WALGREEN CO.

Techniques for discovering or predicting that a patient is eligible for a post-hospital discharge medication reconciliation process are disclosed. The prediction is based on automatically applying a machine learning model to one or more incoming prescription orders, where the model has been generated from statistically analyzing a plurality of historical prescriptions to determine prescription attributes and/or values thereof that are more strongly correlated to hospital discharges than are other prescription attributes and/or values. When a prescription order is discovered to be associated with a hospital discharge, the named patient is deemed eligible for medication reconciliation, and an alert is generated so that pharmacy personnel may initiate a post-hospital discharge medication reconciliation process for the patient. As such, patient health outcomes may be improved after being discharged from the hospital, as post-hospital discharge medication reconciliations are able to be completed within 30 days of the patient's discharge using the disclosed techniques.

Embodiments are provided for enhancing an in-store retail experience for a customer by facilitating search queries for products and services available for sale in a retail store. According to certain aspects, an electronic device may receive a search string associated with the retail store and transmit the search string to a server that may execute a corresponding search query. The server may send results from the search query to the electronic device, which may dynamically update an interface accessible by a user. The user may view the information and make appropriate selections.

An offer decay generation model determines, for a particular customer, a personalized optimal offer decay curve of an incentive corresponding to a product provided by an enterprise, where the offer decay curve defines a set of decreasing incentive values and respective time intervals during which each incentive value is valid. The offer decay generation model is trained on historical data indicative of customers, customer interactions, offered incentives, resulting outcomes of the incentives, and time intervals elapsing between incentives and resulting outcomes. As such, the optimized offer decay curve is structured to maximize a probability that the particular customer is motivated to accept the incentive offer, purchase a product, and/or further interact with the enterprise during the lifetime of the offer decay curve. The offer decay curve may unique to the individual customer, and may be further customized based on other parameters such as location, time/day/date, inventories, etc.

Systems and methods for space optimization of a retail environment are provided. Example techniques may include calculating demand values associated with each of a plurality of departments that exist in the retail environment based on departmental data associated with each of the plurality of departments, the retail environment having a known amount of space; for each possible ordered pair of departments determining a halo demand value based on a relationship between a first demand value, associated with a first department of a pair, and an existence of a second department of the pair in the retail environment; and generating an optimized space output corresponding to a proportion of the retail environment allotted to each of the plurality of the departments based on respective demand values for each of the plurality of departments and the halo demand values associated with each possible ordered pair of departments of the plurality of departments.

Systems and methods relating to management of delivery fleets are disclosed. Such systems and methods include using functionally-aligned machine learning engines to manage aspects of fleet dispatch and routing, inventory level adjustments, and order optimization. The techniques may be applied to manage an automated fleet delivery services system controlling a fleet of autonomous delivery devices (e.g., UAVs) to deliver products from a plurality of distribution hubs to fulfil customer orders. The interconnected machine learning engines enable efficient management of various aspects of such automated fleet delivery services in real time, including optimization of fleet distribution, optimization of inventory distribution, and optimization of order distribution. Optimization of order distribution may be obtained by dynamically adjusting delivery charges for orders based upon current fleet capacity and inventory levels.

The current disclosure relates to systems and methods for prescription stock management at one or more pharmacies in a pharmacy chain. The system initializes and trains a stock management model using machine learning techniques in order to calculate outputs such as a minimum stocked number, a maximum stocked number, and an order amount for at least one prescription item. The system then monitors the inventory of the prescription item, and transmits an order, based on the order amount, for the prescription item if the stock of the prescription item is less than the minimum stocked number.

A method and system may provide a new prescription order interface which allows a customer to order one or more new prescription medications in a quick and easy manner from a remote location using a computer or mobile device. The customer provides a new paper prescription image that includes the prescription data for a pharmacy to fill the new prescription order. The new paper prescription image is received by a server and a default pickup store and a default pickup time are determined. The server also determines whether there is a high risk that the new prescription order is fraudulent by comparing a signature in the new paper prescription image to stored signatures associated with the prescriber, and comparing distances between the locations of the customer's web-enabled device, the pharmacy, and the prescriber. The system may be accessed through a series of web pages and/or via an application.

Techniques for generating an irrevocable or guaranteed out-of-pocket (OOP) cost for a patient's prescription prior to the patient submitting the prescription for processing and filling by an enterprise include receiving a request for the OOP cost, obtaining current information corresponding to the patient, and determining the irrevocable OOP cost of the prescription based on the current patient information, one or more constraints set by the enterprise for a given time interval and associated with OOP prescription costs, and changes to characteristic(s) of the patient and/or occurrences of external condition(s) predicted to occur during the given time interval. The irrevocable OOP cost may be charged to the patient for the prescription irrespective of any amount which is provided by the patient's insurance provider to cover the cost of the prescription. The techniques may utilize a set of specially-trained irrevocable OOP cost machine learning models to determine the irrevocable OOP prescription cost.

Techniques for generating an irrevocable or guaranteed out-of-pocket (OOP) cost for a patient's prescription prior to the patient submitting the prescription for processing and filling by an enterprise include receiving a request for the OOP cost, obtaining current information corresponding to the patient, and determining the irrevocable OOP cost of the prescription based on the current patient information, one or more constraints set by the enterprise for a given time interval and associated with OOP prescription costs, and changes to characteristic(s) of the patient and/or occurrences of external condition(s) predicted to occur during the given time interval. The irrevocable OOP cost may be charged to the patient for the prescription irrespective of any amount which is provided by the patient's insurance provider to cover the cost of the prescription. The techniques may utilize a set of specially-trained irrevocable OOP cost machine learning models to determine the irrevocable OOP prescription cost.

Techniques are disclosed to provide enhanced online security. When user authenticating information is provided to access secure content, a network server identifies the user via a website identifier. Some of the disclosed techniques leverage third party “cookie stitchers” to associate user data, which may include a website identifier, to the user's computing devices. If the cookie stitcher cannot identify a current computing device, or if a current website identifier does not match one stored in the user data, then 2-factor authentication (2FA) may be triggered. Other disclosed techniques leverage stored device management data (DMD), which uniquely identifies each computing device that is associated with a website identifier. These techniques allow the network server to block access to explicitly-identified computing devices, and to trigger 2FA unless specific computing device metrics, which are associated with a computing device, are matched to computing device metrics contained in the DMD.