Depot dispatch protocol for aggregating on-demand deliveries

A server system comprising:

• one or more processors, memory, and one or more programs stored in the memory, the one or more programs comprising instructions for:
• receiving, at the server system, an order message for a first order from a customer device corresponding to a first customer for real-time delivery of perishable goods from a first restaurant;
• receiving confirmations for a plurality of first events for the first order from at least one of a first merchant device corresponding to the first restaurant, a runner device corresponding to a runner, and a courier device corresponding to a courier, wherein the plurality of first events for the first order include:
• receipt of the first order, completion of the first order, receipt of the first order at an aggregation depot, and receipt of the first order by the first customer;
• receiving a first timestamp corresponding to an initial event of the plurality of first events;
• dynamically generating, via a neural network, estimated time of arrivals (ETAs) for one or more of the plurality of first events, including a first ETA corresponding to the completion of the first order, wherein the neural network is implemented by the one or more processors and comprises a plurality of computational layers including weighted parameters,
• wherein in a training mode, the one or more processors are configured to:
• pass a dataset into the neural network, the dataset including a series of successive events with corresponding known time durations between events, and
• train the neural network to dynamically output ETA predictive updates, wherein training the neural network includes:
• inputting different combinations of events and time durations, and comparing actual time of arrivals (ATAs) with generated ETA predictions to allow for the neural network to automatically and iteratively adjust weighted parameters in the neural network,
• wherein in an inference mode, the one or more processors are configured to:
• pass the initial event of the plurality of first events into the neural network, the initial event including the first timestamp,
• automatically generate the first ETA based on the weighted parameters,
• pass a subsequent event of the plurality of first events into the neural network, the subsequent event including an updated timestamp, and
• automatically adjust the first ETA to form an updated ETA for the completion of the first order;
• transmitting a first order notification to the runner device, wherein the first order notification includes:
• the first ETA and a storage location in an automated locker system of the aggregation depot, wherein the storage location is configured to store a batch of one or more orders grouped based on delivery proximity to the first customer, the batch of one or more orders including the first order;
• transmitting a delivery notification to the courier device, wherein the delivery notification includes the storage location in the automated locker system and a customer location corresponding to the first customer;
• and
• authenticating the courier by the automated locker system to provide the courier access to the storage location.

A programmable device configured for aggregating on-demand deliveries, wherein the programmable device is configured for:

• receiving, at a server system, an order message for a first order from a customer device corresponding to a first customer for real-time delivery of perishable goods from a first restaurant;
• receiving confirmations for a plurality of first events for the first order from at least one of a first merchant device corresponding to the first restaurant, a runner device corresponding to a runner, and a courier device corresponding to a courier, wherein the plurality of first events for the first order include:
• receipt of the first order, completion of the first order, receipt of the first order at an aggregation depot, and receipt of the first order by the first customer;
• receiving a first timestamp corresponding to an initial event of the plurality of first events;
• dynamically generating, via a neural network, estimated time of arrivals (ETAs) for one or more of the plurality of first events, including a first ETA corresponding to the completion of the first order, wherein the neural network is implemented by a processor and comprises a plurality of computational layers including weighted parameters,
• wherein in a training mode, the processor is configured to:
• pass a dataset into the neural network, the dataset including a series of successive events with corresponding known time durations between events, and
• train the neural network to dynamically output ETA predictive updates, wherein training the neural network includes:
• inputting different combinations of events and time durations, and comparing actual time of arrivals (ATAs) with generated ETA predictions to allow for the neural network to automatically and iteratively adjust weighted parameters in the neural network,
• wherein in an inference mode, the processor is configured to:
• pass the initial event of the plurality of first events into the neural network, the initial event including the first timestamp,
• automatically generate the first ETA based on the weighted parameters,
• pass a subsequent event of the plurality of first events into the neural network, the subsequent event including an updated timestamp, and
• automatically adjust the first ETA to form an updated ETA for the completion of the first order;
• transmitting a first order notification to the runner device, wherein the first order notification includes:
• the first ETA and a storage location in an automated locker system of the aggregation depot, wherein the storage location is configured to store a batch of one or more orders grouped based on delivery proximity to the first customer, the batch of one or more orders including the first order;
• transmitting a delivery notification to the courier device, wherein the delivery notification includes the storage location in the automated locker system and a customer location corresponding to the first customer;
• and
• authenticating the courier by the automated locker system to provide the courier access to the storage location.