# US 2026/0065220 A1 · System and method for proactive aggregation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0065220 A1
- Document ID: US20260065220A1
- Status: Published application
- Kind: A1
- Application number: 19/379,294
- Filed: 2025-11-04
- Published: 2026-03-05
- Earliest claimed: 2021-04-28
- Assignees: DoorDash, Inc.
- Applicants: DoorDash, Inc
- Inventors: Rohit Raghunathan; Dananjayan Thirumalai; Chang Zhu; Kyle Hsiao; Li Pei
- Web page: https://patentgrep.com/patent/US20260065220A1

## CPC

- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06N 20/00: Machine learning
- G06Q 10/083: Shipping
- G06Q 10/08726: {for replenishment processing, procedures, or recommendations using forecasting or optimisation}
- G06Q 10/08744: {by distributed inventory management}
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The method includes determining, by a central server computer using a machine learning model, aggregates of items that are likely to be ordered by end users. The method also includes initiating placement of the items in the aggregates of items in one or more locations based on locations of the end users, receiving a request for an aggregate of items, and initiate the fulfillment of the request for the aggregate of items, where the items in the aggregates of items are at the one or more locations.

## Claims

### Claim 1

A method comprising:
training, by a central server computer, a machine learning model comprising a neural network using historical interaction data associated with prior interactions to determine values of model parameters, the historical interaction data comprising at least an identification of items ordered for each historical interaction, to generate the trained machine learning model configured to, based on input interaction data, predict aggregates of items and locations for placing the aggregates of items;
determining, by the central server computer using the trained machine learning model, aggregates of items that are likely to be ordered by end users within a geographical area, wherein the items include perishable items to be stored in a temperature-controlled environment;
determining, by the central server computer, an available storage capacity at one or more locations of a third party that are within the geographical area for placing the determined aggregates of items, the determining the available storage capacity comprising:
determining that the one or more locations comprise a temperature-controlled storage section suitable for storing the perishable items of the determined aggregates of items, and
determining the available storage capacity at the temperature-controlled storage section of each of the one or more locations by receiving one or more detection signals provided by one or more sensors detecting the available storage capacity at the temperature-controlled storage section of each of the one or more locations, the one or more sensors are disposed at the temperature-controlled storage section of each of the one or more locations;
initiating, by the central server computer, placement of the items in the aggregates of items at the one or more locations based on locations of the end users;
displaying, by the central server computer on a user device operated by an end user associated with a physical location, the aggregates of items via an application interface screen displayed on the user device, the end user being one of the end users;
receiving, by the central server computer, a signal corresponding to a user selection input, the user selection input being provided via the application interface screen and indicating a selection of one of the aggregates of items stored at the one or more locations, wherein the selection of the one of the aggregates of items is for perishable items and non-perishable items; and
in response to the receiving the signal, sending, by the central server computer to a transporter device, a request to deliver the one of the aggregates of items from the one or more locations to the physical location, wherein the one of the aggregates of items is thereafter delivered to the physical location.

### Claim 2 (depends on 1)

The method of claim 1, wherein any of the one or more locations comprises a service provider location, a transporter vehicle, and/or a vending machine.

### Claim 3 (depends on 1)

The method of claim 1, further comprising:
communicating, by the central server computer, with one or more transporter devices to deliver the aggregates of items to at least some of the end users.

### Claim 4 (depends on 1)

The method of claim 1, wherein the initiating further comprises:
communicating with service providers and transporter devices to place the items in the aggregates along predicted routes.

### Claim 5 (depends on 1)

The method of claim 1, further comprising;
updating, by the central server computer, the machine learning model using interaction data associated with the aggregates of items that are fulfilled, the updating comprising updating the values of model parameters, to generate an updated machine learning model;
after updating the machine learning model, determining again, by the central server computer using the updated machine learning model, updated aggregates of items that are likely to be ordered by the end users within the geographical area and one or more second locations of the third party within the geographical area for placing the updated aggregates of items; and
initiating, by the central server computer, placement of the items in the updated aggregates of items at the one or more second locations based on locations of the end users.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
prior to the initiating, communicating, by the central server computer, with one or more service providers that can fulfill one or more of the items in the aggregates of items.

### Claim 7 (depends on 6)

The method of claim 6, further comprising:
communicating, by the central server computer, with one or more transporter devices to deliver the aggregates of items to at least some of the end users.

### Claim 8 (depends on 1)

The method of claim 1, wherein the transporter device is an autonomous vehicle.

### Claim 9

A central server computer comprising:
a processor; and
a non-transitory computer readable medium comprising code, executable by the processor for performing operations including:
training a machine learning model comprising a neural network using historical interaction data associated with prior interactions to determine values of model parameters, the historical interaction data comprising at least an identification of items ordered for each historical interaction, to generate the trained machine learning model configured to, based on input interaction data, predict aggregates of items and locations for placing the aggregates of items;
determining, using the trained machine learning model, aggregates of items that are likely to be ordered by end users within a geographical area, wherein the items include perishable items to be stored in a temperature-controlled environment;
determining an available storage capacity at one or more locations of a third party that are within the geographical area for placing the determined aggregates of items, the determining the available storage capacity including:
determining that the one or more locations comprise a temperature-controlled storage section suitable for storing the perishable items of the determined aggregates of items, and
determining the available storage capacity at the temperature-controlled storage section of each of the one or more locations by receiving one or more detection signals provided by one or more sensors detecting the available storage capacity at the temperature-controlled storage section of each of the one or more locations, the one or more sensors are disposed at the temperature-controlled storage section of each of the one or more locations;
initiating placement of the items in the aggregates of items at the one or more locations based on locations of the end users;
displaying, on a user device operated by an end user associated with a physical location, the aggregates of items via an application interface screen displayed on the user device, the end user being one of the end users;
receiving a signal corresponding to a user selection input, the user selection input being provided via the application interface screen and indicating a selection of one of the aggregates of items stored at the one or more locations, wherein the selection of the one of the aggregates of items is for perishable items and non-perishable items; and
in response to the receiving the signal, sending, to a transporter device, a request to deliver the one of the aggregates of items from the one or more locations to the physical location, wherein the one of the aggregates of items is thereafter delivered to the physical location.

### Claim 10 (depends on 9)

The central server computer of claim 9, wherein any of the one or more locations comprises a service provider location, a transporter vehicle, and/or a vending machine.

### Claim 11 (depends on 9)

The central server computer of claim 9, wherein the operations further include:
updating the machine learning model using interaction data associated with the aggregates of items that are fulfilled, the updating including updating the values of model parameters, to generate an updated machine learning model;
after updating the machine learning model, determining again, using the updated machine learning model, updated aggregates of items that are likely to be ordered by the end users within the geographical area and one or more second locations of the third party within the geographical area for placing the updated aggregates of items; and
initiating placement of the items in the updated aggregates of items at the one or more second locations based on locations of the end users.

### Claim 12 (depends on 9)

The central server computer of claim 9, wherein the initiating further includes communicating with service providers and transporter devices to place the items in the aggregates along predicted routes.

### Claim 13 (depends on 9)

The central server computer of claim 9, wherein the operations further include communicating with one or more transporter devices to deliver one or more of the aggregates of items to at least some of the end users.

### Claim 14 (depends on 9)

The central server computer of claim 9, wherein the transporter device is an autonomous vehicle.

### Claim 15

A system comprising:
a central server computer comprising:
a processor; and
a non-transitory computer readable medium comprising code, executable by the processor for performing operations including:
training a machine learning model comprising a neural network using historical interaction data associated with prior interactions to determine values of model parameters, the historical interaction data comprising at least an identification of items ordered for each historical interaction, to generate the trained machine learning model configured to, based on input interaction data, predict aggregates of items and locations for placing the aggregates of items;
determining, using the trained machine learning model, aggregates of items that are likely to be ordered by end users within a geographical area, wherein the items include perishable items to be stored in a temperature-controlled environment;
determining an available storage capacity at one or more locations of a third party that are within the geographical area for placing the determined aggregates of items, the determining the available storage capacity including:
determining that the one or more locations comprise a temperature-controlled storage section suitable for storing the perishable items of the determined aggregates of items, and
determining the available storage capacity at the temperature-controlled storage section of each of the one or more locations by receiving one or more detection signals provided by one or more sensors detecting the available storage capacity at the temperature-controlled storage section of each of the one or more locations, the one or more sensors are disposed at the temperature-controlled storage section of each of the one or more locations;
initiating placement of the items in the aggregates of items at the one or more locations based on locations of the end users;
displaying, on a user device operated by an end user associated with a physical location, the aggregates of items via an application interface screen displayed on the user device, the end user being one of the end users;
receiving a signal corresponding to a user selection input, the user selection input being provided via the application interface screen and indicating a selection of one of the aggregates of items stored at the one or more locations, wherein the selection of the one of the aggregates of items is for perishable items and non-perishable items; and
in response to the receiving the signal, sending, to a transporter device, a request to deliver the one of the aggregates of items from the one or more locations to the physical location, wherein the one of the aggregates of items is thereafter delivered to the physical location.

### Claim 16 (depends on 15)

The system of claim 15, further comprising a logistics platform in operative communication with the central server computer.

### Claim 17 (depends on 15)

The system of claim 15, wherein any of the one or more locations comprises service provider locations.

### Claim 18 (depends on 15)

The system of claim 15, wherein the operations further include:
updating the machine learning model using interaction data associated with the aggregates of items that are fulfilled, the updating including updating the values of model parameters, to generate an updated machine learning model;
after updating the machine learning model, determining again, using the updated machine learning model, updated aggregates of items that are likely to be ordered by the end users within the geographical area and one or more second locations of the third party within the geographical area for placing the updated aggregates of items; and
initiating placement of the items in the updated aggregates of items at the one or more second locations based on locations of the end users.

### Claim 19 (depends on 15)

The system of claim 15, wherein the initiating further includes:
communicating with service providers and transporter devices to place the items in the aggregates along predicted routes.

### Claim 20 (depends on 15)

The system of claim 15, wherein the transporter device is an autonomous vehicle.
