# US 2020/0402129 A1 · Configuring food-related information search and retrieval based on a predictive quality indicator

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

- Number: US 2020/0402129 A1
- Document ID: US20200402129A1
- Status: Published application
- Kind: A1
- Application number: 17/007,856
- Filed: 2020-08-31
- Published: 2020-12-24
- Earliest claimed: 2017-09-28
- Assignees: Grubhub Holdings Inc.
- Applicants: GrubHub Holdings Inc.
- Inventors: Geopher Stephy Justin; Patrick Gomes; Arthi Murugesan; Maria Belousova; Robert Trevelyan Waite
- Web page: https://patentgrep.com/patent/US20200402129A1

## CPC

- G06Q 30/0623: {by investigating goods or services}
- G06Q 30/0635: {replenishment orders; recurring orders}
- G06Q 50/12: Hotels or restaurants
- 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

The disclosed technologies can compute predictive reorder scores and measures of the quality of food products and food providers using objectively verifiable data, including reorder data, and use these predictive quality measures to create new functionality in an information search and retrieval system and/or a product ordering system.

## Claims

### Claim 1

A computer-implemented method for providing improved search and retrieval of made-to-order menu item data using a computing device that is communicatively coupled to a product ordering computer, the method comprising:
determining a set of menu item data, an instance of menu item data in the set of menu item data comprising menu item identifier data and restaurant identifier data, the menu item data identifying a made-to-order food product that can be ordered through the product ordering computer, the restaurant identifier data identifying a restaurant;
obtaining food order data from the product ordering computer, the food order data comprising numerical values indicating a number of times that food products comprising food data items that have been reordered during a time interval using restaurants that are identified in the restaurant identifier data;
using at least some of the food order data, at least some of the menu item data, and a food taxonomy communicatively coupled to the computing device, computing reorder scores for made-to-order food products having food data items that are provided by restaurants identified in the restaurant identifier data;
when a set of reorder scores satisfies a reorder confidence criterion, causing, by a food information interface communicatively coupled to the computing device, tagging a subset of the menu item data with a quality label, the subset comprising menu item data that is associated with the set of reorder scores that satisfies the reorder confidence criterion;
using the quality label to configure a search, retrieval, or display operation executed by the computing device.

### Claim 2 (depends on 1)

The method of claim 1, comprising:
using the food order data, creating a predictive model of quality of the made-to-order food products;
using the predictive model, generating the reorder scores.

### Claim 3 (depends on 1)

The method of claim 1, comprising:
using one or more exclusion criteria, determining the set of menu item data;
normalizing the reorder scores across the set of menu item data.

### Claim 4 (depends on 1)

The method of claim 1, comprising:
using a statistical test, determining when the set of reorder scores satisfies a reorder confidence criterion.

### Claim 5 (depends on 1)

The method of claim 1, comprising:
using the reorder scores, computing a best in class score for a plurality of restaurants;
when the best in class score for a restaurant satisfies a best in class confidence criterion, causing, by a graphical interface, displaying a subset of the menu item data that is associated with the restaurant having the best in class score that satisfies the best in class confidence criterion.

### Claim 6 (depends on 5)

The method of claim 5, comprising:
using one or more exclusion criteria, determining the set of menu item data;
normalizing the best in class scores across the set of menu item data.

### Claim 7 (depends on 1)

The method of claim 1, comprising:
displaying a visual representation of the subset of the menu item data that is associated with the set of reorder scores that satisfies the reorder confidence criterion;
linking a graphical interface element with the visual representation of the subset of the menu item data that is associated with the set of reorder scores that satisfies the reorder confidence criterion.

### Claim 8 (depends on 1)

The method of claim 1, comprising:
displaying a visual representation of the subset of the menu item data that is associated with the best in class score that satisfies the reorder confidence criterion;
linking a graphical interface element with a visual representation of the subset of the menu item data that is associated with the best in class score that satisfies the best in class confidence criterion.

### Claim 9 (depends on 1)

The method of claim 1, comprising:
using the set of reorder scores, sorting the subset of the menu item data that is associated with the set of reorder scores that satisfies the reorder confidence criterion.

### Claim 10 (depends on 1)

The method of claim 1, comprising:
using sensor data that is received by a computing device that is coupled to the display device, detecting a geographic location;
using the detected geographic location, generating the display of the subset of the menu item data that is associated with the set of reorder scores that satisfies the reorder confidence criterion.

### Claim 11 (depends on 1)

The method of claim 1, comprising:
using historical food order data that is associated with a computer account, determining a food class label that is descriptive of similar food items;
using the food class label, determining the set of menu item data.

### Claim 12 (depends on 11)

The method of claim 11, comprising:
using historical interaction data that is associated with a computer account, determining the food class label.

### Claim 13 (depends on 1)

The method of claim 1, comprising:
dynamically adjusting at least one of the reorder scores based on an implicit or an explicit quality influencer.

### Claim 14 (depends on 1)

The method of claim 1, comprising:
dynamically adjusting at least one of the reorder scores based on a difference in order volume.

### Claim 15 (depends on 1)

The method of claim 1, comprising:
dynamically adjusting at least one of the reorder scores based on recency of the food order data.

### Claim 16

A system for providing improved search and retrieval of made-to-order menu item data in a computing device that is communicatively coupled to a product ordering computer, the system comprising:
one or more processors;
a communication interface coupled to the one or more processors;
one or more non-transitory computer-readable storage media coupled to the one or more processors and storing sequences of instructions, which when executed by the one or more processors, cause the one or more processors to:
determine a set of menu item data, an instance of menu item data in the set of menu item data comprising menu item identifier data and restaurant identifier data, the menu item data identifying a made-to-order food product that can be ordered through the product ordering computer and comprising a food data item, the restaurant identifier data identifying a restaurant;
obtain food order data from the product ordering computer, the food order data comprising numerical values indicating a number of times that food products comprising food data items have been reordered during a time interval using restaurants that are identified in the restaurant identifier data;
using at least some of the food order data, at least some of the menu item data, and a food taxonomy communicatively coupled to the computing device, compute reorder scores for made-to-order food products having food data items that are provided by restaurants identified in the restaurant identifier data;
when a set of reorder scores satisfies a reorder confidence criterion, cause, by a food information interface communicatively coupled to the computing device, tagging a subset of the menu item data with a quality label, the subset comprising menu item data that is associated with the set of reorder scores that satisfies the reorder confidence criterion;
use the quality label to configure a search, retrieval, or display operation executed by the computing device.

### Claim 17 (depends on 16)

The system of claim 16, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
using the food order data, create a predictive model of quality of the made-to-order food products;
using the predictive model, generate the reorder scores.

### Claim 18 (depends on 16)

The system of claim 16, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
using one or more exclusion criteria, determine the set of menu item data;
normalize the reorder scores across the set of menu item data.

### Claim 19 (depends on 16)

The system of claim 16, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
using a statistical test, determine when the set of reorder scores satisfies a reorder confidence criterion.

### Claim 20 (depends on 16)

The system of claim 16, wherein the instructions, when executed by the one or more processors, cause the one or more processors to:
using the reorder scores, compute a best in class score for a plurality of restaurants;
when the best in class score for a restaurant satisfies a best in class confidence criterion, cause, by a graphical interface of the system, displaying a subset of the menu item data that is associated with the restaurant having the best in class score that satisfies the best in class confidence criterion.