System and method for recommending 2D images - Patents.com

The system recommends 2D images based on 3D models and customer interactions in augmented or virtual reality to improve product representation in online stores and search results, addressing the challenge of selecting optimal images.

JP7595436B2Active Publication Date: 2024-12-06SHOPIFY INC
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
JP2020170285
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2020-07-30
Filing Date
2020-10-08
Publication Date
2024-12-06
Estimated Expiration
2040-10-08

AI Technical Summary

Technical Problem

Merchants struggle to select the most appropriate 2D images for their online store listings and search engine results, as they often default to generic views without considering customer interactions, leading to suboptimal representation of products.

Method used

A system that recommends 2D images based on 3D models, analyzing customer interactions in augmented or virtual reality environments to determine desired views, and generating recommendations for optimal image selection.

Benefits of technology

Enhances the representation of products by aligning images with customer preferences, potentially increasing sales and engagement through more appealing and relevant 2D views.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007595436000001
    Figure 0007595436000001
  • Figure 0007595436000002
    Figure 0007595436000002
  • Figure 0007595436000003
    Figure 0007595436000003
Patent Text Reader

Abstract

To provide systems and methods for recommending two-dimensional images, which may be implemented on an e-commerce platform.SOLUTION: Methods and systems for generating 2D images based on a 3D model are disclosed. Three-dimensional (3D) model data associated with a product offering in an online store are sent to a first electronic device, the 3D model data being generated from a stored 3D model. Data representing a selected value for a viewing parameter of the stored 3D model are received from the first electronic device. From the received data, a desired 2D view is determined for a stored 3D model. A recommendation is generated, for a second electronic device, to include the desired 2D view in a stored listing associated with the product offering.SELECTED DRAWING: Figure 6
Need to check novelty before this filing date? Find Prior Art

Description

[Technical field]

[0001] The present disclosure relates to a system and method for recommending two-dimensional images that may be implemented in an e-commerce platform. [Background technology]

[0002] (background) The e-commerce platform may enable customers to purchase merchant products (e.g., goods and / or services) from merchants. Customers may also use the e-commerce platform to discover merchant products that may be of interest to them (e.g., using search and / or recommendation services offered by the e-commerce platform).

[0003] A customer may view details of a product (or service) before making a purchase on an e-commerce platform. Typically, a merchant online store may list a variety of products and / or services, and each listing of an offering may have one or more images associated with the offering, at least one of which may be a default image. Typically, the default image is the dominant image shown on the listing page for the offering. For example, the default image may be the largest image shown on the listing page among multiple images for a given offering. In another example, the default image may be the only image shown on the listing page, but additional images, if available, may be hidden from view. Thus, the right default image may be valuable in making a good first impression of an offering by a merchant through the online store.

[0004] Customers may also use general search engines (e.g., Google™) to look for merchant offerings, and the search engine may return multiple results based on the customer's search query. Some of the returned results may include images associated with the online store or offerings that match the search query. The returned search results, including images, can be a powerful tool for a merchant's online store in attracting potential customers and generating virtual foot traffic. Thus, in responding to a web-based search engine query, it can be important to provide the most appropriate image that represents the online store or offering.

[0005] Traditionally, most merchants do not know which representative image should be selected as the default image in a listing or as the image for responding to web-based search engines. Often, merchants choose a representative view (e.g., a product view that shows the entire product in a reasonable setting) without too much thought.

[0006] Therefore, improvements are desired to aid in the selection of images to include in a listing and / or to represent an online store. Summary of the Invention [Means for solving the problem]

[0007] (overview) The present disclosure describes various examples in which 2D images are recommended based on 3D models. In some implementations, the 3D models are associated with products offered in an online store. For example, 2D views or 2D images may be recommended based on how a customer manipulates or interacts with a stored 3D model of a product offered in an online store. In some implementations, the interaction may occur in an augmented reality (AR) or virtual reality (VR) environment.

[0008] In some aspects of the present disclosure, a system for generating recommendations for 2D images based on a 3D model is provided. The system may include a processor in communication with a storage, the processor being configured to execute instructions that cause the system to: send three-dimensional (3D) model data associated with an offering of an online store to a first electronic device, where the 3D model data is generated from the stored 3D model; receive data representing selected values ​​for view parameters of the stored 3D model from the first electronic device; determine a desired two-dimensional (2D) view of the stored 3D model from the received data; and generate a recommendation for including the desired 2D view in a stored listing associated with the offering of the online store for a second electronic device.

[0009] In some instances, the recommendations are generated after determining that the desired 2D view is not present in the stored listings for the product offering.

[0010] In some examples, the instructions also cause the system to generate a 2D image corresponding to the desired 2D view from the stored 3D model.

[0011] In some examples, the instructions further cause the system to compare the generated 2D image with a current 2D image included in a stored listing for the offered product to determine that the desired 2D view is not present in the listing.

[0012] In some examples, the recommendations include 2D images or options for updating the stored listings with 2D images.

[0013] In some examples, the selected value for the view parameter includes one of a selected zoom level, a selected size of the virtual object generated based on the stored 3D model, a selected view angle, a selected orientation of the virtual object, or a selected visual characteristic of the virtual object.

[0014] In some examples, the selected value for the view parameter is determined to be the selected value based on the stored 3D model being viewed at the selected value for the view parameter for a threshold dwell time.

[0015] In some examples, data representing a plurality of selected values ​​for a view parameter of the stored 3D model is received from a respective plurality of customer electronic devices.

[0016] In some examples, the desired 2D view of the stored 3D model is determined from the received data based on a statistical analysis of a plurality of selected values ​​for the view parameter.

[0017] In some examples, the instructions further cause the system to cause the first electronic device to display the stored 3D model in a virtual reality environment.

[0018] In some examples, the instructions further cause the system to cause the first electronic device to display the stored 3D model in an augmented reality environment.

[0019] In some examples, the instructions further cause the system to associate at least one customer attribute with the selected value for the view parameter and generate recommendations specific to the at least one customer attribute.

[0020] In some aspects, the present disclosure provides a system for generating a recommendation for a 2D image for a second electronic device based on a first different 3D model. The system may include a processor in communication with a storage, the processor being configured to execute instructions that cause the system to: send three-dimensional (3D) model data associated with an offering product to the first electronic device, where the 3D model data is generated from the first stored 3D model; receive data representing selected values ​​for view parameters of the first stored 3D model from the first electronic device; determine from the received data a desired 2D view of a second stored 3D model associated with the same offering product or a different offering product, where the first stored 3D model is determined to be associated with the second stored 3D model; and generate a recommendation for including the desired 2D view in a stored listing associated with the second stored 3D model for the second electronic device.

[0021] In some examples, a first stored 3D model is determined to be related to a second stored 3D model on the basis that the first stored 3D model and the second stored 3D model are associated with the same product offering.

[0022] In some examples, the first stored 3D model and the second stored 3D model are associated with different product offerings, and the first stored 3D model is determined to be related to the second stored 3D model on the basis that the different product offerings belong to the same category.

[0023] In some examples, the instructions further cause the system to generate a 2D image corresponding to the desired 2D view from the second stored 3D model. The recommendation may include the generated 2D image or an option to update a stored listing associated with the second stored 3D model with the generated 2D image.

[0024] In some examples, data representing a plurality of selected values ​​for a view parameter of the first stored 3D model may be received from a respective plurality of customer electronic devices, and a desired 2D view of the second stored 3D model may be determined from the received data based on a statistical analysis of the plurality of selected values ​​for the view parameter.

[0025] In some aspects, the disclosure describes a method that includes sending three-dimensional (3D) model data associated with an offering of an online store to a first electronic device, where the 3D model data is generated from a stored 3D model, receiving data representing selected values ​​for view parameters of the stored 3D model from the first electronic device, determining a desired two-dimensional (2D) view of the stored 3D model from the received data, and generating a recommendation for including the desired 2D view in a stored listing associated with the online store for a second electronic device.

[0026] In some instances, the recommendations are generated after determining that the desired 2D view is not present in the stored listings for the product offering.

[0027] In some examples, the method may include generating a 2D image corresponding to the 2D view from the stored 3D model.

[0028] In some examples, the method may include comparing the generated 2D image with a current 2D image included in a stored listing for the offered product to determine that the desired 2D view is not present in the listing.

[0029] In some examples, the recommendations include 2D images or options for updating the stored listings with 2D images.

[0030] In some examples, the selected value for the view parameter includes one of a selected zoom level, a selected size of the virtual object generated based on the stored 3D model, a selected view angle, a selected orientation of the virtual object, or a selected visual characteristic of the virtual object.

[0031] In some examples, the selected value for the view parameter is determined to be the selected value based on the stored 3D model being viewed at the selected value for the view parameter for a threshold dwell time.

[0032] In some examples, data representing a plurality of selected values ​​for a view parameter of the stored 3D model is received from a respective plurality of customer electronic devices.

[0033] In some examples, the desired 2D view of the stored 3D model is determined from the received data based on a statistical analysis of a plurality of selected values ​​for the view parameter.

[0034] In some examples, the method may include causing the first electronic device to display the stored 3D model in a virtual reality environment.

[0035] In some examples, the method may include causing the first electronic device to display the stored 3D model in an augmented reality environment.

[0036] In some examples, the method may include associating at least one customer attribute with a selected value for the view parameter and generating recommendations to be specific to the at least one customer attribute.

[0037] Thus, there is provided a method, system and computer program product as detailed in the claims below. For example, the present invention provides the following: (Item 1) 1. A method for generating recommendations for a 2D image based on a 3D model, the method comprising: sending three-dimensional (3D) model data associated with the object to one or more first electronic devices, the 3D model data being generated from a stored 3D model; receiving data representing one or more selected values ​​for a respective view parameter of the stored 3D model from a first of the one or more electronic devices; determining a two-dimensional (2D) view of the stored 3D model from the received data based on a statistical analysis of the one or more selected values ​​for the view parameter; generating a recommendation for a second electronic device to include the desired 2D view in a stored listing associated with the object; and A method comprising: (Item 2) The method of any preceding claim, wherein the recommendation is generated after determining that the desired 2D view is not present in a stored listing for the object. (Item 3) generating a 2D image corresponding to the 2D view from the stored 3D model; and comparing the generated 2D image with a current 2D image included in the stored listing for the object to determine that the 2D view does not exist in the listing; and The method according to any of the above items, further comprising: (Item 4) The method of any preceding claim, wherein the recommendation includes the 2D image or includes an option to update the stored listing with the 2D image. (Item 5) The one or more selected values ​​for the view parameter The selected zoom level, a selected size of a virtual object generated based on the stored 3D model; The selected view angle, a selected orientation of the virtual object, or Selected visual characteristics of the virtual object. The method according to any of the above items, comprising one or more of the following: (Item 6) The method of any of the preceding items, wherein the one or more selected values ​​for the view parameter are determined to be the one or more selected values ​​based on the stored 3D model viewed at the one or more selected values ​​for the view parameter for a threshold dwell time. (Item 7) Associating at least one customer attribute with the one or more selected values ​​for the view parameter; generating the recommendations to be specific to the at least one customer attribute; The method according to any of the above items, further comprising: (Item 8) 1. A method for generating recommendations for a 2D image based on a 3D model, the method comprising: sending three-dimensional (3D) model data associated with the object to one or more first electronic devices, the 3D model data being generated from a first stored 3D model; receiving data representing one or more selected values ​​for view parameters of the first stored 3D model from a first of the one or more electronic devices; determining a 2D view of a second stored 3D model associated with the same object or a different object from the received data based on a statistical analysis of the one or more selected values ​​for the view parameter, wherein the first stored 3D model is determined to be associated with the second stored 3D model; generating a recommendation for a second electronic device to include the 2D view in a stored listing associated with the second stored 3D model; and A method comprising: (Item 9) 20. The method of claim 19, wherein the first stored 3D model is determined to be related to the second stored 3D model on the basis that the first stored 3D model and the second stored 3D model are associated with the same object. (Item 10) 2. The method of claim 1, wherein the first stored 3D model and the second stored 3D model are associated with different objects, and the first stored 3D model is determined to be related to the second stored 3D model on the basis that the different objects belong to the same category. (Item 11) generating a 2D image corresponding to the 2D view from the second stored 3D model; the recommendation includes the generated 2D image or includes an option to update the stored listing associated with the second stored 3D model with the generated 2D image. The method according to any of the above items, further comprising: (Item 12) data representing a plurality of selected values ​​for the view parameter of the first stored 3D model is received from a respective plurality of customer electronic devices; a desired 2D view of the second stored 3D model is determined from the received data based on a statistical analysis of the plurality of selected values ​​for the view parameter. A method according to any of the above items. (Item 13) causing the first electronic device to display the stored 3D model in a virtual reality environment; or causing the first electronic device to display the stored 3D model in an augmented reality environment. The method according to any of the above items, further comprising: (Item 14) 1. A system comprising: A processor in communication with the storage, the processor configured to execute instructions that cause the system to perform a method according to any of the preceding items. Including, the system. (Item 15) A computer program which, when executed by a computer, causes the computer to perform the steps of the method according to any of the preceding items. (Summary) A method and system for generating a 2D image based on a 3D model is disclosed. Three-dimensional (3D) model data associated with an offering product in an online store is sent to a first electronic device, and the 3D model data is generated from the stored 3D model. Data representing selected values ​​for view parameters of the stored 3D model is received from the first electronic device. A desired 2D view is determined for the stored 3D model from the received data. A recommendation is generated for a second electronic device to include the desired 2D view in a stored listing associated with the offering product. [Brief description of the drawings]

[0038] Reference will now be made, by way of example, to the accompanying drawings which illustrate exemplary embodiments of the present application.

[0039] [Figure 1] FIG. 1 is a block diagram of an example e-commerce platform in which the examples described herein may be implemented.

[0040] [Diagram 2] FIG. 2 is an exemplary administrator home page that may be accessed via the e-commerce platform of FIG.

[0041] [Diagram 3] FIG. 3 is another block diagram of the e-commerce platform of FIG. 1 showing some details regarding application development.

[0042] [Figure 4] FIG. 4 illustrates an example data flow that may occur when a purchase is made using the e-commerce platform of FIG.

[0043] [Diagram 5] FIG. 5 is a block diagram of an exemplary hardware configuration of an e-commerce platform.

[0044] [Figure 6] FIG. 6 is another block diagram of the e-commerce platform of FIG. 1 showing some details regarding processing 3D models.

[0045] [Figure 7] FIG. 7 illustrates an exemplary 3D model of a product that may be stored by the e-commerce platform of FIG.

[0046] [Figure 8] FIG. 8 shows an example 2D view rendered by the 3D model in FIG.

[0047] [Figure 9] FIG. 9 is a schematic diagram illustrating a 3D model positioned in a 3D coordinate system and an example 2D view generated based on a view point.

[0048] [Figure 10A] 10A, 10B and 10C each show another example 2D view rendered by the 3D model in FIG. [Figure 10B] 10A, 10B and 10C each show another example 2D view rendered by the 3D model in FIG. [Figure 10C] 10A, 10B and 10C each show another example 2D view rendered by the 3D model in FIG.

[0049] [Figure 11] FIG. 11 is a flowchart of an example method that may be implemented by the e-commerce platform of FIG. 1 to generate recommendations for 2D images based on a 3D model.

[0050] [Figure 12] FIG. 12 is a flowchart of an example method that may be implemented by the e-commerce platform of FIG. 1 to generate recommendations for 2D images based on a 3D model.

[0051] Like reference numbers may be used in different drawings to represent like components. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0052] Description of exemplary embodiments The present disclosure is described in the context of an e-commerce platform, as described below. However, it should be understood that the description is for illustrative purposes only and is not intended to be limiting. Moreover, it should be understood that the present disclosure may be implemented in other contexts and is not necessarily limited to implementation in an e-commerce platform.

[0053] Referring to Figure 1, an embodiment e-commerce platform 100 is shown for offering merchant products and services to customers. Although the disclosure contemplates use of the disclosed apparatus, systems and procedures to purchase products and services throughout, the description herein will refer to products or services for simplicity. All references to products throughout this disclosure should be understood to also refer to products and / or services, including physical products, digital content, tickets, subscriptions, services, etc., offered.

[0054] Although the disclosure contemplates that "merchants" and "customers" may be larger than individuals throughout, the description herein will generally refer to merchants and customers as such for simplicity. It should be understood that all references to merchants and customers throughout this disclosure may also be references to groups of individuals, companies, corporations, computing entities, and the like, and may represent commercial or non-commercial transactions of products. Additionally, although the disclosure refers to “merchants” and “customers” throughout and describes their roles as “merchants” and “customers,” it should be understood that the e-commerce platform 100 more generally supports users in an e-commerce environment, and all references to merchants and customers throughout this disclosure should be understood to also be references to users, such as a merchant-user (e.g., a seller, retailer, wholesaler, or provider of products), a customer-user (e.g., a product buyer, purchasing agent, or user), a prospective user (e.g., a user that is browsing and has not yet decided to purchase, a user that is evaluating the e-commerce platform 100 for potential use in marketing and selling products, etc.), a service provider user (e.g., a shipping provider 112, a financial provider, etc.), a company or corporate user (e.g., a company representative for purchasing, selling, or using products; a corporate user; a customer service or customer care agent, etc.), an information technology user, a computing entity user (e.g., a computing bot for purchasing, selling, or using products), etc.

[0055] The e-commerce platform 100 may provide a centralized system for providing merchants with online resources and facilities for managing their business. The facilities described herein may be deployed in part or in whole through merchants executing computer software, modules, program code, and / or instructions on one or more processors, which may be part of or external to the platform 100. Merchants may utilize the e-commerce platform 100 to manage commerce with customers, for example, through an online store 138, through channels 110, by implementing an e-commerce experience with customers through point-of-sale (POS) devices 152 at a physical location (e.g., a physical storefront or other location such as a kiosk, terminal, reader, printer, 3D printer, etc.), by managing their business through the e-commerce platform 100, by interacting with customers through communication facilities 129 of the e-commerce platform 100, or any combination thereof. A merchant may utilize the e-commerce platform 100 as a standalone commerce presence with customers, for example, through a physical store (e.g., a "brick-and-mortar" retail store), a merchant off-platform website 104 (e.g., a commerce Internet website or other Internet or Web property or asset supported by or representing the merchant that is separate from the e-commerce platform), or in conjunction with other merchant commerce facilities. However, even these "other" merchant commerce facilities may be incorporated into the e-commerce platform, e.g., a POS device 152 at the merchant's physical store is coupled to the e-commerce platform 100, and the merchant off-platform website 104 is tied to the e-commerce platform 100, e.g., through a "buy button" that links content from the merchant off-platform website 104 to the online store 138.

[0056] The online store 138 may represent a multi-tenant facility with multiple virtual storefronts 139. In various embodiments, a merchant may manage one or more storefronts 139 in the online store 138, for example, through a merchant device 102 (e.g., a computer, a laptop, a mobile computing device, etc.) and offer products to customers through several different channels 110 (e.g., the online store 138; a physical storefront through a POS device 152; an electronic marketplace through an electronic buy button integrated into a website or social media channel, on a social network, a social media page, a social media messaging system, etc.; etc.). After selling across the channels 110, merchants may manage their sales through the e-commerce platform 100. After selling in a physical store, in a pop-up store, through a wholesale store, over the phone, etc., merchants may manage their sales through the e-commerce platform 100. A merchant may employ, for example, all or any combination of maintaining a business through a physical storefront utilizing POS devices 152, maintaining a virtual storefront 139 through an online store 138, and utilizing communications facilities 129 to leverage customer interactions and analytics 132 to improve the probability of a sale. Throughout this disclosure, the terms online store 138 and storefront 139 may be used synonymously to refer to a merchant's online e-commerce offering presence through e-commerce platform 100, and online store 138 may refer to a multi-tenant collection of storefronts (e.g., for multiple merchants) supported by e-commerce platform 100 or an individual merchant's storefront (e.g., the merchant's online store).

[0057] In various embodiments, customers may interact through customer devices 150 (e.g., computers, laptops, mobile computing devices, etc.), POS devices 152 (e.g., retail devices, kiosks, automated checkout systems, etc.), or any other commerce interface devices known in the art. E-commerce platform 100 may enable merchants to communicate with customers through an online store 138, through POS devices 152 at a physical location (e.g., the merchant's storefront or other location), and facilitate commerce with customers through various features such as platform or standalone applications, dialogue via electronic communications, providing a system for communicating with customers, and facilitating merchant services for real or virtual outlets available to communicate and interact with customers.

[0058] In various embodiments, and as further described herein, e-commerce platform 100 may be implemented through a processing facility including a processor and memory that stores a set of instructions that, when executed, cause e-commerce platform 100 to perform e-commerce and support functions as described herein. The processing facility may be part of a server, client, network infrastructure, mobile computing platform, cloud computing platform, static computing platform, or other computing platform, and may provide electronic connectivity and communication between and among the electronic components of e-commerce platform 100, merchant devices 102, payment gateways 106, application development 108, channels 110, shipping providers 112, customer devices 150, POS devices 152, etc. E-commerce platform 100 may be implemented in software and delivery models, etc., as a cloud computing service, software as a service (SaaS), infrastructure as a service (IaaS), platform as a service (PaaS), desktop as a service (DaaS), management software as a service (MSaaS), mobile backend as a service (MBaaS), information technology management as a service (ITMaaS), etc., where the software is licensed on a subscription basis and centrally hosted (e.g., accessed by a user using a thin client via a web browser, accessed through a POS device, etc.). In various embodiments, elements of e-commerce platform 100 may be implemented to operate on various platforms and operating systems, such as iOS, Android, web, etc. (e.g., administrator 114 implemented in multiple instances for a given online store for iOS, Android, and web, each having similar functionality).In embodiments, features or applications of the platform may be implemented over a peer-to-peer network, such as between a customer device and a merchant device.

[0059] In some embodiments, the online store 138 may be provided to the customer device 150 through web pages provided by a server of the e-commerce platform 100. The server may receive a request for a web page from a browser or other application installed on the customer device 150, which connects to the server through an IP address, which is obtained by translating a domain name. In response, the server sends back the requested web page. The web page may be written in or include HyperText Markup Language (HTML), a template language, JavaScript, etc., or any combination thereof. For example, HTML is a computer language that describes static information for a web page, such as the web page's layout, format, and content. Website designers and developers may use the template language to build web pages that combine static content that is the same across multiple pages and dynamic content that changes from page to page. The template language may allow for the reuse of static elements that define the web page's layout while dynamically populating the page with data from the online store. The static elements may be written in HTML and the dynamic elements may be written in the template language. The template language elements in the file act as placeholders so that the code in the file is compiled and sent to the customer device 150, and the template language is replaced by data from the online store 138 when a theme is installed, etc. Templates and themes may take into account tags, objects and filters. The client device web browser (or other application) then renders the page accordingly.

[0060] In various embodiments, the online store 138 may be provided to customers by the e-commerce platform 100, where the customers can browse and purchase various available products (e.g., add them to a cart, purchase immediately through a buy button, etc.). The online store 138 may be provided to customers in a transparent manner without the customers necessarily knowing that it is provided through the e-commerce platform 100 (and not directly from the merchant). Merchants may use merchant-configurable domain names, customizable HTML themes, etc. to customize their online store 138. Merchants may customize the look and feel of their website through a theme system, where merchants can select and change the look and feel of their online store 138 by changing their theme while having the same original product and business data shown in the online store's product hierarchy. Themes may be further customized through a theme editor, which is a design interface that allows users to flexibly customize the design of their website. Themes may also be customized using theme-specific settings to change aspects such as specific colors, fonts, and pre-built layout schemes. The online store may implement a content management system for website content. Merchants may create blog posts or static pages, publish them to their online store 138 through blogs, articles, etc., and configure navigation menus. Merchants may upload images (e.g., about products), videos, content, data, etc. to the e-commerce platform 100 for storage by the system (e.g., as data 134), etc. In embodiments, the e-commerce platform 100 may provide functionality for resizing images, associating images with products, adding and associating text with images, adding images for new product variants, protecting images, etc.

[0061] As described herein, the e-commerce platform 100 may provide merchants with facilities to transact for products through several different channels 110 including an online store 138, over the telephone, and as described herein through a physical POS device 152. The e-commerce platform 100 may include business support services 116 associated with running an online business, such as providing domain services 118 associated with their online store, administrators 114, payment services 120 for facilitating transactions with customers, shipping services 122 for providing customer shipping options for purchased products, risk and assurance services 124 associated with product protection and liability, merchant billing services 146, etc. The services 116 may be provided through the e-commerce platform 100 or in association with external facilities, such as through a payment gateway 106 for payment processing, a shipping provider 112 for facilitating shipping of products, etc.

[0062] In various embodiments, the e-commerce platform 100 may provide integrated shipping services 122 (e.g., through the e-commerce platform shipping facilities or through a third-party shipping carrier) that provide merchants with, for example, real-time updates, tracking, automatic fee calculations, bulk order preparation, label printing, and the like.

[0063] 2 illustrates a non-limiting embodiment of an administrator 114 home page 170 that may show information about daily tasks, recent store activity, and next steps a merchant can take to build their business. In an embodiment, a merchant may log into the administrator 114 via a merchant device 102, such as from a desktop computer or mobile device, to manage aspects of their online store 138, such as viewing recent activity of the online store 138, updating the catalog of the online store 138, managing orders, recent visit activity, total order activity, etc. In an embodiment, a merchant may access different sections of the administrator 114, for example, by using a sidebar 172, as shown in FIG. 2. The administrator 114 sections may include various interfaces for accessing and managing core aspects of the merchant's business, including orders, products, customers, available reports, and discounts. The administrator 114 may also include interfaces for managing sales channels for the store, including the online store, mobile applications that allow customers to access the store (Mobile App), POS devices, and / or buy buttons. The administrator 114 may also include interfaces for managing applications (Apps) installed on the merchant's account, settings and accounts adapted to the merchant's online store 138. Merchants may use a search bar 174 to search for products, pages, or other information. Depending on the device 102 or software applications that the merchant uses, they may be enabled for different functionality through the administrator 114. For example, if a merchant logs into the administrator 114 from a browser, they may be able to manage all aspects of their online store 138.When a merchant logs in from their mobile device (e.g., via a mobile application), they may be able to view all or a subset of aspects of their online store 138, such as viewing recent activity in the online store 138, updating the online store 138 catalog, managing orders, etc.

[0064] More detailed information about commerce and visitors to the merchant's online store 138 may be viewed through acquisition reports or metrics, such as displaying a sales summary for the merchant's business overall, specific sales and engagement data for active sales channels, and the like. The reports may include acquisition reports, behavior reports, customer reports, finance reports, marketing reports, sales reports, customer reports, and the like. The merchant may be able to view sales data for different channels 110 from different time periods (e.g., days, weeks, months, etc.), such as by using the drop-down menus 176. An overview dashboard may be provided for merchants wanting a more detailed view of the store's sales and engagement data. An activity feed in the home metrics section may be provided to illustrate an overview of activity in the merchant's account. For example, by clicking a dashboard button titled "View All Recent Activity," the merchant may be able to see a longer feed of recent activity in their account. The home page may show notifications about the merchant's online store 138, such as based on account status, growth, recent customer activity, and the like. Notifications may be provided to help merchants navigate procedures such as, for example, capturing payments, marketing order fulfillment, archiving completed orders, and the like.

[0065] The e-commerce platform 100 may provide a communication facility 129 and associated merchant interface for providing electronic communications and marketing, utilizing, for example, an electronic messaging aggregation facility for collecting and analyzing communication interactions between merchants, customers, merchant devices 102, customer devices 150, POS devices 152, etc., to aggregate and analyze the communications to, for example, increase the likelihood of offering a sale of a product, etc. For example, a customer may have a question about a product, which may generate a dialogue between the customer and the merchant (or an automated processor-based agent representing the merchant), and the communication facility 129 may analyze the interaction to provide the merchant with an analysis on how to increase the likelihood of a sale. The e-commerce platform 100 may provide financial facilities 120 for secure financial transactions with customers, for example, through a secure card server environment. The e-commerce platform 100 may store credit card information in a Payment Card Industry Data (PCI) environment (e.g., card server) or the like to perform financial reconciliations, bill merchants, perform Automated Clearing House (ACH) transfers between the e-commerce platform 100's financial institution accounts and the merchant's backing accounts (e.g., when capital is used), and the like. These systems may have Sarbanes-Oxley Act (SOX) compliance and high levels of diligence required in their development and operation. The financial facilities 120 may also provide financial support to merchants, for example, through the provision of capital loans (e.g., loan funds, cash advances, etc.) and insurance. In addition, the e-commerce platform 100 may provide a set of marketing and partner services to manage the relationships between the e-commerce platform 100 and its partners. They may also connect and onboard new merchants to the e-commerce platform 100. These services may enable merchant growth by making it easier for merchants to transact across e-commerce platform 100. Through these services, merchants may be provided with auxiliary facilities via e-commerce platform 100.

[0066] In an embodiment, the online store 138 may support numerous independently operated storefronts for a variety of products and process large volumes of transaction data daily. The transaction data may include customer contact information, billing information, shipping information, information regarding product purchases, information regarding services rendered, and any other information associated with a business through the e-commerce platform 100. In an embodiment, the e-commerce platform 100 may store this data in the data facility 134. The transaction data may be processed to generate analytics 132, which may be provided to merchants or third party commerce entities, for example, to provide customer trends, marketing and sales insights, suggestions for sales improvement, evaluation of customer behavior, marketing and sales modeling, fraud trends, and the like, regarding online commerce, and provided through dashboard interfaces, reports, and the like. The e-commerce platform 100 may store information regarding business and merchant transactions, and the data facility 134 may have many means to enhance, contribute, refine, and extract data, and the collected data may enable improvements to aspects of the e-commerce platform 100 over time.

[0067] Referring again to FIG. 1 , in various embodiments, the e-commerce platform 100 may be configured with core commerce facilities 136 for content management, task automation, and data management to enable support and service (e.g., regarding products, inventory, customers, orders, collaboration, suppliers, reporting, finance, risk, and fraud, etc.) to multiple online stores 138, but may be extensible through applications 142 to enable a greater degree of flexibility and custom procedures required to accommodate an ever-growing variety of merchant storefronts 139, POS devices 152, products, and services. For example, the core commerce facilities 136 may be configured for flexibility and scalability through partitioning (e.g., sharing) of functionality and data by customer identifier, order identifier, storefront identifier, etc. The core commerce facilities 136 may accommodate store-specific business logic and web administrators. Online stores 138 may represent channels and may be embedded in the core commerce facilities 136, providing a set of support and debugging tools to support usage for merchants. The core commerce facilities 136 may provide centralized management of key data about the storefronts 139.

[0068] The core commerce facilities 136 include the base or "core" functionality of the e-commerce platform 100, and as such, may not qualify for inclusion of all functionality supporting the online store 138, as described herein. For example, functionality included in the core commerce facilities 136 may require: exceeding a core functionality threshold through which the functionality may be determined to be core to the commerce experience (e.g., common to most storefront activities across channels, administrator interfaces, merchant locations, industries, product types, etc.); being reusable across online stores 138 (e.g., functionality that can be reused / modified across core functionality); being limited to the context of a single storefront at a time (e.g., implementing the online store "isolation principle" - code should not interact with more than one online store 138 at a time, ensuring that online stores 138 cannot access each other's data); providing transaction workloads, etc. Since many desired features are provided directly by the core commerce facilities 136 or enabled through application programming interface (API) 140 connections to its extensions / applications 142, maintaining control over which functionality is implemented can allow the core commerce facilities 136 to remain responsive. If care is not taken to limit functionality in the core commerce facilities 136, responsiveness can be compromised, for example, through infrastructure degradation through a slow database or non-critical backend failure, through catastrophic infrastructure degradation with a data center going offline, etc., through the deployment of new code that takes longer to execute than expected, etc. To prevent or mitigate these situations, the core commerce facilities 136 can be configured to maintain responsiveness through configurations that utilize, for example, timeouts, queues, back pressure to prevent degradation, etc.

[0069] While isolating online store data is important to maintain data privacy between online stores 138 and merchants, there may also be reasons to collect and use cross-storefront data, such as with an order risk assessment system or platform payment facilities (both of which require information from multiple online stores 138 to operate successfully). In various embodiments, rather than violating the isolation principle, it may be preferred to move these components outside of the core commerce facilities 136 into their own infrastructure in the e-commerce platform 100. For example, data facilities 134 and analytics 132 may be located outside of the core commerce facilities 136.

[0070] In various embodiments, the e-commerce platform 100 may provide a platform payment facility 149, which is another example of a component that may be located externally to utilize data from the core commerce facility 136 but does not violate the isolation principle. The platform payment facility 149 may allow customers interacting with the online store 138 to have their payment information securely stored by the core commerce facility 136 so that they only need to enter it once. If the customer visits a different online store 138, even if they have not visited it before, the platform payment facility 149 may recall their information to enable faster and more accurate checkout. This may provide a cross-platform network effect, where the e-commerce platform 100 becomes more convenient for merchants as more merchants participate because, for example, more customers checkout more frequently due to the ease of use associated with customer purchases. To maximize this network effect, payment information for a given customer may be retrievable from a storefront checkout station, allowing the information to be available globally across the online stores 138. It would be difficult and error-prone for each online store 138 to be able to connect with any other online store 138 and directly retrieve payment information stored therein. As a result, the platform payment facility 149 may be implemented outside of the core commerce facility 136.

[0071] For functionality not included in the core commerce facilities 136, applications 142 provide a way to add features to the e-commerce platform 100. Applications 142 may be able to access and modify data in a merchant's online store 138, perform tasks through the administrator 114, create new flows for merchants through a user interface (e.g., surfaced through extensions / APIs 140), etc. Merchants may be enabled to discover and install applications 142 through application search 208 and application recommendations 210 (see FIG. 3). In various embodiments, the core product, core extension points, applications, and administrator 114 may be developed to work together. For example, application extension points may be built into the administrator 114 so that core features can be extended by applications 142 that can deliver functionality to merchants through extensions / APIs 140.

[0072] In various embodiments, the application 142 may deliver functionality to the merchant through the extensions / API 140, for example, the application 142 may surface transaction data to the merchant (e.g., app: "Surface my application in mobile and web admin using the embedded app SDK.") and / or the core commerce facilities 136 may ask the application to perform an action upon request (e.g., core: "App, give me the local tax calculation for this charge.").

[0073] Applications 142 may support storefronts 139 and channels 110, provide support to merchants, integrate with other services, etc. Whereas core commerce facilities 136 may provide a foundation of services to storefronts 139, applications 142 may provide a way for merchants to meet specific and sometimes unique needs. Different merchants have different needs and therefore may benefit from different applications 142. Applications 142 may be discoverable through e-commerce platform 100, such as through the development of application taxonomies (categories) that allow applications to be tagged according to the type of function they perform for a merchant; through application data services that support search, ranking and recommendation models; through application discovery interfaces such as an application store, home information cards, application settings pages, etc.

[0074] Applications 142 may be connected to the core commerce facilities 136 through extension / API layer 140, for example, utilizing APIs to expose the functionality and data available through and within the core commerce facilities 136 to the application's functionality (e.g., through REST, GraphQL, etc.). For example, e-commerce platform 100 may provide API interfaces to merchant and partner products and services including, for example, application extensions, process flow services, developer resources, etc. With customers using mobile devices more frequently for shopping, applications 142 related to mobile usage may benefit from more extensive use of APIs to support growing associated commerce traffic. The flexibility provided through the use of applications and APIs (e.g., as provided for application development) allows e-commerce platform 100 to better adapt to new and unique needs of merchants (and internal developers through internal APIs) without requiring constant changes to the core commerce facilities 13, thereby providing merchants with what they need, when they need it. For example, the shipping service 122 may be integrated with the commerce facility 136 through a shipping or carrier services API, thereby enabling the e-commerce platform 100 to provide shipping service functionality without directly affecting the code running within the core commerce facility 136.

[0075] Many merchant problems, such as problems associated with back-office operations (merchant-facing applications) and problems in the storefront (customer-facing applications), can be solved by having partners improve and extend the merchant workflow through application development. As part of doing business, many merchants use mobile and web-related applications every day for back-office tasks (e.g., merchandising, inventory, discounts, fulfillment, etc.) and storefront tasks (e.g., applications related to their online shops, for flash sales, new product offerings, etc.), and the applications 142, through extensions / APIs 140, help to easily view and purchase products in a fast-growing market. In various embodiments, a software development kit (SDK) can be provided for partners, application developers, internal application facilities, etc., through creating a frame that sandboxes the application interface within the administrator 114, for example. In various embodiments, the administrator 114 may have no control or knowledge regarding what happens within the frame. The SDK may be used in conjunction with a user interface kit, for example, to create an interface that mimics the look and feel of the e-commerce platform 100 that acts as an extension of the core commerce facilities 136 .

[0076] Applications 142 utilizing the API may pull data on demand, but they also often need to have data pushed to them as updates occur. Update events may be implemented in a subscription model, such as for customer creations, product changes, or order cancellations. Update events may provide needed updates to merchants regarding the changed state of core commerce facilities 136, for example, to synchronize local databases, notify external integration partners, etc. Update events may enable this functionality without having to constantly poll core commerce facilities 136 to check for updates, for example, through update event subscriptions. In various embodiments, when a change occurs related to an update event subscription, core commerce facilities 136 may post a request to a predefined callback URL, etc. The body of this request may include the new state of the object and a description of the action or event. Update event subscriptions may be created manually in the administrator facility 114 or automatically (e.g., via an API). In various embodiments, update events may be queued and processed asynchronously from the state change that caused them, generating update event notifications that are not accounted for in real time.

[0077] Reference is now made to FIG. 3, which is another diagram of the e-commerce platform 100. FIG. 3 omits some of the details described with reference to FIG. 1 and provides further details that are described below. In various embodiments, the e-commerce platform 100 may provide application development support 128. The application development support 128 may include developer products and tools 202 to aid in the development of applications, an application dashboard 204 (e.g., to provide a development interface to developers, to administrators for managing applications, to merchants for customizing applications, etc.), facilities for installing and providing permissions 206 for providing access to applications 142 (e.g., for public access, such as where criteria must be met before being installed, or for private use by merchants), an application search 208 to facilitate merchants searching for applications 142 that meet their needs for their online store 138, application recommendations 210 to provide merchants with suggestions on how they can improve the user experience through their online store 138, descriptions of core application capabilities 214 within the core commerce facilities 136, and the like. These support facilities may be utilized by application development 108 performed by any entity including merchants developing their own applications 142, third party developers developing applications 142 (e.g., contracted by a merchant, independently developed for provision to the public, contracted for use in connection with e-commerce platform 100, etc.), or applications being developed by internal human resources associated with e-commerce platform 100. In various embodiments, applications 142 may be assigned application identifiers (IDs) for purposes such as, for example, linking to applications (e.g., through an API), searching for applications, making application recommendations, etc.

[0078] The core commerce facilities 136 may include the base functionality of the e-commerce platform 100 and expose these functions to applications 142 through APIs. The APIs may allow different types of applications to be built through application development 108. The applications 142 may be able to satisfy many types of needs for merchants, but may be broadly categorized into three categories: customer-facing applications 216, merchant-facing applications 218, or integration applications 220. The customer-facing applications 216 may include online stores 138 or channels 110 where merchants can list products and have the products purchased (e.g., online stores, applications for flash sales (e.g., opportunistic sales opportunities from merchant products or third-party sources), mobile store applications, social media channels, applications for offering wholesale purchases, etc.). Merchant applications 218 may include applications that allow merchants to operate their online store 138 (e.g., through applications on a web or website or on a mobile device), run their business (e.g., through applications on a POS device 152), grow their business (e.g., through applications related to shipping (e.g., drop shipping), use of automated agents, use of process flow development and improvement), etc. Integration applications 220 may include applications that provide convenient integration with participating merchants in running their business, such as shipping providers 112 and payment gateways.

[0079] In various embodiments, application developers may use application proxies to retrieve data from external locations and display it on pages of the online store 138. The content of these proxy pages may be dynamic, updatable, etc. Application proxies may be useful for displaying image galleries, statistics, custom forms, and other types of dynamic content. The core application structure of the e-commerce platform 100 may allow an increasing number of merchant experiences to be built in applications 142 so that the core commerce facilities 136 can remain focused on the more commonly used business logic of commerce.

[0080] The e-commerce platform 100 provides an online shopping experience through a curated system architecture that enables merchants to connect with customers in a flexible and transparent manner. A typical customer experience can be better understood through an exemplary purchase workflow of an embodiment, where a customer browses a merchant's products in a channel 110, evaluates one or more products, for example, via an augmented reality application, adds products that they intend to purchase to their cart, proceeds to checkout, pays for the contents of their cart, and leads to the generation of an order to the merchant. The merchant can then view and fulfill (or cancel) the order. The products are then delivered to the customer. If the customers are not satisfied, they can return the products to the merchant.

[0081] In an exemplary embodiment, a customer may browse a merchant's products in a channel 110. A channel 110 is a place where a customer can view and purchase products. In various embodiments, a channel 110 may be modeled as an application 142 (a possible exception is an online store 138 that is integrated within the core commerce facility 136). A merchandising component may allow a merchant to describe what they want to sell and where to sell it. The association between a product and a channel may be modeled as a product exposure and accessed by the channel application, for example, via a product listing API. A product may have many options, such as size and color, and many variations that spread the available options out to a particular combination of all options, such as a tiny green variation or a large blue variation. A product may have at least one variation (e.g., a "default variation" is created for a product that has no options), and at least one variation may have a default product image for display. For ease of browsing and management, products may be categorized into collections, offering product identifiers (e.g., stock keeping units (SKUs)), etc. Collections of products may be built by manually categorizing products together (e.g., custom collections), building rule sets for automatic categorization (e.g., smart collections), etc. Products may be viewed as 2D images, 3D models or images, rotated view images, animated images, through virtual or augmented reality interfaces, etc.

[0082] In various embodiments, customers may add to their cart what they intend to purchase (in alternative embodiments, products may be purchased directly, for example, through a Buy Button as described herein). Customers may add product variations to a shopping cart. Shopping cart models may be channel specific. An online store 138 cart may be composed of multiple cart line items, with each cart line item tracking the quantity of a product variation. Merchants may use cart scripts to offer customers special promotions based on the contents of their cart. Because adding products to a cart does not indicate any commitment from the customer or merchant, and the expected lifespan of a cart may be in minutes (not days), carts may be persisted in a transient data store.

[0083] The customer then proceeds to checkout. The checkout component may implement web checkout as a customer-facing order creation procedure. A checkout API may be provided as a computer-facing order creation procedure used by some channel applications to create an order on behalf of the customer (e.g., for the point of sale). A checkout may be created from a cart and a record of the customer's information, such as email address, invoice, and shipping details. At checkout, the merchant commits to a price. If the customer enters contact information but does not proceed to pay, the e-commerce platform 100 may provide an opportunity to re-attract the customer (e.g., in an abandoned checkout feature). For these reasons, a checkout may have a much longer lifespan (hours or days) than a cart, and thus persist. Checkout may calculate taxes and shipping costs based on the customer's shipping address. Checkout may delegate the calculation of taxes to the tax component and the shipping costs to the delivery component. The pricing component may allow merchants to create discount codes (e.g., "secret" strings that apply new prices to items at the checkout when they enter the checkout). Discounts may be used by merchants to attract customers and gauge the performance of marketing campaigns. Discounts and other custom pricing systems may be implemented on the same platform piece, for example, through pricing rules (e.g., a set of prerequisites that, when met, indicate a set of entitlements). For example, prerequisites may be items such as "order subtotal is over $100" or "shipping cost is less than $10" and entitlements may be items such as "20% off entire order" or "$10 off products X, Y and Z".

[0084] The customer then pays for the contents of their cart, resulting in the creation of an order for the merchant. The channels 110 may move money, currency, or value stores (such as dollars or cryptocurrencies) to and from customers and merchants using the core commerce facilities 136. Communication with various payment providers (e.g., online payment systems, mobile payment systems, digital wallets, credit card gateways, etc.) may be implemented within the payment processing component. The actual interaction with the payment gateway 106 may be provided through a card server environment 148. In various embodiments, the payment gateway 106 may, for example, integrate with leading international credit card processors to accept international payments. The card server environment 148 may include card server applications, card sinks, hosted fields, etc. This environment may act as a secure gatekeeper for sensitive credit card information.

[0085] FIG. 4 illustrates, in a non-limiting example, a simplified sequence diagram of the interactions between the core commerce facility 136 and the card server environment 148 during a credit, prepaid, gift, or other card payment transaction at a Web Checkout.

[0086] In various embodiments, most of the procedure may be organized by a payment processing job. The core commerce facility 103 may support many other payment methods, for example, through an off-site payment gateway 106 (e.g., the customer is directed to another website), manual (e.g., cash), online payment methods (e.g., online payment systems, mobile payment systems, digital wallets, credit card gateways, etc.), gift cards, etc. At the end of the checkout procedure, an order is created. An order is a contract of sale between a merchant and a customer, where the merchant agrees to provide the goods and services listed in the order (e.g., order line items, shipping line items, etc.), and the customer agrees to provide payment (including taxes). This procedure may be modeled in the sales component. Channels 110 that do not rely on core commerce facility checkout may create orders using the order API. Once an order is created, an order confirmation notification may be sent to the customer and a purchase order notification may be sent to the merchant via the notification component. When initiating a payment processing job, inventory may be reserved to avoid overbooking (e.g., the merchant may control this behavior from the inventory policy of each variant). Inventory reservations may have a short time span (a few minutes) and may need to be very fast and scalable to support flash sales (e.g., discounts or promotions offered for a short period of time, such as to target impulse purchases). Reservations are released if payment fails. Once payment is successful and an order is created, the reservation is converted into a long-term inventory commitment assigned to a specific location. The inventory component may record where the variants were stocked and track the quantity of the variants for which inventory tracking has been enabled. It may separate product variants (a customer-facing concept that represents a template for product listings) from inventory items (a merchant-facing concept that represents an item whose quantity and location are managed). The inventory level component may track the quantity that is committed to an order or available for sale, coming in from the inventory movement component (e.g., from a distributor). The merchant may then view and fulfill (or cancel) the order.

[0087] 5 is a block diagram of an example hardware configuration of e-commerce platform 100. In this example, e-commerce platform 100 includes a core server 810, a data server 820, and an application server 830, each in communication with each other (e.g., via a wired connection and / or via a wireless Internet connection). Each of the servers 810, 820, and 830 includes a respective processing device 812, 822, 832 (each of which may be, for example, a microprocessor, a graphics processing unit, a digital signal processor, or other computing element), a respective memory 814, 824, 834 (each of which may be, for example, a random access memory (RAM), a read only memory (ROM), a hard disk, an optical disk, a subscriber identity module (SIM) card, a memory stick, a secure digital (SD) memory card, etc., and may include tangible or transient memory), and a respective communication interface 816, 826, 836 (each of which may include a transmitter, receiver, and / or transceiver for wired and / or wireless communication). The core server 810 may store instructions and perform operations related to the core capabilities of the e-commerce platform, such as providing the administrator 114, analytics 132, core commerce facilities 136, services 116, and / or financial facilities 130, among others. Data servers 820 may be used to implement data facilities 134, including reviews database 310, profile database 320, and keyword database 330, among others. Application servers 830 may store instructions and perform operations for applications 142, for example, storing instructions and data for applications 142 and for implementing application development support 128.

[0088] Merchants and customers using their respective devices 102, 150, 152 may access the e-commerce platform 100 via one or more networks 840 (e.g., wired and / or wireless networks including virtual private networks (VPNs), the Internet, etc.).

[0089] 5 illustrates an example hardware implementation of e-commerce platform 100, it should be understood that other implementations may be possible. For example, there may be a greater or fewer number of servers, e-commerce platform 100 may be implemented in a distributed manner, or at least some of memories 814, 824, 834 may be replaced with external or cloud-based storage, among other possible modifications.

[0090] Reference is now made to FIG. 6, which is another diagram of the e-commerce platform 100, in which further details are provided below. In particular, FIG. 6 illustrates some details of the data facility 134 and analysis facility 132 involved in generating 2D images based on 3D models associated with merchant offerings in an online store 138. For brevity, the following description refers to merchant products. However, it should be understood that the present disclosure may be applicable to merchant offerings in general, including services. For example, the 3D models and 2D images may relate to a service that involves a physical object, such as a car rental service (in which case the 3D models of the rental cars may relate).

[0091] The data facility 134 may store merchant product information for each product listed in the online store 138. In this example, the data facility 134 includes a product database 310 that includes data of one or more merchant products for one or more online stores 138, a 2D image database 320 that includes 2D image data of one or more merchant products for one or more online stores 138, and a 3D model database 330 that includes 3D models of one or more merchant products for one or more online stores 138. In some embodiments, the 3D models of the products may be stored as a collection of data about the 3D models, which may include a collection of points and other associated information in 3D space. In some embodiments, 3D models of products can be stored in common 3D file formats (e.g., GLTF, GLB, USDZ, STL, OBJ, FBX, COLLADA, 3DS, IGES, STEP and VRML / X3D) that can be read and rendered into 3D models via common 3D software such as Autodesk™, CAD™, SOLIDWORKS™, etc.

[0092] The online store 138 may list merchant products such as chairs; a listing for a chair may be stored as a data entry 315 in a product database 310. The data entry 315 for the chair in the product database 310 may have references (e.g., memory addresses) to one or more 2D images (e.g., see FIG. 7 ) stored in a 2D database 320 and references (e.g., memory addresses) to one or more 3D models (e.g., see FIG. 8 ) stored in a 3D database 330. In some embodiments, the product database 310 may include a 3D model database 330 and / or a 2D image database 320. In other embodiments, each of the databases 310, 320, 330 may be a separate database.

[0093] In some embodiments, the 3D model may be a virtual object in a database or other repository of virtual objects. In some embodiments, the virtual object may be created from a photo or video of the real object (e.g., using 2D to 3D conversion software), for example, created using a mobile or other device.

[0094] For each product in a stored listing of the online store 138, there may be a default image for the product among one or more 2D images stored in the 2D image database 320. In some embodiments, the default image may be the dominant image (e.g., the largest image on the product landing page) shown by default among multiple images for the product. In other embodiments, the default image may be the only image for the product shown by default. This default image may be important for driving sales of the product because it is often the first product image for a product listed in the online store 138 seen by a customer.

[0095] The analysis facility 132 in this example includes a 2D image generator 342, a virtual reality (VR) processor 344, and an augmented reality (AR) processor 346. Each of the VR processor 344 and the AR processor 346 may include hardware components, software, or any combination of the two. Each of the 2D image generator 342, the VR processor 344, and the AR processor 346 may be implemented as a separate submodule of the analysis facility 132. In some examples, the functions of one or more of the 2D image generator 342, the VR processor 344, and the AR processor 346 may be provided using a single submodule (instead of three separate submodules) or may be implemented as a general function of the analysis facility 132. As described further below, one or more of the 2D image generator 342, the VR processor 344, and the AR processor 346 may be implemented using a machine learning system.

[0096] It should be noted that the data facility 134 , the analytics facility 132 and the core commerce facility 136 may be implemented in separate hardware components but may be combined as part of a single entity e-commerce platform 100 .

[0097] When a customer browses products at the storefront 139 (e.g., as displayed on customer electronic device 150), the customer may view various images of the products, including, for example, 2D and 3D images. The customer may be able to view a 3D model of the product rendered based on the 3D model data of the product stored in 3D image database 330.

[0098] 7 shows an example 3D model 710 of a chair, an example product offered by a merchant through an online store. The 3D model 710 may be formed by at least a large number of points (which may be known collectively as a "point cloud") 715 in 3D space according to a Cartesian (e.g., XYZ) coordinate system with an origin (0,0,0) at the center of the model 710. The point cloud may be stored as 3D model data in the 3D image database 330. Each point P in the point cloud 715 may be represented by a specific coordinate (X p ,Y p ,Z p 7 only shows a group of points 715 and the lines formed thereby, the 3D model data for the product may also include other information such as color (which may include a color mesh, e.g., a triangular or quadrilateral mesh), texture, material type, transparency level, lighting, shadows, etc. An application on the customer electronic device 150, such as a browser or a specifically configured shopping application, may receive the 3D model data including the point cloud 715 and then render and display a 2D image 720 of the rendered 3D model on a display as shown in FIG.

[0099] Although a Cartesian coordinate system has been described in some embodiments, it should be understood that in other embodiments, one skilled in the art can also use spherical or cylindrical coordinate systems to construct and represent the 3D model.

[0100] 3D model data for the 3D model 710 may be provided by the e-commerce platform 100 to the customer's electronic device 150 to enable the customer to view the 3D model 710. When the 3D model 710 of the product is presented to the customer on a display screen of the electronic device 150, it may be rendered to show a 2D image 720 of the 3D model in a particular setting, as shown in FIG. 8. In some embodiments, the particular setting for rendering the 2D image may be based on a particular view point. The setting may include one or more view parameters, such as zoom level, image size, view point, view angle (also known as orientation), distance from origin, one or more visual characteristics (e.g., color, texture, lighting, etc.).

[0101] 9, there is shown a 3D model 905 (simplified as a rectangular box in dashed dotted lines) whose center coincides with the origin (0,0,0) of a 3D coordinate system 900. The coordinate system 900 has three axes, X, Y and Z. When the 3D model 905 is viewed from a particular observation position or "viewpoint" 910 (e.g., by a human or a real or virtual camera), the viewpoint is represented in the coordinate system 900 by coordinates (x v ,y v ,z v ) with the origin (0,0,0) and the view point (x v ,y v ,z v ) forms a view direction 920 having an angle 940 from the X-axis and an angle 950 from the XY plane. The 2D view plane 930 is aligned with the view point (x v ,y v ,z v920). The 2D view plane 930 may be used to generate a 2D image from the 3D model 905, for example, by projecting the 3D model 905 onto the 2D image plane 930. The 3D model 905 may have any number of rendered 2D images, each a projection of the 3D model 905 onto a respective view plane 930 determined by a respective view point 910 and a respective view direction 920.

[0102] The first time the electronic device 150 renders a 3D model using the 3D model data sent by the e-commerce platform 100, a default 2D view of the 3D model may be shown. The default 2D view may have, for example, a zoom level of 1.5, an image size of 1000 pixels by 1000 pixels, location coordinates (x v ,y v ,z v 7, the 3D model 710 may have multiple view parameters including a view point V at a given point in the 3D model 710, a view angle of (45°, 60°), i.e., 45 degrees from the X axis and 60 degrees from the XY plane, and a distance of 100 (units) from the origin measured between the origin and the view point. Additionally, for each point in the 3D model 710, separate color, texture, and lighting settings may be applied. Based on the view parameter values ​​at a particular setting, the electronic device 150 may render a particular 2D view 720 of the 3D model 710.

[0103] For example, FIG. 10A shows an exemplary 2D view 1010 that may be rendered by electronic device 150 based on a view of 3D model 710 at one viewpoint and zoom level (in this case, the default of zoom level 1); FIG. 10B shows another exemplary 2D view 1020 that may be rendered by electronic device 150 based on a view of 3D model 710 at another viewpoint and zoom level (in this case, zoom level 1.2); and FIG. 10C shows another exemplary 2D view 1030 that may be rendered by electronic device 150 based on a view of 3D model 710 at yet a different viewpoint and zoom level (in this case, zoom level 0.9).

[0104] As described above, while viewing the 3D model 720 of the product on the electronic device 150, the customer may manipulate the 3D model 720 to view the product from different perspectives (e.g., up, down, left, right, front, or back), at different view angles, at different view points, or zooming in or out at different levels. In various embodiments, the customer may manipulate the 3D model 720 through touchscreen motions and gestures if a touchscreen is enabled on the electronic device 150. For example, in the iPhone® OS, to change the current view point for viewing the 3D model to a different view point, the customer can: 1) Change the zoom level by double tapping the screen to zoom in or out on the 3D model view; 2) Changing the view point and / or view angle by placing one or two fingers on the screen and dragging them in the desired direction to rotate or pan the 3D model; or 3) Changing the zoom level by zooming in or out on the 3D model by pinching in or out on the view using a two-finger (e.g., thumb and index finger) gesture.

[0105] Other user gestures and maneuvers may be used to view and control the 3D model depending on the operating system and touch screen settings of the electronic device 150. In some cases, the customer's electronic device 150 may be a desktop computer, in which case a mouse and / or keyboard (or other input device) may be used to manipulate the 3D model. In some other cases, the customer may send voice commands to the electronic device 150 for manipulating the 3D model through speech recognition and processing software. In still other cases, the customer may send commands to the electronic device 150 for manipulating the 3D model through hand gestures or other body movements through body motion processing software. Regardless of the input means used by the customer to view and control the 3D model, the electronic device 150 may determine and store all view parameters and their specific values ​​associated with each view event of the 3D model. A view event may be defined as an event when the customer has been viewing the 3D model at a selected value for a given view parameter (e.g., a particular view point) for a minimum threshold dwell time while the value of the given view parameter remains unchanged. In some examples, the values ​​of all view parameters should remain unchanged for a minimum threshold dwell time in order for those values ​​to be selected for a view event. In other examples, only a subset of the view parameters may need to remain unchanged in order for that subset of values ​​to be selected for a view event. For example, if a particular view angle and zoom level remain unchanged for a minimum threshold dwell time even if the color, lighting, and texture of the 3D model are changed, the particular view angle and zoom level may be considered to be the selected values ​​for the view event, and the associated view angle and zoom level may be stored.The minimum threshold dwell time may be set to a default value (e.g., 3 or 5 seconds) and may be changed from time to time by e-commerce platform 100; for example, the minimum time for defining a view event may be adjusted by a machine learning engine configured to determine the most desired 2D views based on how 3D models are viewed and manipulated by a large number of customers in e-commerce platform 100. View events may be defined in other ways in addition to dwell time. For example, a view event may be a customer selecting an option to save or share a particular view of a 3D model.

[0106] When a customer browses product listings by an online store and manipulates a 3D model (e.g., presented in a browser or through a mobile application), the electronic device 150 may send one or more values ​​for a view parameter associated with each manipulation of the 3D model for one or more view events to the e-commerce platform 100. In addition, the e-commerce platform 100 may provide an option (e.g., through a browser or a mobile application) for the customer to change visual characteristics of the 3D model or a portion of the 3D model. For example, the customer may change the color, texture, lighting, and / or background color of the 3D model or a portion thereof. Each time a visual characteristic is changed, the corresponding view parameter has an updated value. If that updated value corresponds to a view event (e.g., the 3D model is viewed in the selected color for a time longer than a threshold dwell time), the value for the view parameter may be sent by the electronic device 150 to the e-commerce platform 100.

[0107] In some embodiments, the 3D model may have one or more animated portions. For example, the merchant product may be a chair with a seat that can move (e.g., rotate or swivel), and the corresponding 3D model of the chair may include an animated seat portion that is shown swivel. In these cases, for a 3D model with animated portions, the electronic device 150 may send to the e-commerce platform 100 one or more values ​​for view parameters associated with each manipulation of the animation in the 3D model for one or more view events. For example, the electronic device 150 may capture which zoom level and / or view point position a user of the electronic device 150 selects to pause an animation. For another example, the electronic device 150 may capture the duration of the pause when a user of the electronic device 150 pauses an animation. The duration of the pause may be used to define a dwell time that can be used to further determine a view event. In yet another example, electronic device 150 may record a playback point in the animation of the 3D model at which the user paused the animation, and various view parameters associated with the 3D model at this playback point, such as a particular zoom level, a particular view point, a particular still image of the animated portion of the 3D model, and the total number of times the user paused the animation at this playback point. All of these captured values ​​for one or more view parameters may be sent by electronic device 150 to e-commerce platform 100.

[0108] In some embodiments, the e-commerce platform 100 may provide an augmented reality (AR) application, such as the AR processor 346, to allow a customer to view various products as virtual objects in the customer environment. In particular, the e-commerce platform 100 may provide a user with an option to interact with the augmented reality application, allowing a customer user or a merchant user to select a desired item for viewing as a virtual object in one or more user-supplied images. For example, a customer may project a 3D model 710 onto a live view presented on the electronic device 150 by using a camera of the electronic device 150. The customer electronic device 150 may be any suitable device capable of augmented reality display, and may be a dedicated augmented reality device or may be a multi-purpose device. The electronic device 150 may be a smartphone, a tablet, or a specialized device such as "smart glasses" by Microsoft HoloLens™, among other possibilities. If the electronic device 150 is a smartphone or tablet with a touch screen, the user may also view and manipulate the 3D model 710 in a manner similar to that described above in a smartphone or tablet device without AR capabilities, and view parameters may be captured and stored in a similar manner.

[0109] In another example, a customer interested in a merchant product may be enabled to upload or share one or more images of the customer's environment, which may be a single image, a set of separate images, or a set of video images, as used throughout this example and disclosure. The one or more images may be recorded, uploaded from storage, or captured and shared in real time. As an example, the merchant product may be a vase. A customer interested in a vase may share one or more images of a set of shelves in the customer's living room using the camera of the customer's mobile computing device to capture one or more images of the set of shelves, or to capture video of the shelves from various viewpoints, and the video may be streamed in real time. An augmented reality application (e.g., provided by the AR processor 346) may operate to augment one or more customer-supplied images with a virtual object of the vase (generated from a stored 3D model), such that one or more augmented images may be created showing a 3D model of the vase on one of the shelves. The one or more augmented images may be created and displayed on the customer computing device (e.g., via a web browser or application interface). A customer or merchant, via their respective computing devices, may be able to provide control signals, such as touch screen input, mouse positioning, etc., to position or reposition the 3D model of the vase via, for example, a drag-and-drop action or other known operations. For example, the vase can be dragged and dropped into a position on an initially selected shelf and then repositioned and / or reoriented on the same or a different shelf or another surface.

[0110] In yet another example, a customer interested in a merchant product, such as a refrigerator, may be enabled to upload or share (perhaps in real time) one or more images of the customer's kitchen, and the augmented reality application may operate to provide the customer with a 3D model of a virtual refrigerator in the location of the existing refrigerator or in the space provided for the refrigerator. The augmented one or more images may be displayed on the customer's computing device and the merchant's computing device. The customer or merchant, via their respective computing devices, may be able to provide control signals, such as touch screen inputs, to manipulate and move the 3D model of the virtual refrigerator or various components of the virtual refrigerator, such as to ensure there are no obstacles to moving the refrigerator to a desired location, or to illustrate various features of the refrigerator by opening or closing various doors or drawers of the refrigerator.

[0111] Using such an augmented reality application, a customer may have control over which portion of the environment to provide as a background for the 3D model, as well as control over the desired location / orientation of the 3D model. Augmented reality applications may provide customers with new ways to evaluate and interact with various merchant products, and may further provide merchants with the ability to showcase various features of these products to drive appetite for these products, in part, by demonstrating the suitability of the products for a particular customer location.

[0112] The computing and communication components for the AR processor 346 can reside in a variety of locations, such as the customer device 150, the merchant device 102, a separate server, and / or the e-commerce platform 100, and the AR processor 346 can reside as part of the e-commerce platform 100 or externally. The AR processor 346 can include multiple application components that can be replicated in a variety of locations. The application components can include an interface module enabled to receive one or more customer images from a customer computing device, each of the one or more customer images illustrating a customer environment, receive a selection of a merchant item for display, and receive a positioning or repositioning signal corresponding to a desired location of a virtual object in the customer environment. The application component may include a computing module including a processing engine and storage for performing processing related to determining 3D features and 3D feature data by evaluating one or more customer-supplied images and other data, retrieving, creating and sizing virtual objects corresponding to selected items (such as merchant products), creating an augmented image, set of images or a video by overlaying virtual objects at selected or determined locations in one or more customer-supplied images (which may be provided from storage or may be provided in real-time, for example as a real-time video stream), and moving, repositioning, or orienting, reorienting, sizing or resizing virtual objects or component parts of virtual objects in one or more of the customer-supplied images. In some embodiments, the 3D feature data may include one or more of the camera position, camera orientation (including but not limited to rotation, angle, roll, gamma, yaw, alpha, pitch, beta, etc.), the location of any detected surfaces, objects or features, the size and orientation of those surfaces, objects or features, planes, metadata related to the AR, etc.

[0113] In some embodiments, the 3D feature data may be associated with an image or a series of images captured, for example, at a rate equal to the frame rate of a video (such as 60 frames per second). In some embodiments, an augmented reality of one or more images with virtual objects showing selected merchant products may be displayed on both the customer computing device and the merchant computing device (as well as other computing devices), and both the customer and the merchant (as well as others) may be enabled to control the movement, size and orientation of the virtual objects in one or more customer-supplied images. In this way, a 3D model of the customer environment is not required, and those portions of the customer environment are provided as desired by the customer, for example, via a camera on the customer computing device that captures one or more images of potential sites for merchant products. In some embodiments, a peer-to-peer architecture may be used. In embodiments, screen mirroring may be used such that a display on the customer computing device or other computing device is mirrored on the merchant computing device or another computing device.

[0114] In some embodiments, the customer may view the 3D model through a virtual reality (VR) interface provided by the VR processor 344. For example, the electronic device 150 may be a VR headset worn by the customer, such as an Oculus Rift™ headset, or the electronic device 150 may be a multi-purpose device (e.g., a smartphone or tablet) that may be modified (e.g., using an attachment) for VR applications. The VR headset may fully take over the customer's vision to present a virtual space provided by the e-commerce platform 100 (e.g., via the VR processor 344). For example, when wearing the VR headset, the customer may be surrounded by a virtual merchant store having multiple products for sale. The customer may select one product by voice command or hand gestures, and a 3D model of the selected product may be displayed in front of the customer within the boundaries of the virtual space. In some embodiments, the VR headset may be wirelessly connected to the e-commerce platform 100, and the virtual space may be provided by the e-commerce platform 100. A customer can walk around the 3D model to view the product and can manipulate the 3D model by voice commands (e.g., "Show me the top of the chair"), by gestures (e.g., using a sweep gesture to rotate the 3D model), by an input mechanism (e.g., using a button or joystick), or by other suitable means.

[0115] The 3D model is overlaid on a 3D coordinate system that may be invisible to the customer's eyes, with the center of the 3D model coinciding with the origin (0,0,0) of the coordinate system. Because VR headsets are typically worn around the user's line of sight, the position of the VR headset (e.g., the center of the VR headset) can be taken to be at or near the position of the viewport at any given time when a customer wearing the VR headset is looking at the 3D model. Because the position of the VR headset is continuously known and updated in real time, the 3D coordinates (x t ,y t ,zt ) are also known and updated in real-time or near real-time. When a customer physically walks around the 3D model, the VR headset may detect the customer's physical movement and send real-time data representative of the physical movement to the VR processor 344 of the e-commerce platform 100. The VR processor 344 may use the data representative of the physical movement to calculate a virtual physical distance of the customer wearing the VR device to the center of the 3D model at the origin (0,0,0). This virtual physical distance may be used to determine a zoom level to generate an appropriate view of the 3D model in real-time. For example, when a customer takes three steps back, the 3D model may be zoomed out to appear 20% smaller. In another example, when a user bends its head to view a product (or product details), the VR processor 344 may update appropriate view parameters such as the view point position, zoom level, image size, and virtual property changes (if any). In a VR environment, a view event may be defined based on a threshold dwell time, similar to that in a non-VR environment as described above.

[0116] The 2D image generator 342 (see FIG. 6 ) of the e-commerce platform 100 may be configured to generate one or more 2D images based on a given 3D model 710, in particular based on how the 3D model 710 is viewed and / or manipulated by one or more customers interacting with the 3D model 710, according to one or more example methods described below.

[0117] As illustrated in FIG. 11 , an example method 1100 implemented by the e-commerce platform 100 (e.g., using the 2D image generator 342, the VR processor 344, and / or the AR processor 346, as appropriate) for generating recommendations for desired 2D views based on a 3D model may include the following steps. In some embodiments, the e-commerce platform 100 may be configured to provide functionality via a graphic user interface (GUI) for a customer to interact with the 3D model 710. For example, a customer, while browsing the merchant online store 138 on the electronic device 150, may select a product image or icon that points to a 3D model associated with a particular merchant offering by clicking or tapping on the image or icon. In step 1101, which may be optional, the user selection may be processed by the e-commerce platform 100 as a user request to view a 3D model associated with the merchant offering (e.g., a merchant product).

[0118] In some embodiments, if and when a customer browses the merchant online store 138 via a mobile application, the mobile application may be configured to receive a set of device parameters necessary for rendering the 3D model from the electronic device 150. Similarly, if and when a customer browses the merchant online store 138 via a web browser, the web browser may be configured to receive a set of parameters necessary for rendering the 3D model from the electronic device 150. When a user requests a view of the 3D model, a set of device parameters may be sent to the e-commerce platform 100 as part of the user selection. The set of device parameters may include, for example, the version of the web browser, the availability and version of a suitable 3D model viewing application, software or plug-in (e.g., Flash™), RAM size, pixel size of the display screen (which may be obtained by dividing the length and width of the display screen by the total number of pixels), the model and version of the operating system (OS) of the electronic device 150, an input means (e.g., touch screen, touch pad, mouse), etc.

[0119] In step 1102, the e-commerce platform 100 may send 3D model data associated with the selected product to the first electronic device 150 (e.g., in the form of a point cloud or any suitable type of model data). In some embodiments, the 3D model data may be selected to fit the set of device parameters optionally sent to the e-commerce platform 100 in step 1101. For example, a stored 3D model corresponding to the selected merchant offering may be referenced from the 3D model database 330, and the 3D model data may be generated from the stored 3D model. The 3D model data may be stored in the 3D model database 330 in a conventional 3D model format. After the electronic device 150 receives the 3D model data, a virtual object corresponding to the 3D model data of the merchant product may be retrieved or generated in a known manner. The virtual object may be resized to fit the screen size of the electronic device 150 before being displayed on the screen.

[0120] In some embodiments, instead of electronic device 150, e-commerce platform 100 may also generate virtual objects corresponding to the 3D model data of the merchant product in a known manner, in which case e-commerce platform 100 may send the generated virtual objects directly to electronic device 150, for example via a web browser configured with JavaScript.

[0121] As mentioned above, step 1101 may be optional. If a user request for a 3D model associated with a merchant offering is not received by e-commerce platform 100, platform 100 may still send 3D model data associated with the merchant product to the first electronic device based on a triggering event. The triggering event may be, for example, clicking on a web link for a merchant offering shown on storefront 139 by electronic device 150; in this case, an explicit user request is not required for e-commerce platform 100 to send a 3D model associated with a merchant offering being selected for browsing.

[0122] In step 1104, e-commerce platform 100 may receive data representing selected values ​​for one or more view parameters of the stored 3D model from first electronic device 150. For example, e-commerce platform 100 may receive data representing values ​​corresponding to one or more view parameters of the 3D model captured in a single view event, such as values ​​for a view point position, zoom level, image size, view angle, orientation, distance from an origin of the 3D model, size, color, texture, level of detail, lighting, color boundaries, texture boundaries, and lighting boundaries of a virtual object generated based on the 3D model data. Other possibilities may exist. For example, values ​​may be selected for a zoom level of 1.5, an image size of 1000 pixels by 1000 pixels, location coordinates (x v ,y v ,z vThe view parameters may include a view point V at (45°, 60°), a view angle of (45°, 60°), i.e., 45° from the X-axis and 60° from the XY plane, a top view orientation, a virtual object size of 500 pixels by 500 pixels, and / or a distance of 100 (units) from the origin measured between the origin and the view point. A value for a view parameter may be determined based on values ​​of one or more other view parameters. For example, a view point position may determine one or more of the view angles and orientations. An image size may indirectly determine the size of the virtual object displayed at the image size. The view point position may also determine a zoom level. And the zoom level may determine the displayed level of detail of the 3D model. In some cases, there may be a maximum level of detail for the 3D model, and if the 3D model in the view event is zoomed beyond this maximum level of detail, the corresponding 2D view may not show the texture of the merchant product characteristics. Thus, in some embodiments, in the view event, the zoom level is limited by the maximum level of detail.

[0123] In some embodiments, the electronic device 150 may send all updated values ​​for all view parameters to the e-commerce platform 100 regardless of whether there has been a view event. In such cases, the e-commerce platform 100 may determine whether a value for a view parameter corresponds to a view event based on a period of time during which the value for the view parameter remains unchanged. The view parameter value corresponding to the view event may be used to identify a desired 2D view of the 3D model. As described above, in some embodiments, one or more values ​​for the view parameters may be considered to be selected values ​​if a customer spends a minimum amount of time (e.g., a threshold dwell time) viewing the 3D model without changing or modifying any of the view parameters. In other embodiments, one or more values ​​for the view parameters may be considered to be selected values ​​if a customer spends a minimum amount of time (e.g., a threshold dwell time) viewing the 3D model without changing or modifying the value of at least one view parameter, such as a view point position. The machine learning engine may be configured to learn optimal data selection criteria for sending data representing selected values ​​for one or more view parameters for the 3D model.

[0124] In some embodiments, the 3D model may be viewed and manipulated in a VR or AR environment, as described in detail above. The e-commerce platform 100 may include or interface with the VR or AR environment to capture view events and some or all values ​​for some or all view parameters within the VR or AR environment. For example, when a customer wearing a VR headset visits a virtual merchant store and views a virtual object of a chair generated from a stored 3D model, the customer's physical movements, including eye, head and arm movements, may be captured by the VR headset and transmitted to the e-commerce platform 100 to generate corresponding values ​​for one or more view parameters during one or more view events for the virtual object. In another example, in an augmented reality environment, when a customer views or manipulates a virtual object overlaid with a real-world environment captured by a camera of the electronic device 150, the electronic device 150 may be configured to detect and transmit some or all values ​​for some or all view parameters during one or more view events.

[0125] At step 1106, in some embodiments, e-commerce platform 100 may determine a desired 2D image of the stored 3D model from the received data. For example, the desired 2D image of the stored 3D model may be a 2D view determined based on values ​​selected for one or more view parameters in a single view event from a first electronic device 150. In other cases, the desired 2D view of the stored 3D model may be determined based on a set of values ​​selected for one or more view parameters collected from multiple view events across one or more electronic devices 150. The multiple view events may be performed by a single customer or by multiple customers.

[0126] For example, the received data may represent a plurality of selected values ​​for at least one view parameter of the stored 3D model received from a respective plurality of customer electronic devices, including the first electronic device 150. A desired 2D view of the stored 3D model may then be determined from the received data based, for example, on a statistical analysis of the plurality of selected values ​​for the view parameter. The statistical analysis may be performed by the e-commerce platform 100 (e.g., using the 2D image generator 342 or by a machine learning engine in cooperation with the 2D image generator 342). In some embodiments, the machine learning engine may be part of the 2D image generator 342.

[0127] In an exemplary embodiment, the 2D image generator 342 is configured to analyze a group of data (or simply "parameters") representing multiple values ​​for a view parameter, such as a view point parameter, to generate an optimal value for the view parameter for a desired 2D view of a stored 3D model. An exemplary value for the view parameter may be expressed as a position coordinate in a 3D coordinate system, e.g., [100, 150, 200]. For a view point parameter, [X D ,Y D ,Z D A plurality of view point values ​​may be collected from a plurality of view events and a statistical average may be taken from the plurality of view point values ​​to generate an optimal value in the form of a view point position coordinate [X D ,Y D ,Z D It can be appreciated that ] may be used to determine values ​​for additional view parameters such as view angle (e.g., 56 degrees from the X axis and 90 degrees from the ZY plane), zoom level and orientation.

[0128] In some embodiments, the 2D image generator 342 may generate optimal values ​​for the view parameters for the desired 2D view of the stored 3D model based on a weighted average approach. For example, each selected value for the desired view parameter may be assigned a weight proportional to the dwell time for that selected value.

[0129] In some embodiments, instead of using an average or weighted average based on multiple values ​​for a view parameter, a single view point value [X S ,Y S ,Z S ] may be selected.

[0130] The 3D model may be displayed in one of many common viewing orientations. The viewing orientation may be determined based on a particular view angle and a particular zoom level, and may be determined from a particular view point [X S ,Y S ,Z S

[0046] The visual orientation can be determined by the visual orientation (e.g., the visual orientation is a property of the viewpoint). The common visual orientation is defined as one of the most commonly displayed orientations for the product. For example, the common visual orientation can be a perspective view, a front view, a top view, a rear view, a left view, a right view, or a bottom view. In some embodiments, if a particular common visual orientation is the most commonly selected orientation based on a weighted average approach or another suitable method, the 2D image generator 342 can generate optimal values ​​for the view parameters for a desired 2D view of the stored 3D model based on the common visual orientation (e.g., a front view).

[0131] Other techniques for determining optimal values ​​of the view parameters may be used, including non-statistical techniques.

[0132] In some embodiments, the optimal value of the viewpoint for generating a desired 2D view of the 3D model may be associated with the product type of the virtual object rendered by the 3D model data. For example, if the virtual object is a chair, a common viewpoint selected by a potential customer may be a perspective view showing at least three sides (e.g., top, left and front) of the chair placed on a flat surface. Such characteristics may be taken into account by the 2D image generator 342 to remove outlier data from multiple customer electronic devices.

[0133] Another view parameter that may be used to generate a desired 2D view is the visual characteristics of any part of the virtual object generated based on the 3D model, such as color, texture, pattern, or lighting. The customer electronic devices 150 may send data indicating that a yellow or wool texture or cloth pattern is most frequently selected by customers when viewing a virtual object (e.g., a dress) rendered by a stored 3D model. These selected data may be stored for each visual characteristic and used to generate the most desired 2D image of the stored 3D model.

[0134] In some embodiments, to generate the determined desired 2D view of the merchant product, the e-commerce platform 100 may be configured to track and associate at least one customer attribute with one or more values ​​for one or more view parameters of the 3D model.

[0135] For example, the data received in step 1104 above may be associated with a customer profile or customer attributes. This customer information may be used to identify a cohort (e.g., demographic group, geographic group, age group, gender group, etc.) to which the customer belongs.

[0136] In some examples, using such information about customer attributes, a desired 2D view can be determined for a particular cohort of customers. The received data can be sorted based on different cohorts based on associated customer attributes, and in addition to or instead of determining a desired 2D view across all customers, a desired 2D view can be determined for each cohort. Such cohort or attribute specific information can be useful for better fitting of the 2D view to the customer.

[0137] In some embodiments, the 2D image ultimately generated based on the particular desired 2D view may be stored with metadata indicative of one or more cohorts identified based on information from a customer profile or attributes associated with the data received in step 1104. For example, the 2D image generated based on the desired 2D view may be stored with metadata indicating that the 2D image is for customers belonging to the cohort group "female," "ages 20-30," "urban dwellers," or any combination of two or more of the enumerated cohort groups. Thus, the 3D model of the merchant product may have multiple 2D images generated and stored, with at least some of the 2D images being dedicated to one or more cohort groups, according to the metadata.

[0138] In some examples, the e-commerce platform 100 may associate customer actions with one or more selected values ​​for one or more view parameters. The customer actions may be considered to be active, such as, for example, saving a product listing, adding a product listing to a "favorites" list, sharing a link to a product listing, adding a product to a virtual shopping cart, or purchasing a product (among other possibilities), or passive, such as, for example, leaving a product listing page, leaving an online store, removing a product from a virtual shopping cart, or abandoning a virtual shopping cart. The association may generate a data label or weight for each value for one or more view parameters for the 3D model, the data label or weight indicating whether a particular value may lead to more (fewer) views, more (fewer) sales, and more (fewer) abandoned sales. These data labels or weights may be used (e.g., using statistical methods or machine learning techniques) to determine a desired 2D view for a merchant product from the selected values ​​for one or more view parameters of the 3D model. In some instances, instead of associating a data label or weight with each selected view parameter value, values ​​associated with negative customer behavior may simply be removed from consideration.

[0139] In some embodiments, determining the desired 2D view based on data received from electronic device 150 may include determining and storing one or more optimal values ​​for one or more view parameters for the desired 2D view, as described above, and may not necessarily include generating a 2D image based on the one or more optimal values ​​for the one or more view parameters.

[0140] In step 1108, the e-commerce platform 100 may generate recommendations for a second electronic device (e.g., the merchant electronic device 102) including desired 2D views of the stored listings. The stored listings may be listings stored in the e-commerce platform 100 associated with a merchant product and / or an online store. More generally, for a merchant product that is available via an online store, the stored listings of the merchant product may also be considered listings associated with the online store. The stored listings may be listings that are part of a store profile that may be included in search results generated by a search engine, for example. It should be understood that the stored listings may be stored in the e-commerce platform 100 or outside of the e-commerce platform 100. For example, the stored listings may be stored locally on the merchant device 102 or may be stored on a third-party server.

[0141] For example, the recommendation may include one or more determined optimal values ​​for one or more view parameters for the desired 2D view. The recommendation may further include information indicating that the desired 2D view of the merchant's product was determined based on data collected during a period of time, based on data collected from a particular customer cohort, based on positive customer behavior, or a combination thereof. Such information may indicate to the merchant that including the desired 2D view in the listing is likely to result in more customer views, sales, or other positive results.

[0142] As explained above, the default 2D image shown in the listing for a merchant product may be important in at least encouraging customers to place an order and pay for the product. A 2D image generated based on a desired 2D view of a merchant product may bring greater foot traffic to an online store if the "default image" comes up as a search result in a search engine query. The same 2D image may also cause customers to spend more time viewing the product, place the product in a virtual shopping cart, and / or pay for the product to complete the transaction. Thus, recommendations are valuable to the merchant online store and can be sent to the merchant device in real-time or near real-time.

[0143] In some embodiments, the recommendation may include an option to update the stored listing with a 2D image generated (e.g., by the 2D image generator 342) based on the desired 2D view of the 3D model of the merchant product. This may be done regardless of whether the merchant online store 138 already has a 2D image or a default 2D image of the merchant product in the stored product listing. In some embodiments, the e-commerce platform 100 may generate the recommendation after determining that the desired 2D view does not exist in the stored listing for the merchant product. In this case, the recommendation may include a message indicating that the current merchant product does not have a 2D image corresponding to the desired 2D view, and an update to the stored listing may be recommended.

[0144] In some embodiments, the e-commerce platform 100 may generate a recommendation that includes multiple desired 2D views for a merchant product in a stored listing. As described above, the 3D model may lead to multiple desired 2D views, and optionally multiple generated 2D images, based on different cohort group traits. For example, based on a customer profile and / or customer information received while the customer is browsing a merchant product in an online store, the e-commerce platform 100 may recommend a particular desired 2D view and / or a corresponding 2D image to be displayed to the customer browsing the merchant product. In some cases, the e-commerce platform 100 may generate a single recommendation that includes different sub-recommendations for different customers browsing the online store, each sub-recommendation including a particular desired 2D view or linking to a particular stored 2D image for the merchant product based on one or more cohort groups for the target customer. The recommendations may be generated in response to aggregated data regarding one or more customers that have browsed a merchant product online.

[0145] In some embodiments, e-commerce platform 100 may generate multiple recommendations, each recommendation including a particular desired 2D view for a merchant product in a stored listing based on a particular cohort group trait of the customer. For example, each recommendation may include a particular desired 2D view or link to a particular stored 2D image for the merchant product based on a particular cohort group for the target customer (e.g., "female" or "20-30 years old"). Each recommendation may be generated in response to aggregated data about one or more customers who have browsed the merchant product online.

[0146] In some embodiments, the 2D image generator 342 generates a 2D image based on a desired 2D view, i.e., based on one or more optimal values ​​for one or more view parameters. Once a 2D image corresponding to a desired 2D view is generated, it may be stored in the 2D image database 320, and a reference (e.g., memory address) for the desired 2D view may be stored in a data entry 315 in the product database 310 for the corresponding merchant product. The 2D image may be stored in an appropriate format, such as JPG, PNG, or WEBP. In some embodiments, 2D images based on a desired 2D view may be generated and stored in more than one format, and each stored 2D image has a unique reference (e.g., memory address) in the 2D image database 320. The unique reference may be stored in a data entry 315 in the product database 310 for the corresponding merchant product. The stored 2D images may be retrieved at any time by the e-commerce platform 100 to display the merchant product.

[0147] In some embodiments, step 1108 may be optional, in which case the 2D image generator 342 generates a 2D image based on the desired 2D view without generating a recommendation for the desired 2D view. For example, the e-commerce platform 100 may be configured to automatically generate and store one or more corresponding 2D images for one or more merchant products based on the desired 2D view without having to generate a recommendation for a second electronic device (e.g., the merchant electronic device 102). This may be preconfigured by the merchant itself while setting up the stored listings for the merchant products or all stored listings in the online store in general. Once the 2D image corresponding to the desired 2D view is generated, it may be stored in the 2D image database 320, and a reference (e.g., memory address) for the desired 2D view may be stored in a data entry 315 in the product database 310 for the corresponding merchant product. In some embodiments, the e-commerce platform 100 may be configured to automatically upload the generated 2D images for the merchant products in the stored listings of the merchant products, either in real-time or via a batch process. In this manner, the e-commerce platform 100 does not need to wait for any command signal from the merchant product to generate, store or update the stored listing of the merchant product with the appropriate 2D image based on the desired 2D view. This feature can be turned on or off by a system administrator or the merchant in the store settings.

[0148] In some embodiments, the e-commerce platform 100 may generate and store multiple 2D images from the same 3D model based on a desired 2D view for a merchant product in a stored listing, either automatically or after receiving a command signal from a merchant device. For example, a merchant product may be available in various colors or various material types while belonging to the same product category. The e-commerce platform 100 may be configured to recognize that a desired 2D view for one product in a product category is applicable to other products (e.g., having the same 3D model) in the same category, and proceed to generate multiple 2D images, each of which is a corresponding 2D image for a particular product in the same product category. Each generated 2D image may be stored in the 2D image database 320, and each corresponding merchant product may be associated with a unique product ID or SKU, while a unique reference (e.g., memory address) for the 2D image may be stored in a data entry 315 in the product database 310 for the corresponding merchant product. In some cases, a group of multiple 2D images stored in the 2D image database 320 may be associated with a particular product category.

[0149] Next, as an optional step, the e-commerce platform 100 compares the generated 2D image with a current 2D image included in a stored listing for the merchant product (e.g., in an embodiment where the stored listing is stored in the e-commerce platform 100 or in an embodiment where the merchant has submitted a listing for comparison) to determine that the desired 2D view does not exist in the listing, and sends a recommendation to the merchant device 102 with a message that the desired 2D view does not exist in the stored listing for the merchant product. Machine vision techniques, such as image recognition, may be implemented as part of the e-commerce platform 100 to compare the 2D image based on the desired 2D view with one or more 2D images already in the stored listing.

[0150] After the merchant device 102 receives the recommendation, the merchant device 102 may receive a user command from the merchant to update a 2D image, such as a default 2D image, of the merchant product in a stored listing in the merchant store based on the recommendation. In some embodiments, after the e-commerce platform 100 receives the user command from the merchant device 102, the e-commerce platform 100 may automatically update a default 2D image of the merchant product associated with the stored listing. In some embodiments, the e-commerce platform 100 is configured to provide a user interface for the merchant to generate, review, and update the 2D image of the merchant product based on the recommendation.

[0151] After a stored listing for a merchant product has been updated with a 2D image generated based on the desired 2D view, the e-commerce platform 100 may cause the first electronic device 150 to display the updated 2D image as a default 2D image when a customer browses the stored listing using the electronic device 150.

[0152] Although method 1100 has been illustrated and described as a series of consecutive steps, in some examples steps 1101-1104 and steps 1106-1108 may occur at separate times and need not occur immediately in time. For example, e-commerce platform 100 may send 3D model data to and receive view data from multiple customer devices over a period of time. The received data may be analyzed at a future time (e.g., at regular intervals or when a minimum amount of view data has been received) to determine a desired 2D view and generate a recommendation. In some examples, the desired 2D view may be determined and stored. A recommendation of the desired 2D view may be generated at some time in the future, such as after receiving a request from a merchant device. Additionally, in some examples steps 1106-1108 may be performed repeatedly on the same set of received view data, but tailored to different customer attributes. This may allow, for example, the same set of view data to be analyzed to generate different recommended 2D views to target different customer cohorts.

[0153] FIG. 12 is a flowchart of an example method 1200 implemented by the e-commerce platform 100 to generate recommendations for a 2D view of a second 3D model based on how a first model was viewed by a customer. A desired 2D view may be determined from how the first 3D model was viewed, and a desired 2D view may be recommended for the second 3D model based on the association between the first 3D model and the second 3D model. For example, the first 3D model and the second 3D model may be associated with each other because they are both associated with the same merchant product. In another example, the first 3D model and the second 3D model may be associated with each other because they are associated with different products that belong to the same product category. For example, a desired 2D view determined for a particular chair may be used to generate recommendations to include similar 2D views in listings for other chairs.

[0154] In step 1202, e-commerce platform 100 sends 3D model data associated with the merchant product to first electronic device 150, where the 3D model data is generated from a first 3D model of the merchant product. In step 1204, e-commerce platform 100 receives data representing a selected value for at least one view parameter of the first 3D model of the merchant product from first electronic device 150. Steps 1202-1204 may be similar to steps 1102-1104 described above.

[0155] Optionally, in step 1206, e-commerce platform 100 may receive a second 3D model. The second 3D model may be another 3D model of the same merchant product as the first 3D model, e.g., the second 3D model may be generated based on different visual characteristics or updated product materials. The second 3D model may be associated with a variation of the same merchant offering as the first 3D model, for example. Alternatively, the second 3D model may be of a different merchant product from the same merchant or a different merchant.

[0156] In step 1208, e-commerce platform 100 determines a desired 2D view of the second 3D model of the merchant offering from the received data representing selected values ​​for view parameters of the first 3D model of the merchant product and recognizes that the first 3D model is related to the second 3D model (e.g., the first 3D model and the second 3D model are of the same merchant offering or are the same type of merchant offering). For example, both 3D models may be referenced by the same merchant offering in product database 310, or when the merchant offerings are different products, the respective 3D models may be referenced to belong to the same product category.

[0157] In some embodiments, a first stored 3D model may be determined to be related to a second stored 3D model on the basis that the first 3D model and the second 3D model are associated with the same merchant offering. For example, the merchant offering may be stored in a data entry in the product database 310, and the data entry may include a reference to the first 3D model and a reference to the second 3D model. The reference may be, for example, a respective memory address for the first 3D model and the second 3D model. In this case, the first 3D model is recognized as being related to the second 3D model and vice versa. In another example, each of the first 3D model and the second 3D model may be stored separately in a respective data entry in the 3D database 330. Each data entry in the 3D database 330 may include a product field that includes a value (e.g., a reference or memory address) that represents the merchant offering. If the value in the product field in a data entry in the 3D database for a first 3D model is the same as the value in the product field in a data entry in the 3D database for a second 3D model, then the two merchant offerings behind the two 3D models are either identical or variations of the same merchant offering, which means that the first 3D model and the second 3D model are related to each other.

[0158] In some embodiments, the first stored 3D model and the second stored 3D model may be associated with different merchant offerings, and the first stored 3D model may be determined to be related to the second stored 3D model on the basis that the different merchant offerings belong to the same category. For example, each stored listing of the different merchant offerings may be stored in a respective data entry in the product database 310, and each data entry may have a product field including a respective field value representing a product category for the merchant offering. If the value in the category field for the merchant offering for the first 3D model is the same as the value in the category field for the merchant offering for the second 3D model, then the merchant offerings are determined to be in the same category, and the first 3D model and the second 3D model are determined to be related to each other. For example, the first 3D model may be a dining table, and the second 3D model may be a coffee table.

[0159] In some embodiments, the first stored 3D model and the second stored 3D model may be associated with different merchant offerings (from the same or different merchants) each having a different product type, but still be considered to be associated with each other. For example, a pair of sunglasses from brand A may be associated with a pair of snow goggles from the same brand A. In this case, the association may be determined based on the two merchant offerings being associated with the same merchant or the same online store. In some embodiments, even if the merchant offerings are different products and from different brands, if the visual appearance of the two merchant offerings behind the two 3D models have high similarity to each other, the association may be determined based on a visual appearance similarity score, which may be calculated based on the 3D models themselves in a known manner (e.g., using machine vision techniques). In other words, regardless of their respective merchant offerings, the two 3D models may be determined to be associated with each other if and when they appear very similar from a visual perspective. The e-commerce platform 100 may be configured to perform a visual appearance comparison between the two 3D models to calculate a visual appearance similarity score; then, if the score exceeds a certain threshold, according to the steps described in this disclosure, the two 3D models may be determined to be related to each other, and a recommendation for a desired 2D view of one of the 3D models may be generated based on the other 3D model.

[0160] The desired 2D view may include one or more optimal values ​​for one or more view parameters (for the second 3D model) generated based on collected values ​​for corresponding view parameters associated with the first 3D model. For example, based on the view data for the first 3D model, optimal values ​​for one or more view parameters similar to those described above in step 1106 may be determined. Those optimal values ​​may then be applied to the second 3D model to determine a desired 2D view for the second 3D model. For example, when the merchant product is a chair, the first 3D model may be associated with a chair made of leather and the second 3D model may be associated with the same chair but made of linen. Because both chairs may be of the same size and construction, some or all of the selected values ​​for one or more view parameters (e.g., view point and / or zoom level) of the desired 2D view of the first 3D model may be applicable to the second 3D model. In another example, a first 3D model may be associated with a chair made for an adult and a second 3D model may be associated with a chair made for a child, but both chairs have the same construction and materials, the only difference being size. In this case, some of the selected values ​​for one or more view parameters (e.g., color) of the desired 2D view of the first 3D model may be applicable to the second 3D model, but the view point and zoom level may be adjusted based on the size difference between the two chairs.

[0161] In some embodiments, when the first 3D model and the second 3D model are of different merchant offerings but in the same product category, certain viewing parameters collected based on data from the first 3D model may be excluded from being used to generate recommendations for the second 3D model. For example, one or more visual characteristics, such as color and texture, may be excluded because they may be limited to the merchant offering associated with the first 3D model, while other viewing parameters, such as size and view point, may still be relevant to the merchant offering associated with the second 3D model. Other possibilities may exist.

[0162] In step 1210, e-commerce platform 100 generates recommendations for the second electronic device to include the desired 2D view in the stored listing, similar to the procedure described above with respect to Figure 11. The stored listing may be a listing associated with the merchant product represented by the second 2D model and / or an online store listing associated with the second 2D model.

[0163] In some embodiments, similar to step 1108 of FIG. 11, step 1210 may be optional, in which case the 2D image generator 342 may generate a 2D image for the second 3D model based on the desired 2D view without generating a recommendation for the desired 2D view. For example, the e-commerce platform 100 may be configured to automatically generate one or more corresponding 2D images for one or more merchant products based on the desired 2D view without having to generate a recommendation for the second electronic device (e.g., the merchant electronic device 102). This may be preconfigured by the merchant itself while setting up the stored listings for the merchant products or all stored listings in the online store in general. Once the 2D image corresponding to the desired 2D view is generated, it may be stored in the 2D image database 320, and a reference (e.g., a memory address) for the desired 2D view may be stored in a data entry 315 in the product database 310 for the corresponding merchant product. In some embodiments, e-commerce platform 100 may be configured to automatically upload generated 2D images for merchant products in stored listings of the merchant products, either in real-time or via a batch process. This feature may be turned on or off by a system administrator or by the merchant in the store settings.

[0164] In examples in which step 1206 is performed, steps 1208 and 1210 may be performed in response to receiving the second 3D model. For example, when the second 3D model is initially uploaded to e-commerce platform 100 (e.g., as part of the creation of a new product listing), recommendations for desired 2D views of the second 3D model may be generated.

[0165] In examples where step 1206 is omitted, steps 1208 and 1210 may be performed for a stored second 3D model (e.g., previously updated for an existing product listing). For example, steps 1208 and 1210 may be performed after receiving a request from a merchant device.

[0166] In some aspects, the merchant device 102 may be configured to implement a method for receiving recommendations for a desired 2D view of a 3D model associated with a merchant offering. As an optional step, the merchant device 102 may upload a 3D model for the merchant offering to the e-commerce platform 100 so that the 3D model can be used in a stored listing for the merchant offering in the online store 138. Alternatively, the merchant device 102 may request the e-commerce platform 100 to provide a 3D model for the merchant offering. Next, although this step is also optional, the merchant device 102 may upload or select a default 2D image for the stored listing for the merchant offering. Alternatively, and also optionally, the merchant device 102 may request the e-commerce platform 100 to provide a default 2D image for the merchant offering. The default 2D image may be a dominant image (e.g., the largest image on a product landing page) shown by default among multiple images for the merchant offering. In other embodiments, the default image may be the only image for the merchant offering shown by default. In some cases, the default 2D image may be a 2D image randomly generated by e-commerce platform 100 based on a 3D model without considering any customer feedback.

[0167] Next, as an optional step, the merchant device 102 may send a request for recommendations to the e-commerce platform 100 for desired 2D images from the 3D model associated with the merchant offering. The requested recommendation may include a link to the merchant offering associated with the 3D model or a link to the 3D model itself. The recommendation request may specify a data source for generating the recommendation, which may include data associated with the 3D model itself, data associated with other 3D models of the same variation of the same merchant offering, data associated with 3D models of other variations of the same merchant offering, and / or data associated with 3D models of other merchant offerings (from the same or different merchants) of the same or different product type. If the recommendation request does not specify any data source, a default setting may apply. The default setting may include, for example, only data associated with the 3D model or only data associated with the merchant offering of the 3D model.

[0168] The merchant device 102 may then receive a recommendation for a desired 2D view of the 3D model of the merchant offering. The recommendation may include one or more optimal values ​​for one or more view parameters for the desired 2D view and / or may include a 2D image corresponding to the desired 2D view. The recommendation may further include information indicating that the desired 2D view of the merchant offering was determined based on data collected during a period of time, based on data collected from a particular customer cohort, based on data collected from one or more variations and / or one or more merchant offerings, based on positive customer behavior, or a combination thereof. Such information may indicate to the merchant that including the desired 2D view (or the recommended 2D image) in the listing is likely to result in more customer views, sales, or other positive results.

[0169] Finally, the merchant device 102 may choose to accept or reject the recommendation for the desired 2D view of the 3D model of the merchant offering (and / or the recommended 2D image). In some cases, the recommendation may include an option to update the stored listing of the merchant offering with a 2D image generated based on the desired 2D view of the 3D model of the merchant product. The merchant device 102 may send a response indicating acceptance to updating the stored listing with a 2D image generated based on the view parameters in the recommendation.

[0170] In some embodiments, after e-commerce platform 100 receives a user command from merchant device 102 to update a stored listing of a merchant offering with a desired 2D view, e-commerce platform 100 may automatically update a default 2D image of the merchant product associated with the stored listing. In some embodiments, e-commerce platform 100 may be configured to present a user interface through a web browser or an application installed on merchant device 102 for the merchant to generate, review, and update the 2D image of the merchant product based on the recommendation.

[0171] After the stored listing for the merchant's product has been updated with a 2D image generated based on the desired 2D view, the e-commerce platform 100 may cause the first electronic device 150 to display the updated 2D image as a default 2D image when a customer browses the stored listing using the electronic device 150, as described above.

[0172] Although this disclosure describes methods and procedures with a particular order of steps, one or more steps of the methods and procedures may be omitted or modified, where appropriate. One or more steps may be performed in an order other than that described, where appropriate.

[0173] Although the present disclosure describes at least in part a method, it is described so that a person skilled in the art can understand that the present disclosure also relates to various components for implementing at least some of the aspects and features of the described method, as hardware components, software, or any combination of the two. Thus, the technical solution of the present disclosure can be implemented in the form of a software product. A suitable software product can be stored in a pre-recorded storage device or other similar non-volatile or non-transient computer-readable medium, including, for example, a DVD, a CD-ROM, a USB flash disk, a removable hard disk, or other storage medium. The software product includes instructions tangibly stored in the software product that enable a processing device (e.g., a personal computer, a server, or a network device) to execute the method examples disclosed herein.

[0174] The present disclosure may be implemented in other specific forms without departing from the spirit of the claims. The described exemplary embodiments should be considered in all respects as merely illustrative and not restrictive. Selected features from one or more of the above-described embodiments may be combined to create alternative embodiments not expressly described, and features suitable for such combinations are understood to be within the scope of the present disclosure.

[0175] All values ​​and subranges within the disclosed ranges are also disclosed. Also, while the systems, devices and procedures disclosed and illustrated herein may comprise a particular number of elements / components, the systems, devices and assemblies can be modified to include additional or fewer such elements / components. For example, while any of the disclosed elements / components may be referred to as a single entity, the embodiments disclosed herein can be modified to include a plurality of such elements / components. The subject matter described herein is intended to encompass and incorporate all suitable modifications in technology.

[0176] All referenced documents are incorporated herein by reference in their entirety.

Claims

1. A system comprising a processor in communication with a storage, the processor comprising: Sending three-dimensional (3D) model data associated with products offered in the online store to a first electronic device, the 3D model data being generated from a stored 3D model; receiving, from the first electronic device, data representing a first selected value and a first dwell time associated with the first selected value for a view parameter of the stored 3D model, the view parameter being a setting for rendering a view of the stored 3D model; identifying a customer cohort associated with the received data, the customer cohort identified based on at least one customer attribute extracted from a profile associated with the first electronic device; storing the received data in a group of data associated with the customer cohort, the group of data representing a plurality of stored selected values, and associated dwell times for the view parameter collected from among a plurality of views of the stored 3D model by other members of the customer cohort; determining from the group of data a desired setting specific to the customer cohort for rendering a desired two-dimensional (2D) view of the stored 3D model for the customer cohort, the desired setting for rendering the desired 2D view being determined based on a weighted average of the stored selected values ​​for the view parameters weighted according to the associated dwell time; generating, from the stored 3D model, a 2D image corresponding to the desired 2D view included in a stored listing associated with the offered product in the online store, the generated 2D image indicating that the generated 2D image is appropriate for the customer cohort, the 2D image being stored in a 2D image database at a unique memory address; 23. A system configured to execute instructions to cause a

2. The system of claim 1 , wherein the 2D image is generated after determining that the desired 2D view does not exist in stored listings for the offered product.

3. The instructions include: generating a recommendation for including the desired 2D view in the stored listing, the recommendation including an option to include the 2D image or update the stored listing with the 2D image, the recommendation indicating that the 2D image is reserved for the customer cohort; The system of claim 1 , further comprising:

4. The plurality of stored selected values ​​for the view parameter are Multiple selected zoom levels, a plurality of selected sizes of a virtual object generated based on the stored 3D model; or a plurality of selected visual characteristics of the virtual object; The system of claim 1 , comprising at least one of:

5. The system of claim 1 , wherein the data representing the first selected value for the view parameter is stored in the groups of data based on the first dwell time being at least a threshold dwell time.

6. The instructions include: sending the 3D model data to a plurality of other customer electronic devices associated with the customer cohort prior to sending the 3D model data to the first electronic device; receiving, from each of the plurality of other customer electronic devices, data representative of a respective one of the plurality of stored selected values ​​for the view parameter and the respective associated dwell time; storing the data received from the plurality of other customer electronic devices in said group of data; The system of claim 1 , further comprising: collecting the groups of data by:

7. The instructions include: causing the first electronic device to display the stored 3D model in a virtual reality environment. The system of claim 1 , further comprising:

8. The instructions include: causing the first electronic device to display the stored 3D model in an augmented reality environment. The system of claim 1 , further comprising:

9. 2. The system of claim 1, wherein the desired settings for rendering the desired 2D view are determined based on the weighted average of the stored selected values ​​for the view parameters instead of based on a most commonly occurring selected value for the view parameters.

10. A system comprising a processor in communication with a storage, the processor comprising: Sending three-dimensional (3D) model data associated with the offered product to a first electronic device, the 3D model data being generated from a first stored 3D model; receiving, from the first electronic device, data representing a first selected value and a first dwell time associated with the first selected value for a view parameter of the first stored 3D model; identifying a customer cohort associated with the received data, the customer cohort identified based on at least one customer attribute extracted from a profile associated with the first electronic device; storing the received data in a group of data associated with the customer cohort, the group of data representing a plurality of stored selected values, an associated dwell time for the view parameter of the first stored 3D model collected from among a plurality of views of the stored 3D model by other members of the customer cohort, the view parameter being a setting for rendering a view of the first stored 3D model; determining from the group of data a desired setting specific to the customer cohort for rendering a desired two-dimensional (2D) view of a second stored 3D model associated with the same or a different product offering for the customer cohort, the first stored 3D model being determined to be associated with the second stored 3D model, and the desired setting for rendering the desired 2D view being determined based on a weighted average of the stored selected values ​​for the view parameters weighted according to the associated dwell time; generating, from the second stored 3D model, a 2D image corresponding to the desired 2D view included in a stored listing associated with the second stored 3D model, the generated 2D image indicating that the generated 2D image is appropriate for the customer cohort, the 2D image being stored in a 2D image database at a unique memory address; 23. A system configured to execute instructions to cause a

11. 11. The system of claim 10, wherein the first stored 3D model is determined to be associated with the second stored 3D model on the basis that the first stored 3D model and the second stored 3D model are associated with the same product offering.

12. 11. The system of claim 10, wherein the first stored 3D model and the second stored 3D model are associated with different offerings, and the first stored 3D model is determined to be associated with the second stored 3D model on the basis that the different offerings belong to the same category.

13. The instructions include: generating a recommendation for including the desired 2D view in the stored listing associated with the second stored 3D model, the recommendation including an option to include the generated 2D image or update the stored listing associated with the second stored 3D model with the generated 2D image, the recommendation indicating that the 2D image is reserved for the customer cohort; The system of claim 10 , further comprising:

14. The instructions include: sending the 3D model data to a plurality of other customer electronic devices associated with the customer cohort prior to sending the 3D model data to the first electronic device; receiving, from each of the plurality of other customer electronic devices, data representative of a respective one of the plurality of stored selected values ​​for the view parameter and the respective associated dwell time; storing the data received from the plurality of other customer electronic devices in said group of data; The system of claim 10 , further comprising: collecting the groups of data by:

15. The instructions include: causing the first electronic device to display the stored 3D model in a virtual reality or an augmented reality environment. The system of claim 10 , further comprising:

16. 1. A method for generating recommendations for a 2D image based on a 3D model, the method comprising: Sending three-dimensional (3D) model data associated with products offered in the online store to a first electronic device, the 3D model data being generated from a stored 3D model; receiving, from the first electronic device, data representing a first selected value and a first dwell time associated with the first selected value for a view parameter of the stored 3D model, the view parameter being a setting for rendering a view of the stored 3D model; identifying a customer cohort associated with the received data, the customer cohort identified based on at least one customer attribute extracted from a profile associated with the first electronic device; storing the received data in a group of data associated with the customer cohort, the group of data representing a plurality of stored selected values, and associated dwell times for the view parameter collected from among a plurality of views of the stored 3D model by other members of the customer cohort; determining from the group of data a desired setting specific to the customer cohort for rendering a desired two-dimensional (2D) view of the stored 3D model for the customer cohort, the desired setting for rendering the desired 2D view being determined based on a weighted average of the stored selected values ​​for the view parameters weighted according to the associated dwell time; generating, from the stored 3D model, a 2D image corresponding to the desired 2D view included in a stored listing associated with the online store, the generated 2D image indicating that the generated 2D image is appropriate for the customer cohort, the 2D image being stored in a 2D image database at a unique memory address; A method comprising:

17. The method of claim 16 , wherein the 2D image is generated after determining that the desired 2D view does not exist in stored listings for the offered product.

18. 20. The method of claim 17, further comprising: comparing the generated 2D image with a current 2D image included in a listing for the offered product to determine that the desired 2D view does not exist in the stored listing.

19. 20. The method of claim 18, further comprising generating a recommendation for including the desired 2D view in the stored listing, the recommendation including an option to include the 2D image or update the stored listing with the 2D image, the recommendation indicating that the 2D image is reserved for the customer cohort.

20. The plurality of stored selected values ​​for the view parameter are Multiple selected zoom levels, a plurality of selected sizes of a virtual object generated based on the stored 3D model; or a plurality of selected visual characteristics of the virtual object; 17. The method of claim 16, comprising at least one of:

21. The method of claim 16 , wherein the data representing the first selected value for the view parameter is sorted in the groups of data based on the first dwell time being at least a threshold dwell time.

22. sending the 3D model data to a plurality of other customer electronic devices associated with the customer cohort prior to sending the 3D model data to the first electronic device; receiving, from each of the plurality of other customer electronic devices, data representative of a respective one of the plurality of stored selected values ​​for the view parameter and the respective associated dwell time; storing the data received from the plurality of other customer electronic devices in said group of data; The method of claim 16 , further comprising collecting the groups of data by:

23. The method of claim 16 , further comprising causing the first electronic device to display the stored 2D model in a virtual reality or an augmented reality environment.

Citation Information

Patent Citations

  • Content recommendation system, content recommendation method, and program

    JP2019061525A

  • Augmented reality e-commerce for home improvement

    US20170132841A1

  • Integration of 3D models

    US20180261001A1