Abstract: In some embodiments, apparatuses and methods are provided herein useful for user engagement with a retailer. In some embodiments, a system includes an application including a set of computer program code configured to be executed by a mobile electronic device associated with a customer of the retailer. The application includes a first component and a second component. A first server includes a first control circuit and communicatively coupled to the application and configured to: communicate with the first component. A second server includes a second control circuit and communicatively coupled to the application and configured to: facilitate purchase of products for sale at an ecommerce website; and switch, upon an activation of the second component, control by the first server of a first user interface provided by the first component to control by the second server of the second user interface provided by the second component.

Abstract: A method can include determining a frame processing operation for one or more frames of an image from an electronic device, the one or more frames of the image corresponding to a body of a user; determining if the electronic device is in alignment; determining if the electronic device is in an environment that satisfies a light threshold; determining pre-selected joint points for the body of the user in the one or more frames of the image based on pre-selected joint landmarks defined in a configuration set; determining a face alignment of the user in the one or more frames of the image; determining hair of the user is properly positioned in the one or more frames of the image; determining enough skin of the user is visible in the one or more frames of the image; and in response to the one or more frames of the image being validated, capturing an image of the user with the pre-selected joint landmarks to enable items to be overlaid on the image of the user. Other embodiments are disclosed.

Abstract: Systems, methods, and machine readable media are provided for relabeling items. A computing device is communicatively coupled to a scanning device, a printing device, and an inventory system. The computing device identifies at least one of the items as missing an expected label type, the expected label indicating a location where the item should be stocked. The system scans the item via the scanning device, queries the inventory system to determine a location for the item. The system prints, via the printing device, a label indicating a location where the item should be stocked in the retail facility, applies the label to the item and sorts the item, via the sorting apparatus, to transport the item to one of the outlets based on the location indicated on the label.

Abstract: In some examples, a system may be configured to, implement a first set of operations that generate a first set of data characterizing an importance of the most recently added anchor item to the user. Further, the system may be configured to, implement a second set of operations that generate a second set of data characterizing a likelihood of an occurrence of a substitution rejection event associated with the user. That way, based on the first set of data and the second set of data, the system may be configured to generate output data, and implement a set of notification operations based on the output data.

Abstract: A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising: determining, using a predictive analysis, an estimated collection time to collect one or more items of an order; receiving a mobile check-in from an electronic device indicating that a pickup is en-route to pick-up the order from the store; tracking a location of the pickup; periodically determining an estimated travel time for the pickup to travel to the store from the location, as tracked; and transmitting instructions for the one or more employees of the store to begin collecting the one or more items of the order on a store interface Other embodiments are disclosed herein.

Abstract: Autonomous carriers or totes that include vacuum units are provided. As the totes move or are moved through a warehouse carrying products, they collect debris. The debris can be analyzed at the tote, and actions can be performed based upon the analysis.

Abstract: A delivery route planning system can include a computing device configured to obtain order delivery data that includes information characterizing delivery locations and delivery time windows associated with a first plurality of orders and to determine a delivery plan based on the order delivery data. The computing device can be further configured to identify recyclable time in the delivery time and to obtain supplemental order delivery data that includes information characterizing supplemental orders characterizing delivery locations and delivery time windows associated a second plurality of orders. The computing system can add one or more supplemental order deliveries from the second plurality of orders to the delivery plan based on the recyclable time, the supplemental order delivery data and at least one predetermined delivery constraint.

Abstract: Provided are a re-using e-commerce payment instruments for in-store purchasing systems and methods. A customer enters a check out and a transaction at the point of sale is started. The system receives a pairing request at a wallet processor from a customer mobile device operating a mobile application. This pairing request is created and sent in response to scanning of a code having a transaction identification. The system associates a customer payment profile with the transaction identification and sends associated information to the point of sale. The point of sale sends an amount of sale to authorize to the wallet processor after completing scanning of items. The system creates an authorization for payment and sending the authorization for payment to an authorizer. The transaction may then be completed by processing payment.

Abstract: A system comprising one or more processors and one or more non-transitory computer-readable media storing computing instructions that, when executed on the one or more processors, cause the one or more processors to perform operations comprising: training a visual similarity model to output one or more vector representations in a vector space; determining one or more nearest neighbors based on embeddings nearest to a respective embedding in the vector space for the item; ranking the one or more nearest neighbors for the item in an order; re-ranking the order of the one or more nearest neighbors of the item into a re-ranked order; inserting, into a display of the item, the one or more nearest neighbors of the item; and facilitating altering a graphical user interface (GUI) to convey the display of the item. Other embodiments are disclosed herein.

Abstract: A communication protocol provides for a smartphone transmitting location information to a control circuit and the control circuit then determining whether the smartphone is within a predetermined distance of a particular facility, and, when true, determining whether a temporal flag is active for the smartphone. If true, the control circuit does not respond to the smartphone. When the smartphone is within the predetermined distance of the particular facility and that temporal flag is not active, however, the control circuit transmits an in-app alert to the smartphone to provide the user with an opportunity to indicate whether the user will now take a particular action, or not. When the smartphone transmits a not-now message to the control circuit, the latter sets the aforementioned temporal flag.

Abstract: Systems, method and computer readable medium are provided for automated storage and retrieval. User authentication information is received via a user interface for a dynamic storage and retrieval device. The user identity is verified based upon the authentication information and previously stored authentication data. Order information is retrieved for an order associated with the user following the verifying of user identity, the order information indicating one or more locations for items associated with the order. Instructions are transmitted to initiate a physical opening of at least one of the dynamic storage and retrieval device and at least one static storage location to enable the user to retrieve at least one item of the order, the static storage location including a controller controlling a locking mechanism and communicatively coupled to the dynamic storage and retrieval device.

Abstract: In some embodiments, apparatuses and methods are provided herein useful for a retail facility to maintain information regarding product location, in part, from correlating a shopper's cart path and their purchased items with those of other shoppers. In some approaches, the methods and apparatuses may determine a cart path for a particular shopping cart by analyzing aisle markers captured by an image capturing device in the shopping cart, associate that cart path with the purchased items from that shopping cart, and compare the associated cart path and purchased items with similar information from other customers. In some examples, by comparing the associated cart paths and purchased items form a plurality of customers, an aisle location of one of the retail items is identified and the database of aisle locations and retail items may be updated accordingly.

Abstract: A method including a user who has brand affinities about a product brand or a product brand category. The method can include analyzing whether the user has brand affinities for the product brand or the brand category with two binary classification models that can include (a) a model one to determine an affinity to a particular product brand and (b) a model two to determine an affinity to a particular product brand category. The method also can include analyzing whether the user has affinities for a similar product brand or a similar product brand category by a model three neural network. The method can include displaying recommendations and the promotions for a product brand, a product brand category, a similar product brand, or a similar product brand category to the user. Other embodiments are disclosed.

Abstract: In some embodiments, apparatuses and methods are provided herein useful to processing online orders. In some embodiments, a system for processing online order comprises an order processing server configured to receive an online order including grocery items and transmit, to a control circuit, the online order, the control circuit configured to receive the online order, determine the grocery items included in the online order, determine a number of grocery items that require refrigeration and a number of grocery items that require freezing, determine a number of totes required for the online order, assign to the online order the number of totes required, transmit, to the totes, a command, wherein each of the number of totes is configured to receive, from the control circuit, the command, and in response to the receipt of the command, one of maintain its temperature, enter the refrigeration state, and enter the freezer state.

Abstract: Systems and methods for controlling electronic shelf labels are disclosed. Product data identifying at least one product and a price of the at least one product and layout data of a physical environment including locations of one or more shelves, a respective shelf location of the at least one product, and coordinates of a plurality of electronic shelf labels is received. Coordinates for a first electronic shelf label associated with the respective shelf location is determined. A first emitter of a plurality of emitters that is capable of communicating with the first electronic shelf label is determined and positioned to direct a signal to the coordinates of the first electronic shelf label to establish a link with only the first electronic shelf label. A portion of the product data is transmitted via the signal, which causes the first electronic shelf label to display the portion of the product data.

Abstract: Systems and methods including one or more processors and one or more non-transitory storage devices storing computing instructions configured to run on the one or more processors and cause the one or more processors to perform acts of: in response to receiving search queries at a search engine, storing search event data and ranking features in one or more databases; generating, using the search event data and the ranking features, a training dataset comprising training event samples; executing a hybrid labeling procedure that assigns labels to the training event samples based, at least in part, on individual engagement information associated with the training event samples; and training a personalized ranking model to rank search results using the training event samples and the labels. Other embodiments are disclosed herein.

Abstract: Systems and methods for automatically determining and providing digital advertisements with ensured relevancy to a search query are disclosed. In some embodiments, based on historical user session data, a query is determined to be a head query, torso query, or tail query. For each sponsored item, a relevance score is generated to represent a degree of relevancy between the sponsored item and the query, and it is determined whether the sponsored item is eligible to be recommended in response to the query based on: (a) comparing the relevance score to a first threshold when the query is a head or torso query, or (b) comparing the relevance score to a second threshold when the query is a tail query. Based on all sponsored items that are eligible to be recommended, a ranked list of recommended items is generated for display based on an auction mechanism.

Abstract: Examples provide an apparatus having a first accumulator that water received from a first supply line. A first conduit connects to the first accumulator and provides a second supply line from the first accumulator to a fixture. The second accumulator receives drainage water from the fixture. The second conduit connects to the second accumulator and includes a drainage line that directs the drainage water away from the second accumulator. A pump associated with the second accumulator assists with moving the drainage water out of the second accumulator through the drainage line.

Abstract: Systems and methods for generating dynamic interfaces using explore-exploit models is disclosed. A first interface including a first set of content modules selected from a set of candidate content modules is generated and feedback data representative of one or more interactions with the first interface is received. The feedback data includes positive feedback and negative feedback. A set of weights for each content module is generated by a contextual explore-exploit model based on the feedback data. A request for a second interface including a context is received and a set of ranked content modules is selected for the context based on the weights of each of the content modules in the set of candidate content modules. A second interface including a second set of content modules is generated. The second set of content modules includes a predetermined number of top ranked content modules in the set of ranked content modules.

Abstract: A system can receive a first set of data. The first set of data can include information indicating a first set of user sessions and for each of the first set of user sessions having an associated summary and a corresponding agent indicated intent. The system can also, based on the first set of data, determine a set of utterances and for each of the set of utterances a corresponding set of intents. Additionally, the system can receive a second set of data. The second set of data including information indicating a second set of user sessions and for each of the second set of user sessions having an associated determined utterance and corresponding interaction of a user. Moreover, the system can validate a corresponding intent of one or more utterances of the set of utterances, based on the second set of data.