Abstract: The present disclosure provides techniques for curating search results. A first request to look up an identifier for an item is received from a first user, and first tracking information corresponding to movements of the first user in a physical space is retrieved. At least one item associated with the first user while moving in the physical space is identified from the first tracking information. A first identifier of the at least one item is determined, and the first identifier is provide to the first user.

Abstract: A routing system of a call center determines a plurality of advisor clusters to be assigned to each of a plurality of lead records stored in a lead model database. The predictive machine learning model inputs lead model data and advisor model data into a clustering analysis. Various modeling data are extracted from source lead data, sales data, and advisor data, in which the advisor data has been flattened for modeling. The predictive machine learning model applies a combination of a clustering analysis, a cluster model, and an aggregate conversion model to lead model data and user model data. The clustering analysis utilizes unsupervised clustering and supervised clustering, and outputs a plurality of advisor clusters and sales conversion scores. The clustering analysis clusters each of the advisors into one of the plurality of advisor clusters based on degree of similarity of a clustering vector.

Abstract: The subject disclosure relates systems and methods for making upgrade recommendations, such as recommendations for version upgrades to a purchasable media-content item. A process of implementing the subject technology can include steps for authenticating a user associated, identifying affiliates of the user, wherein the affiliates are associated with the user via a social network or online gaming platform, receiving a user selection of a content item, and identifying an upgrade version of the content item, wherein the upgrade version is associated with a second version identifier and a second price indicator. In some aspects, the process can further include steps for providing a recommendation to the user, wherein the recommendation indicates the upgrade version of the content item and the second price indicator. Systems and machine-readable media are also provided.

Abstract: Examples described herein relate to apparatuses and methods of providing real-time notifications on affordability and advisability of purchasing goods or services using augmented reality. The method includes receiving, from AR device associated with a user, visual data representing a view through a viewing area of the AR device. The visual data comprises geolocation data indicating a geolocation of the AR device. The method includes identifying an image of an object included in the visual data. The method includes determining, based on the visual data, a product identifier associated with the object. The method includes determining an attempt by the user to purchase the object. The method includes generating, in response to determining the attempt, recommendation data based on the product identifier and an account associated with the user. The method includes sending the recommendation data to the AR device to cause the AR device to display the recommendation data to the user.

Abstract: Disclosed are systems, methods, and devices for managing a personal user inventory. In one embodiment, the method comprises retrieving a message associated with a user identifier, the message including a body content portion; identifying a parser associated with the message; parsing the body content portion using the parser to identify an item of merchandise present within the body content portion, wherein the item of merchandise is associated with an item identifier and a set of item details; associating the item of merchandise with the user identifier; and generating a display listing merchandise associated with the user identifier, wherein the listing of merchandise includes the item of merchandise.

Abstract: Systems and method for mapping the location of a product in a store make use of images of products on shelf modules to identify the location of a product. In one implementation, a central computer receives a first image from a camera showing a subset of electronic shelf modules in the store and an indicia displayed thereon. The indicia on a selected one of the subset associated with a particular product or product is subsequently changed. The central computer then receives a second image from the camera showing the changed indicia such that the first and second image can be compared to identify the location of the shelf module and/or product within the store. In another implementation, coordinates of a scanner within one image are utilized to outline borders corresponding to the positioning of products in another image to map the location of a product in a store.

Abstract: Techniques are disclosed for purchasing, accessing, consuming, and/or providing electronic content using an electronic bookshelf (eBookshelf) system. The eBookshelf system can be used by accessing a touchscreen-based user interface and/or local hardware controls and/or a remote control. A user's personal library of eBooks and/or any other electronic content can be displayed and/or aurally presented. In addition, the vast content of commercial retailers can also be displayed for browsing and purchase/rental. If the user identifies a content selection on the eBookshelf system that he/she wishes to consume, it can be readily transferred from the system to a personal content consuming device. Multiple eBookshelf systems can be attached to one another to extend the length and/or height of the eBookshelf. Accessing the eBookshelf system by a user ID allows multiple users to enjoy a personally customized version of the system.

Abstract: There are provided systems and methods for user specific data distribution of crowd-sourced data. A user may provide data indicative of an item the user may wish to purchase, for example, through browsing history, entry of the item to a transaction, or other information. A community of users associated with the user, which may include the user or other known or nearby users, may provide real-time data collected by their devices of information that may be relevant to purchase of the item. The information may be passively or actively collected by components of devices for their devices, and may be crowd-sourced so that the community of users may elect to release the information and receive rewards by virtue of their data sharing. The information may be processed to determine a recommendation for purchase, which may be output through a commonly used communication platform for the user.

Abstract: A computer-implemented method includes determining a set of target listings, retrieving a seed image associated with the seed listing, the seed listing is categorized within a first item category, and generating a seed item feature vector for the seed image using a convolutional neural network (CNN) trained with images of items. The method also includes identifying a plurality of feature vectors associated with the first item category, comparing the seed item feature vector to the plurality of feature vectors using a k-nearest neighbors (kNN) algorithm, and generating a set of nearest neighbor listings to the seed listing. The method further includes storing the set of nearest neighbor listings as associated with the seed listing, selecting one or more nearest neighbor listings from the set of nearest neighbors, and presenting the one or more nearest neighbor listings as a recommendation to a user of the online e-commerce system.

Abstract: A network node associated with a retail store receives digital images from customers who have initiated a customer transaction at a first location. The digital images are unique and are associated with the transaction. The transaction is then temporarily suspended. To resume the transaction, the customer provides information describing features of the previously provided digital image. The network node uses this information to locate the corresponding digital image, and thus, the corresponding suspended transaction, and to authenticate the customer to resume the transaction. Provided the customer is authenticated, the node resumes the suspended transaction.

Abstract: Provided are an information recommendation method and apparatus. According to historical data, an information recommendation apparatus identifies a pair of matching items so as to determine a cross-category relationship of items; the item cross-category relationship is used to construct item match contexts; an item context portrait and a user context portrait are used to sort the match contexts; the items in the match contexts are sorted according to the feedback behavior of the user concerning the items in the match contexts; the sorted match contexts are recommended to the user.

Abstract: An e-commerce service is configured to interface between merchants and vendors so that a merchant can purchase from vendors without having to communicate directly with the vendors. A recommendation service is also provided to provide recommendations to merchants regarding which of multiple available vendors to use for any given product. The recommendation service bases its recommendations on historical order data that has been archived by the e-commerce service, as well as on known or derived merchant properties. The recommendation service may also recommend rates at which an item should be ordered, based on ordering rates of other merchants.

Abstract: A sales person at a retail store which traditionally does not sell paint assists a consumer in selecting and purchasing a non-paint product and thereafter employs a computer terminal and display in conjunction with a website operated by a paint manufacturer to provide a paint color recommendation to the consumer. The sales person may thereafter respond to consumer selection of a particular paint color by employing an on-line electronic ordering tool to transmit a paint order to an order processing terminal located at a paint manufacturer facility. Thereafter, the paint manufacturer may proceed to process the order, perform tinting and shaking steps to formulate paint of the particular color, package the tinted paint, and cause the packaged paint to be shipped to the consumer.

Abstract: A method for providing information in an information management system that manages taste information regarding a user including an order record at a first restaurant and that associates the taste information with identification information for identifying the user. The method includes obtaining, from a terminal apparatus, the identification information and a store identifier indicating a second restaurant in a chain different from a chain to which the first restaurant belongs, arranging, on a basis of the taste information associated with the identification information and menu information regarding the second restaurant indicated by the store identifier, menu items included in the menu information in order according to the taste information, and transmitting menu information regarding the menu items arranged in the order to the terminal apparatus to display the menu information regarding the menu items arranged in the order on a display screen of the terminal apparatus.

Abstract: According to an example, a model is selected from models including an augmented buyer model based on probabilities of conceivable transitions, and each conceivable transition includes a multi-step transition between a first URL and a second URL via at least one intermediate URL of the website. A user is determined to likely be a buyer or a non-buyer based on interaction data and the selected model. The user is presented with an offer that encourages the user to buy from the website upon the determination that the user is a buyer.

Abstract: A system is provided for use in managing waste services performed by a service vehicle. The system may include a sensor configured to capture during completion of a waste service activity an image of waste set out for retrieval by the service vehicle, a portal, and a processor in communication with the sensor and the portal. The processor may be configured to execute instructions stored in memory to receive from a consumer via the portal at least one of a picture and a description of a desired item, to recognize an object in the image captured by the sensor, to make a determination regarding matching of the object with the desired item, and to selectively cause a notification to be displayed on the portal based on the determination.

Abstract: An online concierge shopping system identifies recipes to users to encourage them to include items from the recipes in orders. The online concierge system maintains user embeddings for users and recipe embeddings for recipes. For users who have not placed orders, recipes are recommended based on global user interactions with recipes. Users who have previously ordered items from recipes are suggested recipes selected based on a similarity of their user embedding to recipe embeddings. Users who have purchased items but not from recipes are compared to a set of similar users based on the user embeddings, and recipes with which users of the set of similar users interacted are used for identifying recipes to the users. A recipe graph may be maintained by the online concierge system to identify similarities between recipes for expanding candidate recipes to suggest to users.

Abstract: A method for evaluating bids for the purchase of inventory items to optimize bid-generated revenue. The method comprises receiving a bid for an inventory item, the bid comprising a bid price, a specific inventory item that is to be purchased, and a number of inventory items to be purchased. The bid is input into a machine learning algorithm as are features associated with the inventory item and information associated with the bid. The machine learning algorithm analyzes the bid and generates an output to accept or decline the bid. Responsive to that output the bidder is advised whether the bid was accepted or declined.

Abstract: A method begins with a server in a data communication system identifying an instance for a user computing device associated with an exchange item to utilize the exchange item for acquisition of a particular item, where the exchange item has a quantifiable value and the particular item has an acquisition value. The method continues by, for the instance, determining compliance with one or more rules of a set of exchange item rules, determining that the quantifiable value of the exchange item is less than the acquisition value of the particular item, determining an alternative exchange item utilization protocol to facilitate the acquisition of the particular item such that the quantifiable value of the exchange item is greater than or equal to the acquisition value, and when requested, executing the alternative exchange item utilization protocol to facilitate the acquisition of the particular item.

Abstract: The innovation disclosed and claimed herein, in one aspect thereof, comprises systems and methods for optimized communications based on a customer emotional state. In aspects of the system and method, a customer social media account is analyzed for past social media posts. Customer emotional states are determined for the past social media posts. The past social media posts are also associated with financial transactions made by the customer such that emotional states are linked to specific financial transactions. The system and method monitor the customer social media account for new social media posts. A new social media post can be detected. An emotional state can be determined for the new social media post. The system and method collect the financial transactions with the same emotional state. The system and method generate an offer for similar products and/or related to the financial transactions. The offer is communicated to the customer.