IP Library › Granted Patent US 12664579
Granted Patent B2
US 12664579 · App. 18/780,146 · Granted Jun 23, 2026

Selectively displaying videos by an online system

Inventors: Shaun Navin Maharaj (Vaughan, CA); Brent Scheibelhut (Toronto, CA); Mark Oberemk (Toronto, CA); Madeline Mesard (New York, NY); Mengfei Gu (Woodland Hills, CA)
Assignee: Maplebear Inc.
G06Q30/0631G06Q30/0603
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12664579
App. No.
18/780,146
Granted
Jun 23, 2026
Kind
B2
Abstract

An online concierge system selectively replaces default static item displays with dynamic item displays to represent items. The dynamic item displays encourage a viewing user of the online concierge system to purchase the items and may be selected based on item or user preferences or characteristics. The online concierge system applies a machine learning model to determine display scores describing the expected benefit of dynamic item displays and bandwidth scores describing resource usage of dynamic item displays. The online concierge system selectively replaces default static item displays with dynamic item displays based on the display and bandwidth scores so as to maximize benefit while ensuring that performance of the online concierge system is not negatively impacted by the resource usage.

Claims (59)

1 . A method, performed by a system comprising one or more processors, comprising:

Identifying, by the one or more processors, a plurality of items for a user responsive to a search query, wherein each of the plurality of items is associated with respective display content including a default static item display;

applying, by the one or more processors, a machine learning model to a dynamic item display associated with an item of the plurality of items, the machine learning model receiving a first set of input features describing the user and a second set of input features describing the dynamic item display and generating a display score describing a lift of the dynamic item display relative to the default static item display associated with the item;

generating, by the one or more processors, a bandwidth score for the dynamic item display, the bandwidth score describing resource usage of the dynamic item display;

based on the generated display score and the bandwidth score, selectively replacing, by the one or more processors, the default static item display with the dynamic item display as the display content for the item; and

sending, by the one or more processors, the plurality of items and respective display content for display to the user on a client device, wherein the sending causes the client device to display the display content with the dynamic item display.

2 . The method of claim 1 , wherein applying the machine learning model to the dynamic item display comprises retrieving information describing one or more of: locations associated with the dynamic item display, a duration of the dynamic item display, or content creators associated with the dynamic item display.

3 . The method of claim 1 , wherein receiving the first set of input features describing the user comprises receiving one or more of: a geographic location of the user, items previously purchased by the user, items previously purchased by other users having a similar geographic location to the user, demographic information of the user, or content creators or interests associated with the user.

4 . The method of claim 1 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises:

generating another bandwidth score for another dynamic item display associated with another item of the plurality of items;

identifying that the bandwidth score for the dynamic item display and the other bandwidth score for the other dynamic item display do not exceed a threshold bandwidth; and

replacing the default static item display with the dynamic item display as the display content for the item and replacing another static item display with the other dynamic item display for the other item.

5 . The method of claim 1 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises:

identifying a set of dynamic item displays associated with one or more items of the plurality of items, the set of dynamic item displays including the dynamic item display and the plurality of items including the item;

applying the machine learning model to generate display scores for each of the set of dynamic item displays;

generating bandwidth scores for each of the set of dynamic item displays; and

based on the generated display scores and bandwidth scores, selecting at least the dynamic item display to replace the default static item display as the display content for the item.

6 . The method of claim 1 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises:

identifying a set of dynamic item displays associated with the item, the set of dynamic item displays including the dynamic item display;

applying the machine learning model to generate display scores for each of the set of dynamic item displays associated with the item;

generating bandwidth scores for each of the set of dynamic item displays associated with the item; and

based on the generated display scores and bandwidth scores, selecting the dynamic item display to replace the default static item display as the display content for the item.

7 . The method of claim 1 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises selecting the dynamic item display based on having a display score above a first threshold value and a bandwidth score below a second threshold value.

8 . The method of claim 1 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises selecting the dynamic item display based on having a higher ratio of display score to bandwidth score than one or more other dynamic item displays and a bandwidth score beneath a threshold value.

9 . The method of claim 1 , wherein the selecting selectively replacing the default static item display with the dynamic item display as the display content for the item comprises determining a display/bandwidth ratio based on the display score and bandwidth score.

10 . The method of claim 1 , wherein the machine learning model is trained on training data describing comparative performance of static item displays and dynamic item displays over a prior time period.

11 . The method of claim 1 , wherein the lift of the dynamic item display is generated based on an expected difference in user interaction when presented with the dynamic item display relative to the default static item display.

12 . A computer program product comprising a non-transitory computer-readable storage medium having instructions encoded thereon that, when executed by a processor, cause the processor to perform steps comprising:

identifying a plurality of items for a user responsive to a search query, wherein each of the plurality of items is associated with respective display content including a default static item display;

applying a machine learning model to a dynamic item display associated with an item of the plurality of items, the machine learning model receiving a first set of input features describing the user and a second set of input features describing the dynamic item display and generating a display score describing a lift of the dynamic item display relative to the default static item display associated with the item;

generating a bandwidth score for the dynamic item display, the bandwidth score describing resource usage of the dynamic item display;

based on the generated display score and the bandwidth score, selectively replacing the default static item display with the dynamic item display as the display content for the item; and

sending the plurality of items and respective display content for display to the user on a client device, wherein the sending causes the client device to display the display content with the dynamic item display.

13 . The computer program product of claim 12 , wherein applying the machine learning model to the dynamic item display comprises retrieving information describing one or more of: locations associated with the dynamic item display, a duration of the dynamic item display, or content creators associated with the dynamic item display.

14 . The computer program product of claim 12 , wherein receiving the first set of input features describing the user comprises receiving one or more of: a geographic location of the user, items previously purchased by the user, items previously purchased by other users having a similar geographic location to the user, demographic information of the user, or content creators or interests associated with the user.

15 . The computer program product of claim 12 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises:

generating another bandwidth score for another dynamic item display associated with another item of the plurality of items;

identifying that the bandwidth score for the dynamic item display and the other bandwidth score for the other dynamic item display do not exceed a threshold bandwidth; and

replacing the default static item display with the dynamic item display as the display content for the item and replacing another static item display with the other dynamic item display for the other item.

16 . The computer program product of claim 12 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises:

identifying a set of dynamic item displays associated with one or more items of the plurality of items, the set of dynamic item displays including the dynamic item display and the plurality of items including the item;

applying the machine learning model to generate display scores for each of the set of dynamic item displays;

generating bandwidth scores for each of the set of dynamic item displays; and

based on the generated display scores and bandwidth scores, selecting at least the dynamic item display to replace the default static item display as the display content for the item.

17 . The computer program product of claim 12 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises:

identifying a set of dynamic item displays associated with the item, the set of dynamic item displays including the dynamic item display;

applying the machine learning model to generate display scores for each of the set of dynamic item displays associated with the item;

generating bandwidth scores for each of the set of dynamic item displays associated with the item; and

based on the generated display scores and bandwidth scores, selecting the dynamic item display to replace the default static item display as the display content for the item.

18 . The computer program product of claim 12 , wherein the selectively replacing the default static item display with the dynamic item display as the display content for the item comprises selecting the dynamic item display based on having a display score above a first threshold value and a bandwidth score below a second threshold value.

19 . The computer program product of claim 12 , wherein the machine learning model is trained on training data describing comparative performance of static item displays and dynamic item displays over a prior time period.

20 . A computer system comprising:

one or more processors; and

a non-transitory computer-readable storage medium storing instructions executable by the one or more processors for performing steps including:

identifying a plurality of items for a user responsive to a search query, wherein each of the plurality of items is associated with respective display content including a default static item display;

applying a machine learning model to a dynamic item display associated with an item of the plurality of items, the machine learning model receiving a first set of input features describing the user and a second set of input features describing the dynamic item display and generating a display score describing a lift of the dynamic item display relative to the default static item display associated with the item;

generating a bandwidth score for the dynamic item display, the bandwidth score describing resource usage of the dynamic item display;

based on the generated display score and the bandwidth score, selectively replacing the default static item display with the dynamic item display as the display content for the item; and

sending the plurality of items and respective display content for display to the user on a client device, wherein the sending causes the client device to display the display content with the dynamic item display.