In the world of digital advertising, optimally allocating an advertisement campaign within a fixed pre-defined budget for an advertising duration aimed at maximizing number of conversions is very important for an advertiser. Embodiments of present disclosure provides a robust and easily generalizable method of optimal allocation of advertisement campaign by formulating it as a constrained Markov Decision Process (MDP) defined by agent state comprising user state and advertiser state, action space comprising a plurality of ad campaigns, state transition routine and a cumulative reward model which rewards maximum total conversions in an advertising duration. The cumulative reward model is trained in conjunction with a deep Q-network for solving the MDP to optimally allocate advertisement campaign for an advertising duration within a constrained budget.

Method and system for determining total carbon emissions of a first vehicle are disclosed. For example, the method includes determining a first amount of carbon emissions produced during a commissioning stage of the first vehicle, collecting driving data for one or more trips made by the first vehicle during an operating stage of the first vehicle, determining a second amount of carbon emissions produced during the operating stage of the first vehicle based at least in part upon the driving data, determining a third amount of carbon emissions produced during a decommissioning stage of the first vehicle, and determining the total amount of carbon emissions produced during a life cycle of the first vehicle based at least upon the first amount of carbon emissions, the second amount of carbon emissions, and the third amount of carbon emissions.

A computer implemented method for the automated analysis or use of data is implemented by a voice assistant. The method comprises the steps of: (a) storing in a memory a structured, machine-readable representation of data that conforms to a machine-readable language (‘machine representation’); the machine representation including representations of user speech or text input to a human/machine interface; and (b) automatically processing the machine representations to analyse the user speech or text input.

A system, method, and computer program product for implementing electronically generated promotion deployment is provided. The method includes receiving electronic data comprising shipment identification for a shipment of an item from a shipping client to a recipient. Specialized programmable software code is generated and a resulting profile is generated for the recipient. A visible promotional structure associated with a package comprising the shipment is generated and presented during delivery of the package. Generating the visible promotional structure may include generating a physical structure or a digital structure.

We describe offline links to online digital assets. The offline links can be in hardcopy text. A link can be in a format like [BBQ Ribs], where there is a starting delimiter (eg “[”) and a closing delimiter (“]”). We call this a “linket”. A user has a mobile device with a camera. She scans a linket in hardcopy she is reading. Her device converts this to digital form and sends to a server. The server maps the linket to an URL or other electronic data. The linket acts as a brand, akin to a domain name.

Computer-implemented systems and methods for privacy-safe user tracking. A plurality of tracking pools is provided, with each tracking pool having a plurality of users assigned to the pool. Each tracking pool further includes combined tracking data associated with the users in the pool. Tracking data associated with a user is received, and the user is assigned to at least one of the tracking pools. The received tracking data is added to the combined tracking data of the assigned tracking pool, such that no portion of the combined tracking data can be used to identify an individual user in the assigned tracking pool.

A server, method, and computer program product for implementing electronically generated promotion deployment is provided. Package shipments being shipped from a client to at least one recipient recipient are detected. A promotional placement request associated with promotions with respect to attributes of the at least one recipient is received within a data structure. Promotional attributes from the client with the at least one recipient are cross referenced with respect to the received promotional placement request. At least one visible promotional structure associated with the promotional attributes is electronically generated. The at least one visible promotional structure is deployed during a real time delivery process of at least one package to the at least one recipient.

A method and system for conducting an online payment transaction through a point of sale device. The method includes receiving input from a user selecting an item for purchase through the point of sale device; calculating a total purchase amount for the item in response to a request from the user to purchase the item; and sending payment authorization for the total purchase amount from the point of sale device to a payment entity, in which the payment authorization is sent to the payment entity via a mobile communication device of the user. The method further includes receiving a result of the payment authorization from the payment entity through the mobile communication device; and completing the payment transaction based on the result of the payment authorization.

An information processing apparatus includes a processor configured to specify, using information regarding a product selected as a purchase target by an in-store customer who visits a store and a movement flow line of the in-store customer in the store, a recommended product to be recommended to the in-store customer from among products displayed at a place not looked by the in-store customer in the store.

Machine Learning based ranking models are ubiquitous in powering recommendation engines at internet companies. These models typically use a combination of real-valued numerical and categorical features to generate predictions. Feature selection may be a widely encountered problem in this setting, that entails picking the optimal set of features as inputs to these models from a large pool of candidate real-valued and categorical features. A novel feature selection algorithm for categorical features building on stochastic neural networks is provided. It is shown empirically through results, the superiority of this algorithm over existing approaches. Study and proposal of best practices are also provided to practitioners to extract maximum value out of the new feature selection approach.