# US 11,308,543 B1 · Methods and apparatus for automatically providing personalized carousels > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,308,543 B1 - Document ID: US11308543B1 - Status: Granted - Kind: B1 - Application number: 17/129,539 - Filed: 2020-12-21 - Granted: 2022-04-19 - Earliest claimed: 2020-12-21 - Assignees: Walmart Apollo, LLC - Applicants: Walmart Apollo LLC - Inventors: Aditya Mantha; Shubham Gupta; Anirudha Sundaresan; Gaoyang Wang; Shashank Kedia; Yokila Arora; Parveenkumar Kanumala; Stephen Dean Guo; Kannan Achan - Web page: https://patentgrep.com/patent/US11308543B1 ## CPC - G06Q 30/0631: {Recommending goods or services} - G06F 16/24578: {using ranking} - G06F 16/9535: Search customisation based on user profiles and personalisation - G06F 16/9538: Presentation of query results - G06Q 30/0255: {based on user history} - G06Q 30/0269: {based on user profile or attribute} - G06Q 30/0641: {utilising user interfaces specially adapted for shopping} - G06F 3/14: Digital output to display device {; Cooperation and interconnection of the display device with other functional units} - G09G 2354/00: Aspects of interface with display user - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G09G: ARRANGEMENTS OR CIRCUITS FOR CONTROL OF INDICATING DEVICES USING STATIC MEANS TO PRESENT VARIABLE INFORMATION (arrangements for transferring data between digital computers and displays G06F3/14; static indicating arrangements comprising an association of a number of separate sources or light control cells G09F9/00; static indicating arrangements comprising integral associations of a number of light sources H01J, H01K, H10H, H05B33/12; scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission, details thereof H04N1/00) ## Abstract This application relates to apparatus and methods for automatically determining and providing carousels specifically curated for a user. In some examples, a computing device obtains user transaction data identifying in-store and/or online transactions, and user engagement data identifying user interactions with items and carousels from user's prior sessions. The computing device determines a sequential order for presentation of carousels with a set of item recommendations. For example, the computing device scores each potential carousel based on prior user interactions and transactions with items and carousels. The carousels are then ranked and subsequently presented to the user based on their corresponding scores. ## Claims ### Claim 1 A system comprising: a computing device configured to: obtain user data associated with a user from a database during a session on a user device; obtain a plurality of carousels, each carousel including a set of items; compute, for the user, a user-carousel repeat score indicating a likelihood of the user interacting with previously selected items in each carousel of the plurality of carousels based on prior interactions with the corresponding carousel and the corresponding set of items indicated in the user data; compute, for the user, a user-carousel discovery score indicating a likelihood of the user interacting with previously unseen items in each carousel of the plurality of carousels based on prior interactions indicated in the user data; determine a user-carousel score for each carousel of the plurality of carousels based on the user-carousel repeat score and the user-carousel discovery score, the user-carousel score indicating a likelihood of the user interacting with each corresponding carousel; and cause to present, via a user interface of the user device, the plurality of carousels to the user device based at least in part on the corresponding user-carousel scores. ### Claim 2 (depends on 1) The system of claim 1, wherein the user data includes user engagement data and user transaction data. ### Claim 3 (depends on 2) The system of claim 2, wherein the user engagement data includes one or more of user clicks, add to carts, carousel impressions, and item impressions. ### Claim 4 (depends on 1) The system of claim 1, wherein the computing device is further configured to: for each carousel of the plurality of carousels, determine a user-item affinity score associated with item in the set of items based on user data, the user-item affinity score indicating a propensity of the user to buy the item; for each carousel of the plurality of carousels, determine a user-carousel prior score based on user data, the user-carousel prior score indicating a likelihood of the user interacting with the carousel based on past interaction with the carousel; and determine, for each carousel of the plurality of carousels, the user-carousel repeat score based on the corresponding user-item affinity scores and the corresponding user-carousel prior score. ### Claim 5 (depends on 1) The system of claim 1, wherein the computing device is further configured to: for each carousel of the plurality of carousels, determine a user-category discovery score associated with each item in the set of items based on user data, the user-category discovery score indicating a likelihood of the user interacting with previously unseen items in the corresponding category; and determine, for each carousel of the plurality of carousels, the user-carousel discovery score based on the corresponding user-category discovery scores for the corresponding carousel. ### Claim 6 (depends on 1) The system of claim 1, wherein the computing device is further configured to rank the plurality of carousels based on the corresponding user-carousel scores, and the plurality of carousels are caused to present in an order based on the corresponding ranks. ### Claim 7 A method comprising: obtaining user data associated with a user from a database during a session on a user device; obtaining a plurality of carousels, each carousel including a set of items; computing, for the user, a user-carousel repeat score indicating a likelihood of the user interacting with previously selected items in each carousel of the plurality of carousels based on prior interactions with the corresponding carousel and the corresponding set of items indicated in the user data; computing, for the user, a user-carousel discovery score indicating a likelihood of the user interacting with previously unseen items in each carousel of the plurality of carousels based on prior interactions indicated in the user data; determining a user-carousel score for each carousel of the plurality of carousels based on the user-carousel repeat score and the user-carousel discovery score, the user-carousel score indicating a likelihood of the user interacting with each corresponding carousel; and causing to present, via a user interface of the user device, the plurality of carousels to the user device based at least in part on the corresponding user-carousel scores. ### Claim 8 (depends on 7) The method of claim 7, wherein the user data includes user engagement data and user transaction data. ### Claim 9 (depends on 8) The method of claim 8, wherein the user engagement data includes one or more of user clicks, add to carts, carousel impressions, and item impressions. ### Claim 10 (depends on 7) The method of claim 7, the method further comprising: for each carousel of the plurality of carousels, determining a user-item affinity score associated with item in the set of items based on user data, the user-item affinity score indicating a propensity of the user to buy the item; for each carousel of the plurality of carousels, determining a user-carousel prior score based on user data, the user-carousel prior score indicating a likelihood of the user interacting with the carousel based on past interaction with the carousel; and determining, for each carousel of the plurality of carousels, the user-carousel repeat score based on the corresponding user-item affinity scores and the corresponding user-carousel prior score. ### Claim 11 (depends on 7) The method of claim 7, the method further comprising: for each carousel of the plurality of carousels, determining a user-category discovery score associated with each item in the set of items based on user data, the user-category discovery score indicating the likelihood of the user interacting with previously unseen items in the corresponding category; and determining, for each carousel of the plurality of carousels, the user-carousel discovery score based on the corresponding user-category discovery scores for the corresponding carousel. ### Claim 12 (depends on 7) The method of claim 7, the method further comprising ranking the plurality of carousels based on the corresponding user-carousel scores, and causing to present the plurality of carousels in a sequential order based on the corresponding ranks. ### Claim 13 A non-transitory computer readable medium having instructions stored thereon, wherein the instructions, when executed by at least one processor, cause a device to perform operations comprising: obtaining user data associated with a user from a database during a session on a user device; obtaining a plurality of carousels, each carousel including a set of items; computing, for the user, a user-carousel repeat score indicating a likelihood of the user interacting with previously selected items in each carousel of the plurality of carousels based on prior interactions with the corresponding carousel and the corresponding set of items indicated in the user data; computing, for the user, a user-carousel discovery score indicating a likelihood of the user interacting with previously unseen items in each carousel of the plurality of carousels based on prior interactions indicated in the user data; determining a user-carousel score for each carousel of the plurality of carousels based on the user-carousel repeat score and the user-carousel discovery score, the user-carousel score indicating a likelihood of the user interacting with each corresponding carousel; and causing to present, via a user interface of the user device, the plurality of carousels to the user device based at least in part on the corresponding user-carousel scores. ### Claim 14 (depends on 13) The non-transitory computer readable storage medium of claim 13, wherein the user data includes user engagement data and user transaction data. ### Claim 15 (depends on 14) The non-transitory computer readable storage medium of claim 14, wherein the user engagement data includes one or more of user clicks, add to carts, carousel impressions, and item impressions. ### Claim 16 (depends on 13) The non-transitory computer readable storage medium of claim 13, the operations further comprising: for each carousel of the plurality of carousels, determining a user-item affinity score associated with item in the set of items based on user data, the user-item affinity score indicating a propensity of the user to buy the item; for each carousel of the plurality of carousels, determining a user-carousel prior score based on user data, the user-carousel prior score indicating a likelihood of the user interacting with the carousel based on past interaction with the carousel; and determining, for each carousel of the plurality of carousels, the user-carousel repeat score based on the corresponding user-item affinity scores and the corresponding user-carousel prior score. ### Claim 17 (depends on 13) The non-transitory computer readable storage medium of claim 13, the operations further comprising: for each carousel of the plurality of carousels, determining a user-category discovery score associated with each item in the set of items based on user data, the user-category discovery score indicating the likelihood of the user interacting with previously unseen items in the corresponding category; and determining, for each carousel of the plurality of carousels, the user-carousel discovery score based on the corresponding user-category discovery scores for the corresponding carousel.