Customized e-commerce tags in realtime multimedia content

A method, comprising:

• receiving, at one or more server computing devices of a service provider, data associated with a stream of multimedia content;
• determining that the stream displays a representation of an item (1) at a first timestamp during output of the stream and (2) at a first location relative to a viewable window of a user device;
• generating an interactive element, wherein the interactive element comprises an e-commerce tag interactable for purchase of the item, wherein the interactive element is generated based at least in part on data associated with items available for sale by a merchant, wherein the data associated with the items is received in near real time;
• rendering, at the first timestamp and on a display of the user device, the interactive element overlaid on a first portion of the stream and positioned relative to the representation of the item in a predetermined spatial configuration in the viewable window;
• detecting, in near real time during output of the stream, that the stream displays the representation of the item (1) at a second timestamp and (2) at a second location relative to the viewable window;
• rendering, at the second timestamp and on the display of the user device, the interactive element overlaid on a second portion of the stream and positioned relative to the representation of the item in the predetermined spatial configuration in the viewable window;
• detecting an interaction with the interactive element via the user device by a user;
• and
• based on detecting the interaction, causing presentation, on the display of the user device, of a graphical user interface configured to allow the user to purchase the item.

A system comprising:

• one or more processors;
• and
• one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions cause the one or more processors to perform acts comprising:
• receiving image data associated with a stream of multimedia content;
• determining, using computer vision techniques applied to the image data in near real time as the stream is received, that the stream displays a representation of an item (1) at a first timestamp and (2) at a first location relative to a viewable window of a user device of a user;
• receiving data associated with items available for sale by a merchant in near real time as the stream is received;
• generating an interactive element, wherein the interactive element comprises an e-commerce tag interactable for purchase of the item, and wherein the interactive element is generated based at least in part on the data associated with the items available for sale;
• causing rendering, at the first timestamp and on a display of the user device, of the interactive element overlaid on a first portion of the stream and positioned relative to the representation of the item in a predetermined spatial configuration in the viewable window;
• detecting, in near real time during output of the stream, that the stream displays the representation of the item (1) at a second timestamp and (2) at a second location relative to the viewable window;
• causing rendering, at the second timestamp and on the display of the user device, of the interactive element overlaid on a second portion of the stream and positioned relative to the representation of the item in the predetermined spatial configuration in the viewable window;
• receiving, from the user device, an indication of interaction with the interactive element;
• and
• causing presentation, on the display of the user device, of a graphical user interface configured to allow the user to purchase the item.

One or more non-transitory computer-readable media storing instructions executable by one or more processors that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:

• receiving data associated with a stream of multimedia content, the stream including a representation of an item;
• determining that the stream displays the representation of the item (1) at a first timestamp during output of the stream and (2) at a first location relative to a viewable window of a user device;
• generating an interactive element, wherein the interactive element comprises an e-commerce tag interactable for purchase of the item, and wherein the interactive element is generated based at least in part on data associated with items available for sale by a merchant;
• causing rendering, at the first timestamp and on a display of the user device, of the interactive element overlaid on a first portion of the stream in the viewable window;
• detecting, in near real time during output of the stream, that the stream displays the representation of the item (1) at a second timestamp and (2) at a second location relative to the viewable window;
• causing rendering, at the second timestamp and on the display of the user device, of the interactive element overlaid on a second portion of the stream in the viewable window;
• receiving an indication of an interaction with the interactive element;
• and
• based on receiving the indication, causing presentation of a graphical user interface configured to allow a user to purchase the item.