# US 2025/0148418 A1 · Creation and arrangement of items in an online concierge system-specific portion of a warehouse for order fulfillment

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

- Number: US 2025/0148418 A1
- Document ID: US20250148418A1
- Status: Published application
- Kind: A1
- Application number: 19/013,722
- Filed: 2025-01-08
- Published: 2025-05-08
- Earliest claimed: 2022-04-21
- Assignees: Maplebear Inc.
- Applicants: Maplebear Inc.
- Inventors: Joey Loi; Viswa Mani Kiran Peddinti
- Web page: https://patentgrep.com/patent/US20250148418A1

## CPC

- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/08741: {by picking of items from inventory for fulfillment}
- 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

## Abstract

A warehouse from which shoppers fulfill orders for an online concierge system maintains an online concierge system-specific portion for which the online concierge system specifies placement of items in regions. To place items in the online concierge system-specific portion, the online concierge system accounts for co-occurrences of different items in orders and measures of similarity between different items. From the co-occurrences of items, the online concierge system generates an affinity graph. The online concierge system also generates a colocation graph based on distances between different regions in the online concierge system-specific portion. Using an optimization function with the affinity graph and the colocation graph, the online concierge system selects regions within the online concierge system-specific portion for different items to minimize an amount of time for shoppers to obtain items in the online concierge-system specific portion.

## Claims

### Claim 1

A method, performed by a computing system comprising a processor and a computer-readable medium, comprising:
generating an affinity graph including nodes representing items offered by a warehouse and connections between pairs of items offered by the warehouse, wherein a connection between a pair of items represents co-occurrences of both items of the pair collected by a user in the warehouse;
generating a colocation data structure for the warehouse, the colocation data structure including different regions within the warehouse, wherein the colocation data structure includes connections between pairs of regions within the warehouse, and wherein the connections represent distances between regions within the warehouse;
generating instructions for placing items in regions within the warehouse by applying an optimization function to a plurality of combinations of pairs, wherein each combination of the plurality of combinations of pairs comprises a first pair including information specifying a first item and a first region within the warehouse and a second pair including information specifying a second item and a second region within the warehouse, and wherein the optimization function is a function based on a connection between the first region and the second region within the colocation data structure and a connection between the first item and the second item in the affinity graph; and
transmitting the instructions for placing items in regions within the warehouse to a computing system associated with the warehouse.

### Claim 2 (depends on 1)

The method of claim 1, wherein generating the affinity graph comprises:
determining the connection between the pair of items based on a weight of a co-occurrence score calculated based on co-occurrences of both items of the pair items of the pair being collected by a user in the warehouse.

### Claim 3 (depends on 2)

The method of claim 2, wherein generating the affinity graph comprises:
determining the co-occurrence score by computing a sum of collections of items by users including one item of the pair of items and collections of items by users including a different item of the pair and dividing a product of a constant and a number of collections of items by users including both items of the pair by the sum.

### Claim 4 (depends on 1)

The method of claim 1, wherein the optimization function is a function based on a measure of similarity between a first item embedding for the first item and a second item embedding for the second item.

### Claim 5 (depends on 1)

The method of claim 1, wherein generating the affinity graph including items offered by the warehouse comprises:
generating clusters of items offered by the warehouse based on distances between items in the affinity graph, wherein a distance between each pair of items in the affinity graph is based on a number of co-occurrences of the pair of items both being collected by a user and a measure of similarity between the pair of items.

### Claim 6 (depends on 5)

The method of claim 5, further comprising:
determining the distance between each pair of items in the affinity graph by dividing the measure of similarity between the pair of items by a co-occurrence score of the pair of items, the co-occurrence score based on a number of collections of items in the warehouse including both of the pair of items.

### Claim 7 (depends on 5)

The method of claim 5, wherein the combination of pairs includes each pair of items in a specific cluster and regions within the warehouse.

### Claim 8 (depends on 1)

The method of claim 1, wherein applying the optimization function comprises:
determining a co-occurrence value as a product of a distance between the first region and the second region, a co-occurrence score of the first item and the second item based on a number of co-occurrences of the first item and the second item being collected by a user, a predicted number of baskets including the first item, and a predicted number of baskets including the second item;
determining a similarity value by multiplying a measure of similarity between the first item and the second item, a predicted number of baskets in which the first item is found, and a predicted number of baskets in which the second item is found; and
determining a value for the combination by dividing the co-occurrence value by the similarity value.

### Claim 9 (depends on 1)

The method of claim 1, wherein generating instructions for placing items in regions within the warehouse comprises:
ranking combinations including pairs of items and regions within the warehouse based on corresponding values from application of the optimization function to the combinations of pairs;
selecting combinations having at least a threshold position in the ranking; and
generating the instructions specifying placement of items in regions within the warehouse according to the selected combinations.

### Claim 10

A non-transitory computer-readable medium storing instructions that, when executed by a computer system, cause the computer system to perform operations comprising:
generating an affinity graph including nodes representing items offered by a warehouse and connections between pairs of items offered by the warehouse, wherein a connection between a pair of items represents co-occurrences of both items of the pair collected by a user in the warehouse;
generating a colocation data structure for the warehouse, the colocation data structure including different regions within the warehouse, wherein the colocation data structure includes connections between pairs of regions within the warehouse, and wherein the connections represent distances between regions within the warehouse;
generating instructions for placing items in regions within the warehouse by applying an optimization function to a plurality of combinations of pairs, wherein each combination of the plurality of combinations of pairs comprises a first pair including information specifying a first item and a first region within the warehouse and a second pair including information specifying a second item and a second region within the warehouse, and wherein the optimization function is a function based on a connection between the first region and the second region within the colocation data structure and a connection between the first item and the second item in the affinity graph; and
transmitting the instructions for placing items in regions within the warehouse to a computing system associated with the warehouse.

### Claim 11 (depends on 10)

The computer-readable medium of claim 10, wherein generating the affinity graph comprises:
determining the connection between the pair of items based on a weight of a co-occurrence score calculated based on co-occurrences of both items of the pair items of the pair being collected by a user in the warehouse.

### Claim 12 (depends on 11)

The computer-readable medium of claim 11, wherein generating the affinity graph comprises:
determining the co-occurrence score by computing a sum of collections of items by users including one item of the pair of items and collections of items by users including a different item of the pair and dividing a product of a constant and a number of collections of items by users including both items of the pair by the sum.

### Claim 13 (depends on 10)

The computer-readable medium of claim 10, wherein the optimization function is a function based on a measure of similarity between a first item embedding for the first item and a second item embedding for the second item.

### Claim 14 (depends on 10)

The computer-readable medium of claim 10, wherein generating the affinity graph including items offered by the warehouse comprises:
generating clusters of items offered by the warehouse based on distances between items in the affinity graph, wherein a distance between each pair of items in the affinity graph is based on a number of co-occurrences of the pair of items both being collected by a user and a measure of similarity between the pair of items.

### Claim 15 (depends on 14)

The computer-readable medium of claim 14, further comprising:
determining the distance between each pair of items in the affinity graph by dividing the measure of similarity between the pair of items by a co-occurrence score of the pair of items, the co-occurrence score based on a number of collections of items in the warehouse including both of the pair of items.

### Claim 16 (depends on 14)

The computer-readable medium of claim 14, wherein the combination of pairs includes each pair of items in a specific cluster and regions within the warehouse.

### Claim 17 (depends on 10)

The computer-readable medium of claim 10, wherein applying the optimization function comprises:
determining a co-occurrence value as a product of a distance between the first region and the second region, a co-occurrence score of the first item and the second item based on a number of co-occurrences of the first item and the second item being collected by a user, a predicted number of baskets including the first item, and a predicted number of baskets including the second item;
determining a similarity value by multiplying a measure of similarity between the first item and the second item, a predicted number of baskets in which the first item is found, and a predicted number of baskets in which the second item is found; and
determining a value for the combination by dividing the co-occurrence value by the similarity value.

### Claim 18 (depends on 10)

The computer-readable medium of claim 10, wherein generating instructions for placing items in regions within the warehouse comprises:
ranking combinations including pairs of items and regions within the warehouse based on corresponding values from application of the optimization function to the combinations of pairs;
selecting combinations having at least a threshold position in the ranking; and
generating the instructions specifying placement of items in regions within the warehouse according to the selected combinations.

### Claim 19

A computer system comprising:
a processor; and
a non-transitory computer-readable medium storing instructions that, when executed by a computer system, cause the computer system to perform operations comprising:
generating an affinity graph including nodes representing items offered by a warehouse and connections between pairs of items offered by the warehouse, wherein a connection between a pair of items represents co-occurrences of both items of the pair collected by a user in the warehouse;
generating a colocation data structure for the warehouse, the colocation data structure including different regions within the warehouse, wherein the colocation data structure includes connections between pairs of regions within the warehouse, and wherein the connections represent distances between regions within the warehouse;
generating instructions for placing items in regions within the warehouse by applying an optimization function to a plurality of combinations of pairs, wherein each combination of the plurality of combinations of pairs comprises a first pair including information specifying a first item and a first region within the warehouse and a second pair including information specifying a second item and a second region within the warehouse, and wherein the optimization function is a function based on a connection between the first region and the second region within the colocation data structure and a connection between the first item and the second item in the affinity graph; and
transmitting the instructions for placing items in regions within the warehouse to a computing system associated with the warehouse.

### Claim 20 (depends on 19)

The computer system of claim 19, wherein generating the affinity graph comprises:
determining the connection between the pair of items based on a weight of a co-occurrence score calculated based on co-occurrences of both items of the pair items of the pair being collected by a user in the warehouse.
