of a sponsor's logo or other object in a media item, such as an image or video. This determination may be based on factors such as clarity, prominence, visibility, size, or placement of a sponsor logo or other object related to the sponsor within at least one media item. One or more machine learning models may be utilized to automatically identify objects within, and otherwise analyze, image data in order to determine sponsor value.
Claims21
(canceled)
A computing system comprising:
- a memory;
- and
- a processor in communication with the memory and configured with processor-executable instructions to perform operations comprising:
- retrieving a plurality of media items, wherein the plurality of media items include images or videos depicting a sporting event;
- identifying, from the plurality of media items, at least a first media item that depicts a first object associated with a first sponsor, wherein the first media item is identified to depict the first object at least in part by a classifier trained to identify the first object associated with the first sponsor based on input image or video data, wherein the first object comprises at least one of a logo or advertisement associated with the first sponsor;
- determining, based on automated analysis of image or video data of the first media item, factors to be applied when determining a value to the first sponsor of appearance of the first object in at least the first media item, wherein the factors include two or more of:
- size, clarity, duration or position of the first object in the first media item;
- determining the value to the first sponsor of the appearance of the first object in at least the first media item, wherein the value is determined based at least in part on at least two of:
- the size, the clarity, the duration or the position of the first object in the first media item;
- and
- generating user interface data, for display to a user associated with the first sponsor, that identifies the value and one or more factors contributing to the value, wherein the factors are identified in the user interface data by indication of one or more of the size, the clarity, the duration or the position of the first object in the first media item.
A computer-implemented method comprising:
- retrieving a first media item, wherein the first media item comprises image or video data;
- determining that the first media item includes depiction of, in addition to other content, a first object associated with a first company, wherein the first media item is determined to depict the first object at least in part by a classifier trained to identify the first object associated with the first company from input image or video data;
- determining, based on automated analysis of image or video data of the first media item, factors to be applied when determining a marketing value to the first company of appearance of the first object in at least the first media item, wherein the factors include two or more of:
- size, clarity, duration or position of the first object in the first media item;
- determining the marketing value to the first company of the appearance of the first object in at least the first media item, wherein the marketing value is determined based at least in part on at least two of:
- the size, the clarity, the duration or the position of the first object in the first media item;
- and
- generating user interface data that identifies the marketing value and one or more factors contributing to the marketing value.
A non-transitory computer readable medium storing computer executable instructions that, when executed by one or more computer systems, configure the one or more computer systems to perform operations comprising:
- retrieving a first media item, wherein the first media item comprises image or video data;
- determining that the first media item includes depiction of a first object associated with a first sponsor, wherein the first media item is determined to depict the first object at least in part by a machine learning model trained to identify the first object associated with the first sponsor in image or video data that is provided as input to the machine learning model;
- determining, based on automated analysis of image or video data of the first media item, factors to be applied when determining a value to the first sponsor of appearance of the first object in at least the first media item, wherein the factors include one or more of:
- size, clarity, duration or position of the first object in the first media item;
- and
- calculating the value to the first sponsor of the appearance of the first object in at least the first media item, wherein the value is calculated based at least in part on at least one of:
- the size, the clarity, the duration or the position of the first object in the first media item.
Dependencies are inferred from the claim text.