Abstract: A method including training two sets of item embeddings for items in an item catalog and a set of user embeddings for users, using a triple embeddings model, with triplets. The triplets each can include a respective first user of the users, a respective first item from the item catalog, and a respective second item from the item catalog, in which the respective first user selected the respective first item and the respective second item in a respective same basket. The method also can include generating an approximate nearest neighbor index for the two sets of item embeddings. The method additionally can include receiving a basket including basket items selected by a user from the item catalog. The method further can include grouping the basket items of the basket into categories based on a respective item category of each of the basket items. The method additionally can include randomly sampling a respective anchor item from each of the categories.

Abstract: A catalog of physical items associated with a target user is accessed. At least a portion of the catalog is at least in part automatically generated based on a retention of one or more of the physical items provided to the target user. A machine learning model trained using outfit combination information gathered from other users is used to automatically determine for the target user, at least a portion of one or more recommended outfit combinations of a plurality of physical items among the physical items within the catalog. An indication of a selected one of the one or more recommended outfit combinations is provided to the target user.

Abstract: Embodiments are disclosed for facilitating Do-It-Yourself (DIY) repairs. In the context of a method, an example embodiment includes receiving, by an experience-based repair service (EBRS) host system, vehicle diagnostic information identifying one or more vehicle problems. This example embodiment of the method further includes evaluating the vehicle diagnostic information, generating, based on the evaluation of the vehicle diagnostic information, required part types and required tools for addressing the one or more vehicle problems, and generating, based on the evaluation of the vehicle diagnostic information, recommended part types for addressing the one or more vehicle problems. Finally, this example embodiment of the method further includes causing presentation of an interface facilitating purchase of required parts from each of the generated required part types, the required tools, and recommended parts from each of the generated recommended part types.

Abstract: A method for Simultaneously in one-step filling a Virtual Shopping Cart with many items from one or multiple resources at one time; all items of any type from all potential resources are embodied into a Customized List of All Items, which has been Simultaneously generated and sourced from all potential resources in one-step and then presented visually to the User in a unique format from which the User selects specific designated, approved and desired items, with distinction to the source, type or characteristics of those items; resulting in a Simultaneous one-step of moving all of the selected items into a single Virtual or Online Shopping Cart for purchase or acquisition; ordered and/or ordered and paid for then allocated for acquisition and fulfillment of all items Simultaneously from as many sources as necessary.

Abstract: A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of a method for providing an interactive virtual environment. The system may receive environmental data, and augment the environmental data by adding virtual environmental data. The system may then provide this virtual environment to two or more devices. The system can then receive user input, and modify the virtual environment in response to those inputs.

Abstract: A method for creating a customized virtual shopping experience may include receiving physical-world shopping data of a first user. The physical-world shopping data may be collected while the first user is physically present in a physical-world shopping environment. The method may also include configuring a virtual shopping environment based at least in part on the physical-world shopping data of the first user, and displaying to the first user the virtual shopping environment.

Abstract: Systems and methods for color coordination for scanned products are provided. A kiosk has a control module, an input device, a display device, and an optical code reader. The kiosk has access to a product/color database. The control module is configured to receive an identification code scanned by the optical code reader, determine a sample product associated with the identification code, determine at least one coordinating color for the sample product based on the product/color database, display a simulated environment including a sample room having at least one selectable surface, display on the display device the at least one coordinating color, receive with the input device a selected color, receive with the input device a selected surface from the sample room, display on the display device the simulated environment showing the sample room with the sample product and with the selected color on the selected surface of the sample room.

Abstract: Techniques are described for analyzing data regarding users and purchasable items, and providing user experiences to users regarding the buying, leasing, and/or selling of item(s), the history of item(s), and/or other services associated with the item(s). Data may be analyzed by a data engine that provides output to power multiple user experiences (e.g., user interfaces). Such user experiences may include providing a user with recommendation(s) of items that may be of interest to the user. Recommendations may be determined using one or more algorithms, such as a content-based, criteria-based, and/or collaborative algorithm. The recommendation(s) may be presented to the user through a search user interface.

Abstract: A store is described, including an ordering interface, a storage area, automated vehicles, and a central processing system. The ordering interface accepts selections of items for purchase from a shopper. The storage area, stocking items for sale, is separate from the area containing the ordering interface. The automated vehicles retrieve items from the storage area. The central processing system is configured to: check-in the shopper; assign an order fulfilment module to the shopper; receive selections of items from the ordering interface in real-time, as the shopper selects the items for purchase; send the selections to the order fulfilment module for retrieval in real-time; check-out the shopper when the shopper is finished selecting items; and arrange delivery of the completed order to the shopper. The order fulfilment module assigns automated vehicles to retrieve the items for purchase in real-time. A method for operating a store is also described.

Abstract: A multi-merchant portal that enables a user to access e-commerce stores is provided. Each e-commerce store has respective merchant categories browsable by the user at a customer device through the portal, each merchant category comprising products available for purchase from a respective merchant. In response to receiving a request from the customer device to switch access of the user browsing a selected merchant category of the first merchant in a first e-commerce store, to a second e-commerce store, the portal determines a system category corresponding to the selected merchant category using mapping data mapping merchant categories to system categories and then determines a destination merchant category of the second merchant in the second e-commerce store corresponding to the determined system category using mapping data mapping the system categories to the merchant categories. The portal switches user's access to the destination merchant category in the second e-commerce store.

Abstract: A system for ordering a new electronic device is provided with an application programming interface to receive notification of the availability of a new electronic device and to send a selection of a feature for that new electronic device. A database can be coupled to a server to store the selected feature and to store a priority status value assigned to the new electronic device when feature selections are made. The priority status value allows prioritized ordering of a new electronic device. Preferably, one or more new electronic devices are ordered within a pre-determined period after a pre-order opening date, all of which is performed on the application programming interface of an electronic device.

Abstract: Embodiments of the present disclosure are directed to, among other things, providing resource allocation advice, configuration recommendations, and/or migration advice regarding data storage, access, placement, and/or related web services. In some examples, a web service may utilize or otherwise control a client instance to control, access, or otherwise manage resources of a distributed system. Based at least in part on one or more resource usage checks and/or configuration checks, resource usage information and/or configuration information of an account utilizing a web service, and/or user preferences and/or settings, resource allocation advice, system configuration recommendations, and/or migration advice may be provided to a user of an account. Additionally, in some examples, one or more remediation operations may be performed automatically.

Abstract: Systems and methods for cognitive mobile wallet management are disclosed. In embodiments, a method comprises: obtaining, by a computing device, user contextual data; determining, by the computing device, a potential user purchase and an associated purchase category; and dynamically determining, by the computing device, a flexible spending rule for the purchase category based on one or more stored spending rules and the contextual data, wherein the flexible spending rule changes an amount of currency available to a user through the computing device.

Abstract: According to various exemplary embodiments, an electronic text message is received from a source telephone number, the electronic text message including content describing a product item. A seller of the product item is identified, based on the source telephone number, and the product item is identified, based on the content included in the electronic text message. Thereafter, a draft version of an item listing is automatically generated, where the item listing lists the product item as being for sale by the seller on a marketplace website.

Abstract: According to certain aspects of the disclosure, a computer-implemented method may be used for providing a vehicle recommendation based on user gestures. The method may include displaying at least one image of a vehicle to a user and receiving at least one gesture from the user performed on the at least one image of the vehicle. Additionally, the method may include assigning a value to the at least one gesture from the user and determining a feature of the vehicle based on the at least one gesture from the user. Additionally, the method may include receiving gesture information related to the at least one gesture and determining a vehicle preference of the user based on the value, the feature of the vehicle, and the gesture information. Additionally, the method may include identifying at least one available vehicle based on the vehicle preference of the user and displaying the at least one available vehicle to the user.

Abstract: Apparatus and associated methods relate to an online ordering/takeout system for customers to place orders with a variety of merchants, where a customer can let a merchant know that the customer is on their way, and in response, the status of the order is updated in a locker-tracking system. In an illustrative example, a customer device may allow for customers to communicate an in-transit status to the merchant. A merchant device may, for example, allow a customer to gain access to a locker that stores the customer's order. In response to milestone events, such as placing a food item in a locker or the customer indicating they are “on their way,” the system may update a status of the locker to reflect a current status of the locker/order. Some embodiments may advantageously provide confirmation to the merchant that the customer is in route to the merchant's location.

Abstract: Systems and methods for generating event templates for requested event types are described herein. In an embodiment, a server computer receives transactional data describing transactions between a plurality of computing devices. The server computer uses the transactional data to identify a plurality of instances of a particular event type by determining, for each instance, that a plurality of transactions associated with a particular computing device relate to an event of the particular event type. The server computer uses the transactional data related to the plurality of instances of the particular event type to determine a plurality of items for the particular event type. When the server computer receives a request from a client computing device to generate an event, the server computer generates and displays an event template which identifies the plurality of items.

Abstract: Methods, apparatus, computer applications, and systems are provided for enabling identification of content to be compiled into a shopping application at a user device. In one embodiment, a general layout for a number of content modules to be displayed and identifying information for content to be inserted are provided from a network server to a user device, the user device then calls the appropriate content and utilizes the layout to generate a page for display to the user natively. One specific variant, activity and profile data collected at the user device via a separate application may be stored at the network and used to select content by the server.

Abstract: A method is provided. The method includes receiving a device type identifier, network access data, and a user identifier that correspond to an order identifier from a terminal. An allocated device serial number corresponding to the order identifier is obtained, the device type identifier, the device serial number, the network access data being written into a customized controlled device. The customized controlled device that is identified by the allocated device serial number and the device type identifier is connected to. A device registration request is received from the terminal and, in response to receiving the device registration request, device registration is performed based on the device type identifier, the allocated device serial number, and the user identifier.

Abstract: A system and computer-readable storage medium perform a method of augmenting eCommerce with quasi in-person discovery facilitated by an eCommerce platform that: (i) presents, to a buyer on a buyer user interface (UI) provided by buyer user device(s), an eCommerce opportunity associated with a tangible object that is offered by a seller via a seller UI; (ii) provides an interactive control affordance on the buyer UI that enables the buyer to select for presentation another visual aspect of the tangible object that is provided by the seller UI; (iii) recognizes, by an augmented reality component of the buyer user device(s), a discovered attribute of the other visual aspect of the tangible object; (iv) accesses information related to the discovered attribute that is pertinent to the eCommerce opportunity; and (v) presents, to the buyer on the buyer user interface, an augmented reality informational item associated with the discovered attribute.