US-12626291-B2 - Personalized storefront for an online concierge system using search-powered carousels

Abstract

An online concierge system generates a personalized storefront user interface to recommend items for purchase and delivery to a customer. The online concierge system obtains a user identifier for the customer and generates a set of recommended search terms that it predicts will be relevant to the customer. The recommended search terms may be identified at least in part by mapping items previously purchased by the customer to search queries that resulted in purchases of that item across a population of customers of the online concierge system. The online concierge system then executes respective search queries for the each of the set of search terms to generate respective search result sets for each of the recommended search terms. The search result sets may be presented as respective search queries on a user interface screen of a customer client device.

Inventors

• Esther Vasiete Allas

Assignees

• MAPLEBEAR INC.

Dates

Publication Date

20260512

Application Date

20230123

Claims (20)

1. 1 . A method comprising, at a computer system comprising a processor and a computer-readable medium: receiving, over a network at a content presentation module of an online concierge system, a request for a home screen user interface from a client device associated with a customer of the online concierge system; responsive to receiving the request, obtaining, by the content presentation module, a user identifier for the customer of the online concierge system; based on the user identifier, obtaining, by the content presentation module, a set of recommended search terms for the customer that the online concierge system predicts will yield search results having relevance to the customer, wherein the set of search terms are obtained from a database storing recommended search terms in association with user identifiers; executing, by the content presentation module, respective search queries in a search application of the online concierge system to generate respective search result sets for each of the respective search queries, each of the respective search result sets comprising respective ranked lists of items relevant to the respective search queries; generating, by the content presentation module, a home screen user interface for the client device, the home screen user interface including selectable user interface elements for selecting one or more items in the ranked lists of items, wherein each selectable user interface element comprises a scrollable carousel of horizontally-arranged items within a corresponding ranked list of items, and wherein the selectable user interface element further comprises a scroll control element that causes the scrollable carousel to display additional items; transmitting, by the content presentation module over the network, instructions to the client device to display the home screen user interface, wherein the instructions cause the client device to display a graphical user interface comprising the home screen user interface; receiving, by the content presentation module over the network, a notification from the client device that the customer has interacted with the scroll control element of a scrollable carousel of a selectable user interface element of the home screen user interface; identifying, by the content presentation module, a set of additional items relevant to a search query corresponding to the selectable user interface element associated with the scroll control element with which the user interacted; transmitting, by the content presentation module over the network, instructions to the client device to update the home screen user interface to display the set of additional items; receiving, by the content presentation module from the client device via the home screen user interface, a selection of an item of the set of additional items for adding to an order; and facilitating, by the online concierge system, procurement of the order and delivery of the order to the customer.
2. 2 . The method of claim 1 , wherein obtaining the set of recommended search terms comprises: identifying, based on the user identifier, an item previously purchased by the customer via the online concierge system; identifying, for the item, a plurality of converted search queries submitted from a population of customers of the online concierge system that resulted in purchases of the item; identifying, from the plurality of converted search query, a top performing converted search query for the item; and including the top performing converted search query in the set of recommended search terms.
3. 3 . The method of claim 1 , wherein obtaining the set of recommended search terms comprises: obtaining, based on the user identifier, a historical set of search queries entered by the customer; and obtaining the set of recommended search terms based at least in part on the historical set of search queries.
4. 4 . The method of claim 1 , wherein obtaining the set of recommended search terms comprises: obtaining a user embedding for the customer based a profile of the customer in the online concierge system; identifying search terms having search embeddings meeting similarity criteria with the user embedding; and obtaining the set of recommended search terms based at least in part on identified search terms.
5. 5 . The method of claim 1 , wherein obtaining the set of recommended search terms comprises: obtaining a set complementary search terms meeting a similarity metric with one or more historical search terms entered by the customer in the online concierge system; and obtaining the set of recommended search terms based at least in part on the set of complementary search terms.
6. 6 . The method of claim 1 , wherein obtaining the set of recommended search terms comprises: obtaining an initial set of candidate search terms; performing a quality assessment of the initial set of candidate search terms; and selecting the set of recommended search terms from the initial set of candidate search terms that pass the quality assessment.
7. 7 . The method of claim 6 , wherein performing the quality assessment comprises at least one of: assessing historical conversion rates on the initial set of candidate search terms; assessing reorder probabilities of items returned in a search query using the initial set of candidate search terms; assessing a sensitivity level of a category of items relating to the initial set of candidate search terms; and assessing a time since a last order from a customer of items in the initial set of candidate search terms.
8. 8 . The method of claim 1 , wherein the ranked lists of items are selected and ordered by applying a search ranking algorithm based on at least customer profile data about the customer and based on promotion data about the items.
9. 9 . A non-transitory computer-readable storage medium storing instructions executable by a processor for performing steps comprising: receiving, over a network at a content presentation module of an online concierge system, a request for a home screen user interface from a client device associated with a customer of the online concierge system; responsive to receiving the request, obtaining, by the content presentation module, a user identifier for the customer of the online concierge system; based on the user identifier, obtaining, by the content presentation module, a set of recommended search terms for the customer that the online concierge system predicts will yield search results having relevance to the customer, wherein the set of search terms are obtained from a database storing recommended search terms in association with user identifiers; executing, by the content presentation module, respective search queries in a search application of the online concierge system to generate respective search result sets for each of the respective search queries, each of the respective search result sets comprising respective ranked lists of items relevant to the respective search queries; generating, by the content presentation module, a home screen user interface for the client device, the home screen user interface including selectable user interface elements for selecting one or more items in the ranked lists of items, wherein each selectable user interface element comprises a scrollable carousel of horizontally-arranged items within a corresponding ranked list of items, and wherein the selectable user interface element further comprises a scroll control element that causes the scrollable carousel to display additional items; transmitting, by the content presentation module over the network, instructions to the client device to display the home screen user interface, wherein the instructions cause the client device to display a graphical user interface comprising the home screen user interface; receiving, by the content presentation module over the network, a notification from the client device that the customer has interacted with the scroll control element of a scrollable carousel of a selectable user interface element of the home screen user interface; identifying, by the content presentation module, a set of additional items relevant to a search query corresponding to the selectable user interface element associated with the scroll control element with which the user interacted; transmitting, by the content presentation module over the network, instructions to the client device to update the home screen user interface to display the set of additional items; receiving, by the content presentation module from the client device via the home screen user interface, a selection of an item of the set of additional items for adding to an order; and facilitating, by the online concierge system, procurement of the order and delivery of the order to the customer.
10. 10 . The non-transitory computer-readable storage medium of claim 9 , wherein obtaining the set of recommended search terms comprises: identifying, based on the user identifier, an item previously purchased by the customer via the online concierge system; identifying, for the item, a plurality of converted search queries submitted from a population of customers of the online concierge system that resulted in purchases of the item; identifying, from the plurality of converted search query, a top performing converted search query for the item; and including the top performing converted search query in the set of recommended search terms.
11. 11 . The non-transitory computer-readable storage medium of claim 9 , wherein obtaining the set of recommended search terms comprises: obtaining, based on the user identifier, a historical set of search queries entered by the customer; and obtaining the set of recommended search terms based at least in part on the historical set of search queries.
12. 12 . The non-transitory computer-readable storage medium of claim 9 , wherein obtaining the set of recommended search terms comprises: obtaining a user embedding for the customer based a profile of the customer in the online concierge system; identifying search terms having search embeddings meeting similarity criteria with the user embedding; and obtaining the set of recommended search terms based at least in part on identified search terms.
13. 13 . The non-transitory computer-readable storage medium of claim 9 , wherein obtaining the set of recommended search terms comprises: obtaining a set complementary search terms meeting a similarity metric with one or more historical search terms entered by the customer in the online concierge system; and obtaining the set of recommended search terms based at least in part on the set of complementary search terms.
14. 14 . The non-transitory computer-readable storage medium of claim 9 , wherein obtaining the set of recommended search terms comprises: obtaining an initial set of candidate search terms; performing a quality assessment of the initial set of candidate search terms; and selecting the set of recommended search terms from the initial set of candidate search terms that pass the quality assessment.
15. 15 . The non-transitory computer-readable storage medium of claim 14 , wherein performing the quality assessment comprises at least one of: assessing historical conversion rates on the initial set of candidate search terms; assessing reorder probabilities of items returned in a search query using the initial set of candidate search terms; assessing a sensitivity level of a category of items relating to the initial set of candidate search terms; and assessing a time since a last order from a customer of items in the initial set of candidate search terms.
16. 16 . The non-transitory computer-readable storage medium of claim 9 , wherein the ranked lists of items are selected and ordered by applying a search ranking algorithm based on at least customer profile data about the customer and based on promotion data about the items.
17. 17 . A computer system comprising: a processor; and a non-transitory computer-readable storage medium storing instructions executable by the processor for performing steps comprising: receiving, over a network at a content presentation module of an online concierge system, a request for a home screen user interface from a client device associated with a customer of the online concierge system; responsive to receiving the request, obtaining, by the content presentation module, a user identifier for the customer of the online concierge system; based on the user identifier, obtaining, by the content presentation module, a set of recommended search terms for the customer that the online concierge system predicts will yield search results having relevance to the customer, wherein the set of search terms are obtained from a database storing recommended search terms in association with user identifiers; executing, by the content presentation module, respective search queries in a search application of the online concierge system to generate respective search result sets for each of the respective search queries, each of the respective search result sets comprising respective ranked lists of items relevant to the respective search queries; generating, by the content presentation module, a home screen user interface for the client device, the home screen user interface including selectable user interface elements for selecting one or more items in the ranked lists of items, wherein each selectable user interface element comprises a scrollable carousel of horizontally-arranged items within a corresponding ranked list of items, and wherein the selectable user interface element further comprises a scroll control element that causes the scrollable carousel to display additional items; transmitting, by the content presentation module over the network, instructions to the client device to display the home screen user interface, wherein the instructions cause the client device to display a graphical user interface comprising the home screen user interface; receiving, by the content presentation module over the network, a notification from the client device that the customer has interacted with the scroll control element of a scrollable carousel of a selectable user interface element of the home screen user interface; identifying, by the content presentation module, a set of additional items relevant to a search query corresponding to the selectable user interface element associated with the scroll control element with which the user interacted; transmitting, by the content presentation module over the network, instructions to the client device to update the home screen user interface to display the set of additional items; receiving, by the content presentation module from the client device via the home screen user interface, a selection of an item of the set of additional items for adding to an order; and facilitating, by the online concierge system, procurement of the order and delivery of the order to the customer.
18. 18 . The computer system of claim 17 , wherein obtaining the set of recommended search terms comprises: identifying, based on the user identifier, an item previously purchased by the customer via the online concierge system; identifying, for the item, a plurality of converted search queries submitted from a population of customers of the online concierge system that resulted in purchases of the item; identifying, from the plurality of converted search query, a top performing converted search query for the item; and including the top performing converted search query in the set of recommended search terms.
19. 19 . The computer system of claim 17 , wherein obtaining the set of recommended search terms comprises: obtaining, based on the user identifier, a historical set of search queries entered by the customer; and obtaining the set of recommended search terms based at least in part on the historical set of search queries.
20. 20 . The computer system of claim 17 , wherein obtaining the set of recommended search terms comprises: obtaining a user embedding for the customer based a profile of the customer in the online concierge system; identifying search terms having search embeddings meeting similarity criteria with the user embedding; and obtaining the set of recommended search terms based at least in part on identified search terms.

Description

BACKGROUND An online concierge system receives selections of items from customers, assigns orders to pickers to procure the items from physical retailers, and facilitates delivery of those items from the picker to the customer. In such a system, it is desirable to generate recommendations for items to assist the customer in efficiently generating orders. SUMMARY An online concierge system generates a personalized storefront user interface to recommend items for purchase and delivery to a customer. The online concierge system obtains a user identifier for a customer of an online concierge system. Based on the user identifier, the online concierge system obtains a set of recommended search terms for the customer that the online concierge system predicts will yield search results having relevance to the customer. The online concierge system executes respective search queries in a search engine of the online concierge system to generate respective search result sets for each of the respective search queries. Each of the respective search result sets comprise respective ranked lists of items relevant to the respective search queries. The online concierge system generates a user interface including selectable user interface elements for selecting one or more items in the ranked lists of items. The online concierge system receives, via the user interface, a selection of an item for adding to an order and facilitates procurement of the order and delivery of the order to the customer. In one or more embodiments, obtaining the set of recommended search terms comprises identifying, based on the user identifier, an item previously purchased by the customer via the online concierge system; identifying, for the item, a plurality of converted search queries submitted from a population of customers of the online concierge platform that resulted in purchases of the item; identifying, from the plurality of converted search query, a top performing converted search query for the item; and including the top performing converted search query in the set of recommended search terms. In one or more embodiments, obtaining the set of recommended search terms comprises obtaining, based on the user identifier, a historical set of search queries entered by the customer and obtaining the set of recommended search terms based at least in part on the historical set of search queries. In one or more embodiments, obtaining the set of recommended search terms comprises obtaining a user embedding for the customer based a profile of the customer in the online concierge system, identifying search terms having search embeddings meeting similarity criteria with the user embedding, and obtaining the set of recommended search terms based at least in part on identified search terms. In one or more embodiments, obtaining the set of recommended search terms comprises obtaining a set complementary search terms meeting a similarity metric with one or more historical search terms entered by the user in the online concierge system, and obtaining the set of recommended search terms based at least in part on the set of complementary search terms. In one or more embodiments, obtaining the set of recommended search terms comprises obtaining an initial set of candidate search terms, performing a quality assessment of the initial set of candidate search terms, and selecting the set of recommended search terms from the initial set of candidate search terms that pass the quality assessment. Performing the quality assessment may comprise at least one of assessing historical conversion rates on the initial set of candidate search terms, assessing reorder probabilities of items returned in a search query using the initial set of candidate search terms, assessing a sensitivity level of a category of items relating to the initial set of candidate search terms, and assessing a time since a last order from a customer of items in the initial set of candidate search terms. In one or more embodiments, the ranked lists of items are selected and ordered by applying a search ranking algorithm based on at least customer profile data characterizing the customer and promotion data associated with items. In further embodiments, a non-transitory computer-readable storage medium stores instructions executable by a processor for carrying out any of the processes described herein. Furthermore, a computer system may include a process and a non-transitory computer-readable storage medium as described herein. BRIEF DESCRIPTION OF THE DRAWINGS FIG. 1 illustrates an example system environment for an online concierge system, in accordance with one or more embodiments. FIG. 2 illustrates an example system architecture for an online concierge system, in accordance with one or more embodiments. FIG. 3 is an example embodiment of a process for generating a personalized storefront user interface in an online concierge system. FIG. 4 is an example layout for a personalized storefront user interfa