Examples of techniques for displaying an advertisement for a product of interest are disclosed. In one example implementation according to aspects of the present disclosure, a computer-implemented method includes identifying, by a processing device, a product of interest. The method further includes retrieving, by the processing device, information about the product of interest. The method further includes retrieving, by the processing device, an advertisement associated with the product of interest based at least in part on the information about the product of interest. The method further includes displaying, by the processing device, the advertisement associated with the product of interest.

A method for controlling a refrigerator performed by an artificial intelligence computing device may include photographing a food material stored inside of the refrigerator; comparing the photographed image with a preconfigured previous image, and transmitting storage information of the food material to a cloud according to a comparison result; learning the transmitted storage information of the food; determining a stock state of the food material based on the learned storage information of the food material; and determining whether to transmit relation information related to the food material depending on the determined stock state of the food material. One or more of the artificial intelligence computing device according to the present disclosure may be linked with an Artificial Intelligence module, a drone (Unmanned Aerial Vehicle, UAV), a robot, an Augmented Reality (AR) device, a virtual reality (VR) device, a device related to 5G service, and the like.

The present teaching relates to obtaining a model for identifying content matching a query. Training data are received which include queries, advertisements, and hyperlinks. A plurality of subwords are identified from each of the queries and a plurality of vectors for the plurality of subwords of each of the queries are obtained. Via a neural network, a vector for each of the queries is derived based on a plurality of vectors for the plurality of subwords of the query. A query/ads model is obtained via optimization with respect to an objective function, based on vectors associated with the plurality of subwords of each of the queries and vectors for the queries obtained from the neural network.

Described is a system for the placement of digital content items on a digital content item space for a point of care (POC) facility by identifying a display interface for a point of care (POC) facility, the display interface including a digital content item space to display a digital content item, identifying one or more digital content item providers for the digital content item space; accessing a selection of the one or more digital content item providers, and identifying a set of digital content item providers for the digital content item space based on the selection. The system then causes display of the digital content item on the display interface based on the identified set of digital content item providers.

In one embodiment, a computing system receives a first set of location updates sent by a first user. Each location update corresponds to a user visit to a particular place, and each location update is determined by a mobile client device of the corresponding user via a first or a second location method. The computing system receives a second set of location updates sent by a second user, sent via only the first location method. A place-visit factor for the second user is calculated based on the total number of unique places visited by the second user within a particular period of time, a first number of places visited by the first user determined from location updates sent via the first location method, and a second number of places visited by the first user determined from location updates sent via the second location method.

Portable devices include environmental sensors that generate metrics about the environment (e.g., accelerometers detecting impulses and vibration, and GPS receivers detecting position and velocity). Such devices often use environmental metrics to extract user input directed at the device by the user, and status information about the device and the environment. Presented herein are techniques for using environmental metrics to infer physical activities performed by the user while attached to the device. For example, jogging may be inferred from regular, strong impulses and typical jogging speed; walking may be inferred from regular, weak impulses and typical walking speed; and riding in a vehicle may be inferred from low-level vibrations and high speed (optionally identifying the type of vehicle ridden by the user). Based on these inferences, the device may automatically present applications and/or or adjust user interfaces suitable for the user's physical activity, rather than responsive to user input.

Provided is an information distribution apparatus which effectively distributes information such as advertisements. An advertisement distribution system predicts seat conditions such as a change in seat occupancy rate with time and distributes advertising information to prospective customers who can visit around the time when the seats are available. By offering more advantageous discount rates, coupons and the like to prospective customers with a short traveling time to a store in a case where seats are already available, it is possible to quickly occupy the seats and recover the seat occupancy rate in a short period of time. On the other hand, a disadvantageous offer is made to prospective customers who arrive after the time when empty seats are predicted since they do not contribute much to the recovery of the seat occupancy rate.

A media management system that handles a plurality of deals for a plurality of advertisers and a plurality of promotional campaigns, receives input and/or parameters for each of the plurality of deals that corresponds to an upfront inventory utilization type and commercial operator break (COB) inventory utilization type, of a plurality of inventory utilization types. Reserve inventory units for each of the plurality of promotional campaigns that corresponds to a promotion inventory utilization type of the plurality of inventory utilization types, are determined for a specified upcoming time-frame. Inventory units from a defined amount of inventory units are dynamically allocated among each inventory utilization types of the plurality of inventory utilization types to meet a plurality of defined parameters for the defined amount of inventory units for one or more specified durations until end of the specified upcoming time-frame.

In one aspect, a computing apparatus is configured to represent offer rules based on requirements for the detection of predefined types of events and actions scheduled to be performed in response to the detection of each occurrence of the events. The events are independent from each other in processing and are linked via prerequisite conditions to formulate the requirements of an offer campaign. The computing apparatus is configured to store data indicating the completion statuses of the events and process the events, including the scheduled actions, if any, in an atomic way. Thus, the offer rules can be changed on-the-fly during run time execution by the computing apparatus.

A computer system determines that an item has been selected for purchase by a user on a user device. In response to determining that the item has been selected for purchase, the computer system determines that the purchase of the item was not completed. In response to determining that the purchase of the item was not completed, the computer system analyzes activity associated with the user device, and based on the analyzed activity, predicts whether the user intended to complete the purchase. In response to predicting that the user intended to complete the purchase, the computer system causes a communication corresponding to the item to be presented to the user.