Systems and methods for affinity-driven interface generation

Patent metadata

Field	Value
Publication number	US-12578976-B2
Application number	US-202418428292-A
Country	US
Kind code	B2
Filing date	Jan 31, 2024
Priority date	Jan 31, 2024
Publication date	Mar 17, 2026
Grant date	Mar 17, 2026

Abstract

Systems and methods of generating personalized interfaces are disclosed. An interface generation request is received and, in response to receiving the interface generation request, a plurality of user-relevant element bundles is selected. The plurality of user-relevant bundles is selected in part by a weighted random sampling process. In response to selecting the plurality of user-relevant element bundles, a set of interface elements associated with each of the plurality of user-relevant element bundles is ranked based on interface element relevance to a user associated with the interface generation request. Instructions to cause generation of an interface including at least one of the plurality of user-relevant element bundles and at least a top-ranked interface element selected from the set of interface elements associated with the at least one of the plurality of user-relevant element bundles are transmitted to a user device.

First claim

What is claimed is:

1 . A system, comprising:
a non-transitory memory; a processor communicatively coupled to the non-transitory memory, wherein the processor is configured to read a set of instructions to: receive an interface generation request; in response to receiving the interface generation request, select a plurality of user-relevant element bundles, wherein the plurality of user-relevant element bundles is selected in part by a weighted random sampling process that includes converting a rank of each user-relevant element bundle in the plurality of user-relevant element bundles to a weight and defining a selection range for each user-relevant element bundle based on the weight; in response to selecting the plurality of user-relevant element bundles, rank a set of interface elements associated with each of the plurality of user-relevant element bundles based on interface element relevance to a user associated with the interface generation request; and transmit instructions to cause generation of an interface including at least one of the plurality of user-relevant element bundles and at least a top-ranked interface element selected from the set of interface elements associated with the at least one of the plurality of user-relevant element bundles.

2 . The system of claim 1 , wherein selection of the user-relevant element bundles comprises ranking a plurality of available element bundles based on a relevance to the user associated with the interface generation request.

3 . The system of claim 2 , wherein selection of the user-relevant element bundles comprises a transaction-based ranking process, and wherein the weighted random sampling process is applied after the transaction-based ranking process.

4 . The system of claim 2 , wherein the ranking of the available element bundles is based on one or more feature weights for one or more features associated with each of the available element bundles.

5 . The system of claim 4 , wherein ranking the set of interface elements associated with each of the plurality of user-relevant element bundles is based on one or more feature weights for one or more features associated with each interface element in the set of interface elements.

6 . The system of claim 4 , wherein the one or more feature weights are representative of a user affinity for each of the one or more features.

7 . The system of claim 1 , wherein the weighted random sampling process comprises:
normalizing each of the weights; defining the selection range for each user-relevant element bundle based on the weight comprises defining the selection range for each user-relevant element bundle based on a corresponding one of the weights and the weight of a next-ranked user-relevant element bundle; and selecting at least one user-relevant element bundle by randomly generating a number within an aggregated selection range for the plurality of user-relevant element bundles.

8 . A computer-implemented method, comprising:
receiving an interface generation request; in response to receiving the interface generation request, selecting a plurality of user-relevant element bundles, wherein the plurality of user-relevant element bundles is selected in part by a weighted random sampling process that includes converting a rank of each user-relevant element bundle in the plurality of user-relevant element bundles to a weight and defining a selection range for each user-relevant element bundle based on the weight; in response to selecting the plurality of user-relevant element bundles, ranking a set of interface elements associated with each of the plurality of user-relevant element bundles based on interface element relevance to a user associated with the interface generation request; and transmitting instructions to cause generation of an interface including at least one of the plurality of user-relevant element bundles and at least a top-ranked interface element selected from the set of interface elements associated with the at least one of the plurality of user-relevant element bundles.

9 . The computer-implemented method of claim 8 , wherein selection of the user-relevant element bundles comprises ranking a plurality of available element bundles based on a relevance to the user associated with the interface generation request.

10 . The computer-implemented method of claim 9 , wherein selection of the user-relevant element bundles comprises a transaction-based ranking process, and wherein the weighted random sampling process is applied after the transaction-based ranking process.

11 . The computer-implemented method of claim 9 , wherein the ranking of the available element bundles is based on one or more feature weights for one or more features associated with each of the available element bundles.

12 . The computer-implemented method of claim 11 , wherein ranking the set of interface elements associated with each of the plurality of user-relevant element bundles is based on one or more feature weights for one or more features associated with each interface element in the set of interface elements.

13 . The computer-implemented method of claim 11 , wherein the one or more feature weights are representative of a user affinity for each of the one or more features.

14 . The computer-implemented method of claim 8 , wherein the weighted random sampling process comprises:
normalizing each of the weights; defining the selection range for each user-relevant element bundle based on the weight comprises defining the selection range for each user-relevant element bundle based on a corresponding one of the weights and the weight of a next-ranked user-relevant element bundle; and selecting at least one user-relevant element bundle by randomly generating a number within an aggregated selection range for the plurality of user-relevant element bundles.

15 . A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause at least one device to perform operations comprising:
receiving an interface generation request; in response to receiving the interface generation request, selecting a plurality of user-relevant element bundles, wherein the plurality of user-relevant element bundles is selected in part by a weighted random sampling process that includes converting a rank of each user-relevant element bundle in the plurality of user-relevant element bundles to a weight and defining a selection range for each user-relevant element bundle based on the weight; in response to selecting the plurality of user-relevant element bundles, ranking a set of interface elements associated with each of the plurality of user-relevant element bundles based on interface element relevance to a user associated with the interface generation request; and transmitting instructions to cause generation of an interface including at least one of the plurality of user-relevant element bundles and at least a top-ranked interface element selected from the set of interface elements associated with the at least one of the plurality of user-relevant element bundles.

16 . The non-transitory computer readable medium of claim 15 , wherein selection of the user-relevant element bundles comprises ranking a plurality of available element bundles based on a relevance to the user associated with the interface generation request.

17 . The non-transitory computer readable medium of claim 16 , wherein selection of the user-relevant element bundles comprises a transaction-based ranking process, and wherein the wei

Assignees

• Walmart Apollo Llc

Inventors

• Inan Aysenur
• Jadhav Shreyas Saiprasad
• Huang Hongyao
• Cho Hyun Duk
• Arora Yokila
• Kumar Sushant
• Achan Kannan

Classifications

• G06F9/451 Primary

  Execution arrangements for user interfaces · CPC title