# US 2022/0044299 A1 · Determining generic items for orders on an online concierge system

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

- Number: US 2022/0044299 A1
- Document ID: US20220044299A1
- Status: Published application
- Kind: A1
- Application number: 16/984,443
- Filed: 2020-08-04
- Published: 2022-02-10
- Earliest claimed: 2020-08-04
- Assignees: Maplebear Inc.
- Applicants: Maplebear, Inc. (dba Instacart)
- Inventors: Tyler Russell Tate; Jason Scott; Logan William Murdock; Tejaswi Tenneti
- Web page: https://patentgrep.com/patent/US20220044299A1

## CPC

- G06Q 30/0631: {Recommending goods or services}
- G06F 16/9538: Presentation of query results
- G06Q 10/087: Inventory or stock management, e.g. order filling, procurement or balancing against orders
- G06Q 10/08726: {for replenishment processing, procedures, or recommendations using forecasting or optimisation}
- G06Q 30/0283: Price estimation or determination
- G06Q 30/0603: {Catalogue creation or management}
- G06Q 30/0617: {Representative agent}
- G06Q 30/0625: {by formulating product or service queries, e.g. using keywords or predefined options}
- G06Q 30/0635: {replenishment orders; recurring orders}
- G06Q 30/0641: {utilising user interfaces specially adapted for shopping}
- 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
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)

## Abstract

An online system provides options for selection by a user. The online system receives a query entered on a client device. The online system queries an item database to retrieve a set of items related to the query and assigns each item to a product category in a predefined taxonomy that maps items to product categories. The online system inputs each item into a prediction model trained to predict a probability that an item is available at a warehouse location. The online system determines that a first product category has low availability based on predicted probabilities for items in the first product category. Responsive to determining that a first product category has low availability, the online system generates a generic item for the first product category and sends a list of items including the generic item to the client device for display responsive to the query.

## Claims

### Claim 1

A method for providing options for selection by a user, the method comprising:
receiving a query sent from a user device to an online concierge system;
querying an item database using the received query to retrieve a set of items matching the query;
assigning each item of the set of items to a product category from a plurality of product categories based on a predefined taxonomy that maps items to product categories; and
inputting each item of the set of items into a prediction model, the prediction model comprising a machine learning model that is trained to predict a probability that the item is available at one or more third-party warehouse locations;
determining that a first product category has low availability based on the predicted probability that each of the items assigned to the first product category is available at one or more third-party warehouse locations;
responsive to determining that the first product category has low availability, generating a generic item for the first product category; and
sending a list of items responsive to the query from the online concierge system for display on the user device, the list of items including the generic item as one of the items.

### Claim 2 (depends on 1)

The method of claim 1, assigning each item of the set of items to a product category from a plurality of product categories comprises:
receiving a set of queries from a plurality of customer user devices;
pairing each of the set of queries with an item subsequently added to an online shopping cart; and
determining a set of leaf categories of the taxonomy related to the paired items.

### Claim 3 (depends on 1)

The method of claim 1, wherein the taxonomy comprises a hierarchy of product categories, each product category related to a set of items on the online concierge system.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
determining a popular size of items in the first product category;
retrieving prices for each item in the first product category based on the popular size; and
selecting an interior price range from within a price range of the retrieved prices, a low end of the interior price range being a first percentile of the price range and a high end of the interior price range being a second percentile of the price range.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
receiving an order of items from the user device, the order including the generic item as one of the items; and
presenting, in a user interface of a second user device, the items in the order, the generic item associated with a maximum price based on the price range.

### Claim 6 (depends on 1)

The method of claim 1, further comprising:
receiving an order of the generic item;
locating an item that matches the first product category of the generic item at the warehouse location, the item having a price;
delivering the item to a user associated with the user device; and
charging the price to the generic item to a user account associated with the user device.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
receiving an order of the generic item, the generic item associated with a price range;
charging a preliminary price to a user account associated with the user device, the preliminary price within the price range;
locating an item that matches the first product category of the generic item at the warehouse location, the item having a price within the price range;
delivering the item to a user associated with the user device; and
adjusting the charged preliminary price based on the price of the item.

### Claim 8

A non-transitory computer-readable storage medium comprising instructions executable by a processor, the instructions comprising:
instructions for receiving a query sent from a user device to an online concierge system;
instructions for querying an item database using the received query to retrieve a set of items matching the query;
instructions for assigning each item of the set of items to a product category from a plurality of product categories based on a predefined taxonomy that maps items to product categories; and
instructions for inputting each item of the set of items into a prediction model, the prediction model comprising a machine learning model that is trained to predict a probability that the item is available at one or more third-party warehouse locations;
instructions for determining that a first product category has low availability based on the predicted probability that each of the items assigned to the first product category is available at one or more third-party warehouse locations;
responsive to determining that the first product category has low availability, instructions for generating a generic item for the first product category; and
instructions for sending a list of items responsive to the query from the online concierge system for display on the user device, the list of items including the generic item as one of the items.

### Claim 9 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, wherein the instructions for assigning each item of the set of items to a product category from a plurality of product categories comprises:
instructions for receiving a set of queries from a plurality of customer user devices;
instructions for pairing each of the set of queries with an item subsequently added to an online shopping cart; and
instructions for determining a set of leaf categories of the taxonomy related to the paired items.

### Claim 10 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, wherein the taxonomy comprises a hierarchy of product categories, each product category related to a set of items on the online concierge system.

### Claim 11 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, the instructions further comprising:
instructions for determining a popular size of items in the first product category;
instructions for retrieving prices for each item in the first product category based on the popular size; and
instructions for selecting an interior price range from within a price range of the retrieved prices, a low end of the interior price range being a first percentile of the price range and a high end of the interior price range being a second percentile of the price range.

### Claim 12 (depends on 11)

The non-transitory computer-readable storage medium of claim 11, the instructions further comprising:
instructions for receiving an order of items from the user device, the order including the generic item as one of the items; and
instructions for presenting, in a user interface of a second user device, the items in the order, the generic item associated with a maximum price based on the price range.

### Claim 13 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, the instructions further comprising:
instructions for receiving an order of the generic item;
instructions for locating an item that matches the first product category of the generic item at the warehouse location, the item having a price;
instructions for delivering the item to a user associated with the user device; and
instructions for charging the price to the generic item to a user account associated with the user device.

### Claim 14 (depends on 8)

The non-transitory computer-readable storage medium of claim 8, the instructions further comprising:
instructions for receiving an order of the generic item, the generic item associated with a price range;
instructions for charging a preliminary price to a user account associated with the user device, the preliminary price within the price range;
instructions for locating an item that matches the first product category of the generic item at the warehouse location, the item having a price within the price range;
instructions for delivering the item to a user associated with the user device; and
instructions for adjusting the charged preliminary price based on the price of the item.

### Claim 15

A computer system comprising:
a computer processor; and
a non-transitory computer-readable storage medium storage instructions that when executed by the computer processor perform actions comprising:
receiving a query sent from a user device to an online concierge system;
querying an item database using the received query to retrieve a set of items matching the query;
assigning each item of the set of items to a product category from a plurality of product categories based on a predefined taxonomy that maps items to product categories; and
inputting each item of the set of items into a prediction model, the prediction model comprising a machine learning model that is trained to predict a probability that the item is available at one or more third-party warehouse locations;
determining that a first product category has low availability based on the predicted probability that each of the items assigned to the first product category is available at one or more third-party warehouse locations;
responsive to determining that the first product category has low availability, generating a generic item for the first product category; and
sending a list of items responsive to the query from the online concierge system for display on the user device, the list of items including the generic item as one of the items.

### Claim 16 (depends on 15)

The computer system of claim 15, wherein the actions for assigning each item of the set of items to a product category from a plurality of product categories further comprise:
receiving a set of queries from a plurality of customer user devices;
pairing each of the set of queries with an item subsequently added to an online shopping cart; and
determining a set of leaf categories of the taxonomy related to the paired items.

### Claim 17 (depends on 15)

The computer system of claim 15, wherein the taxonomy comprises a hierarchy of categories, each category related to a set of items on an online concierge system.

### Claim 18 (depends on 15)

The computer system of claim 15, the actions further comprising:
determining a popular size of items in the first product category;
retrieving prices for each item in the first product category based on the popular size; and
selecting an interior price range from within a price range of the retrieved prices, a low end of the interior price range being a first percentile of the price range and a high end of the interior price range being a second percentile of the price range.

### Claim 19 (depends on 18)

The computer system of claim 18, the actions further comprising:
receiving an order of items from the user device, the order including the generic item as one of the items; and
presenting, in a user interface of a second user device, the items in the order, the generic item associated with a maximum price based on the price range.

### Claim 20 (depends on 15)

The computer system of claim 15, the actions further comprising:
receiving an order of the generic item;
locating an item that matches the first product category of the generic item at the warehouse location, the item having a price;
delivering the item to a user associated with the user device; and
charging the price to the generic item to a user account associated with the user device.