There are provided methods, systems, and non-transitory storage mediums for performing a meta-prediction of time series by using a set of forecasting models each associated with a forecasting theme. Time series data is received, and a set of forecast signals is generated. At least one signal and feature processing model generates a set of features. A meta-learner having been trained on historical time series data generates, based on the time series data and the set of features, a set of weights for the set of forecasting models. A meta-prediction is generated by using the set of features and forecast signals. Implementations may use combinations of endogenous and exogenous data, latent space transformations and generate interpretations and explanations for the meta-prediction.

An information processing system includes: an acquisition unit that acquires schedule information regarding a travel schedule of a recipient who receives a package; and a designation unit that designates, based on the schedule information, a delivery slot corresponding to a scheduled time at which the recipient arrives at a receiving location of the package among a plurality of delivery slots included in a delivery plan of a mobile body used for delivery of the package.

A navigation information processing method, apparatus, and computer-readable storage medium for coordinating vehicle navigation with item ordering and preparation. The method displays a navigation interface with an order control for generating orders during vehicle navigation operations. Order information including the navigation destination is generated and displayed based on user operations. A first duration is determined from real-time remaining travel time to the navigation destination, while a second duration is determined from real-time preparation and delivery times of the target item. When the first duration is less than or equal to the second duration, a preparation state is generated and displayed to indicate the target item is in preparation, enabling synchronized timing between arrival and item preparation.

An information processing method includes acquiring a transportation request for each of one or more transportation objects, the transportation request including a starting point, an ending point, and a first arrival date/time that indicates a date and time at which each of the one or more transportation objects arrives at the starting point, creating a transportation plan on the basis of a sum of one or more holding costs that correspond to a difference between the first arrival date/time and a second arrival date/time that indicates a date and time at which one or more vehicles transporting the transportation objects arrive at the starting point for each of the one or more transportation objects, and one or more transportation costs required for transporting each of the one or more transportation objects from the starting point to the ending point, and outputting the transportation plan.

A method is disclosed, inter alia, performed by a first apparatus or by a component thereof. The first apparatus comprises a plurality of register compartments. The method includes receiving a shipment, in particular a letter shipment. The method includes checking whether the shipment is to be placed in a register compartment of the plurality of register compartments. The method includes accepting the shipment into a register compartment if the checking has concluded that the shipment is to be accepted into a register compartment of the plurality of register compartments and rejecting the shipment if the checking has concluded that the shipment should not be accepted into a register compartment of the plurality of register compartments. In addition, corresponding apparatuses, systems and computer programs for the respective performance and/or control of the disclosed method are disclosed.

Examples provide dynamic delivery promises based on machine learning (ML) predicted transit time to improve promise accuracy and on-time delivery. Actual transit times for previous package deliveries are obtained from historical order data. The actual transit times are weighted based on recency data. A weighted mode is calculated for each shipping lane in a plurality of shipping lanes used to transport packages from a source to a destination location via a carrier method. The mode is calculated based on time period and actual transit times for that time period. Future predicted transit times for each shipping are generated using estimated ship dates and lane-specific modes. The predicted transit times are used to assign a more accurate and reliable delivery promise date to future orders. The promise dates are customized in real-time at a weekday level and a shipping lane level for increased on-time package deliveries.

Methods, systems, and machine learning models for providing accurate estimate time of arrival (ETA) predictions are disclosed, particularly in the context of item fulfillment services. Input features including continuous, numerical, categorical, and time series features can be processed using an initial set of encoders. The resulting embeddings (and other applicable data) can be applied to a set of expert encoders. The embeddings produced by the expert encoders can be combined and processed using a multilayer perceptron, which can return one or more estimated arrival time predictions. Such predictions can correspond to multiple tasks and can include both point estimate predictions and distribution estimate predictions, e.g., predictions describing a probability density function of estimated arrival times. Interval regression can be used to produce distribution estimates, and machine learning models according to embodiments can be trained using multitask learning to produce estimated arrival time predictions for multiple tasks.

An example embodiment is a trailer for a semi-trailer truck that includes an electric, battery-powered drive train mounted on at least one axel of the trailer. A controller sends and receives signals from a global positioning system and from distribution center personnel. Signals are interpreted by a protocol in the controller to move a powered trailer from its current location to a destination. A trailer control algorithm monitors a plurality of variables and communicates to a controller in each trailer to control a plurality of trailers according to the variables.

Example implementations relate to improving an accuracy of an address. A set of address element inputs are received. A quality metric based on the set of address element inputs is computed using a first machine learning model. In accordance with a determination that the quality metric does not meet a threshold, an enriched address is generated based on the set of address element inputs. Feedback indicating an outcome of a delivery associated with the enriched address is received. The first machine learning model is re-train based on the feedback.

According to the present invention, a more realistic and usable delivery plan is generated using a quantum computer. This combinatorial optimization device includes a control unit which is communicably connected to a quantum computer, wherein the control unit: adds a first constraint term specifying a time point relating to a delivery, and a second constraint term for leveling a workload of each vehicle to a cost function used to search for routes when a plurality of vehicles are to visit a plurality of delivery destinations; and causes the quantum computer to perform a quantum calculation of the cost function with the first constraint term and the second constraint term added thereto.