# US 12,112,364 B2 · Different action user-interface components in a comparison view > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,112,364 B2 - Document ID: US12112364B2 - Status: Granted - Kind: B2 - Application number: 17/870,331 - Filed: 2022-07-21 - Published: 2022-11-10 - Granted: 2024-10-08 - Earliest claimed: 2019-10-01 - Assignees: eBay Inc. - Applicants: eBay Inc. - Inventors: Ramesh Periyathambi; Tomer Lancewicki; Sai Vipin Siripurapu; Lakshimi Duraivenkatesh; Selcuk Kopru - Web page: https://patentgrep.com/patent/US12112364B2 ## CPC - G06Q 30/0629: {by pre-processing results, e.g. ranking or ordering results} - G06F 3/0482: Interaction with lists of selectable items, e.g. menus - G06N 20/00: Machine learning - G06Q 30/0643: {graphically representing goods, e.g. 3D product representation} - G06Q 30/08: Auctions - 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) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract Different action user-interface components in a comparison view are described. Initially, a selection is received to display a comparison view via a user interface of a listing platform. Multiple listings of the listing platform are selected for inclusion in the comparison view. A comparison view system determines which action of a plurality of actions, used by the listing platform, to associate with each of the listings. A display device displays the multiple listings concurrently in a comparison view via a user interface of the listing platform and also displays an action user-interface component (e.g., a button) in each of the plurality of listings. The action user-interface component is selectable to initiate the action associated with the respective listing. In accordance with the described techniques, the action user-interface component displayed in at least two of the multiple listings is selectable to initiate different actions in relation to the respective listing. ## Claims ### Claim 1 A method comprising: monitoring user interactions with previously displayed action elements displayed in association with listings of a listing platform and corresponding to actions previously selected using a machine learning model; refining the machine learning model based on the monitored user interactions; determining, using the machine learning model, which action of the actions to associate with a first listing and a second listing to be displayed concurrently in a comparison view; displaying, in the comparison view, only one action element in the first listing that is selectable to initiate an action with respect to the first listing; and displaying, in the comparison view, only one action element in the second listing that is selectable to initiate a different action with respect to the second listing. ### Claim 2 (depends on 1) The method of claim 1, wherein the machine learning model is refined based on the user interactions being monitored over a defined time period subsequent to the previously displayed action elements being displayed. ### Claim 3 (depends on 2) The method of claim 2, wherein refining the machine learning model based on a previously displayed action element includes positively or negatively reinforcing the machine learning model based on whether the previously displayed action element was selected within the defined time period. ### Claim 4 (depends on 2) The method of claim 2, wherein refining the machine learning model based on a previously displayed action element includes determining a reward for the previously displayed action element based on whether the previously displayed action element was selected within the defined time period, and adjusting internal weights of the machine learning model based on the reward. ### Claim 5 (depends on 1) The method of claim 1, wherein the actions corresponding to the previously displayed action elements are determined according to an initial policy for the machine learning model. ### Claim 6 (depends on 5) The method of claim 5, wherein refining the machine learning model includes refining the initial policy for the machine learning model based on the monitored user interactions with the previously displayed action elements, the action and the different action determined according to the refined policy. ### Claim 7 (depends on 1) The method of claim 1, wherein the first listing represents a first item and the second listing represents a second item. ### Claim 8 (depends on 1) The method of claim 1, wherein the machine learning model further determines which action to associate with listings of the comparison view based on at least one of: a most used action element leading to conversion previously with listings of the listing platform for a user to which the comparison view is displayed; a category associated with a respective listing; a price associated with the respective listing; a number of times the respective listing is added to a watch list by other users of the listing platform; a number of times the respective listing is added to an online shopping cart by other users of the listing platform; and a number of times the respective listing is viewed by other users of the listing platform. ### Claim 9 (depends on 1) The method of claim 1, further comprising: determining a first action to associate with the first listing for a particular user of the listing platform at a first time; and determining a second action to associate with the first listing for the particular user of the listing platform at a second time. ### Claim 10 (depends on 1) The method of claim 1, further comprising: determining a first action to associate with the first listing for a user of the listing platform at a particular time; and determining a second action to associate with the first listing for a different user of the listing platform at the particular time. ### Claim 11 (depends on 1) The method of claim 1, further comprising displaying, in each listing of the comparison view, a comparison explanation identifying a reason for including a respective listing in the comparison view. ### Claim 12 (depends on 1) The method of claim 1, further comprising displaying a user interface of the listing platform including the comparison view and a listing specific portion, the listing specific portion corresponding to one listing of the comparison view and including multiple, different action elements that are selectable to initiate multiple, different actions with respect to the one listing. ### Claim 13 (depends on 1) The method of claim 1, wherein refining the machine learning model includes positively or negatively reinforcing the machine learning model based on the monitored user interactions. ### Claim 14 A system comprising: a listing platform implemented by one or more server devices that are communicatively coupled to a client device; and a comparison view system implemented at least partially in software of the one or more server devices to: monitor user interactions with previously displayed action elements displayed in association with listings of a listing platform and corresponding to actions previously selected using a machine learning model; refine the machine learning model based on the monitored user interactions; determine, using the machine learning model, which action of the actions to associate with a first listing and a second listing to be displayed concurrently in a comparison view; and communicating, over a network, the comparison view to the client device causing the client device to display the comparison view, only one action element being displayed in the first listing of the comparison view that is selectable to initiate an action with respect to the first listing, only one action element being displayed in the second listing of the comparison view that is selectable to initiate a different action with respect to the second listing. ### Claim 15 (depends on 14) The system of claim 14, wherein the machine learning model is refined based on the user interactions being monitored over a defined time period subsequent to the previously displayed action elements being displayed. ### Claim 16 (depends on 14) The system of claim 14, wherein the actions corresponding to the previously displayed action elements are determined according to an initial policy embodied by the machine learning model. ### Claim 17 (depends on 16) The system of claim 16, wherein the comparison view system is further implemented to refine the initial policy embodied by the machine learning model based on the monitored user interactions with the previously displayed action elements, the action and the different action determined according to the refined policy. ### Claim 18 (depends on 14) The system of claim 14, wherein the communication of the comparison view to the client device causes the client device to render a user interface of the listing platform including the comparison view and a listing specific portion, the listing specific portion corresponding to one listing of the comparison view and including multiple, different action elements that are selectable to initiate multiple, different actions with respect to the one listing. ### Claim 19 One or more non-transitory computer computer-readable storage media storing instructions that are executable by one or more processors to perform operations including: monitoring user interactions with previously displayed action elements displayed in association with listings of a listing platform and corresponding to actions previously selected using a machine learning model; refining the machine learning model based on the monitored user interactions; determining, using the machine learning model, which action of the actions to associate with a first listing and a second listing to be displayed concurrently in a comparison view; and displaying, in the comparison view, only one action element in the first listing that is selectable to initiate an action with respect to the first listing and only one action in the second listing that is selectable to initiate a different action with respect to the second listing. ### Claim 20 (depends on 19) The one or more non-transitory computer computer-readable storage media of claim 19, wherein the machine learning model is refined based on the user interactions being monitored over a defined time period subsequent to the previously displayed action elements being displayed.