# US 2021/0241076 A1 · Mismatch detection model

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

- Number: US 2021/0241076 A1
- Document ID: US20210241076A1
- Status: Published application
- Kind: A1
- Application number: 16/779,510
- Filed: 2020-01-31
- Published: 2021-08-05
- Earliest claimed: 2020-01-31
- Assignees: Walmart Apollo, LLC
- Applicants: Walmart Apollo, LLC
- Inventors: Yanxin Pan; Swagata Chakraborty; Abhinandan Krishnan; Abon Chaudhuri; Aakash Mayur Mehta; Edison Mingtao Zhang; Kyu Bin Kim
- Web page: https://patentgrep.com/patent/US20210241076A1

## CPC

- G06N 3/045: Combinations of networks
- G06N 3/043: based on fuzzy logic, fuzzy membership or fuzzy inference, e.g. adaptive neuro-fuzzy inference systems [ANFIS]
- G06N 3/0464: Convolutional networks [CNN, ConvNet]
- G06N 3/09: Supervised learning
- G06Q 30/0633: {Managing shopping lists, e.g. compiling or processing purchase lists (shipping orders G06Q10/083; order filling G06Q10/087)}
- G06N 3/08: Learning methods
- G06N 5/048: Fuzzy inferencing
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- 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 system including one or more processors and one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform obtaining a set of items that have been grouped together as matching items in a group; performing an ensemble mismatch detection; performing multiple detection models on the set of items to generate respective outputs regarding mismatches; combining the respective outputs to determine whether a quantity of detected mismatches is at least a predetermined threshold; when the quantity of detected mismatches is at least the predetermined threshold, the acts also can include separating at least one of the set of items from the group; and when the quantity of detected mismatches is not at least the predetermined threshold, the acts additionally can include maintaining each item of the set of items in the group. Other embodiments are disclosed.

## Claims

### Claim 1

A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing computing instructions configured to run on the one or more processors and perform:
obtaining a set of items that have been grouped together as matching items in a group, wherein the items in the group comprise the set of items;
performing an ensemble mismatch detection, comprising:
performing multiple detection models on the set of items to generate respective outputs regarding mismatches; and
combining the respective outputs to determine whether a quantity of detected mismatches is at least a predetermined threshold;
when the quantity of detected mismatches is at least the predetermined threshold, separating at least one of the set of items from the group; and
when the quantity of detected mismatches is not at least the predetermined threshold, maintaining each item of the set of items in the group.

### Claim 2 (depends on 1)

The system of claim 1, wherein:
the set of items consists of two items; and
the group comprises three or more items.

### Claim 3 (depends on 2)

The system of claim 2, wherein:
multiple respective instances of the ensemble mismatch detection are performed in parallel with each other on each pair of the items of the three or more items.

### Claim 4 (depends on 1)

The system of claim 1, wherein the multiple detection models comprise:
a Siamese network model with contrastive loss based at least in part on at least one of a respective title or a respective description for each of the set of items.

### Claim 5 (depends on 4)

The system of claim 4, wherein the multiple detection models further comprise:
the Siamese network model with contrastive loss based at least in part on one or more respective attributes for each of the set of items.

### Claim 6 (depends on 1)

The system of claim 1, wherein the multiple detection models comprise:
a convolutional neural network based on a respective title word matrix for each of the items.

### Claim 7 (depends on 1)

The system of claim 1, wherein the multiple detection models comprise:
a fuzzy matching based on respective titles of the items.

### Claim 8 (depends on 1)

The system of claim 1, wherein the predetermined threshold is one.

### Claim 9 (depends on 1)

The system of claim 1, wherein the multiple detection models are performed in parallel with each other on the set of items.

### Claim 10 (depends on 1)

The system of claim 1, wherein a quantity of the multiple detection models is at least three.

### Claim 11

A method being implemented via execution of computing instructions configured to run at one or more processors and stored at one or more non-transitory computer-readable media, the method comprising:
obtaining a set of items that have been grouped together as matching items in a group;
performing an ensemble mismatch detection, comprising:
performing multiple detection models on the set of items to generate respective outputs regarding mismatches, wherein the items in the group comprise the set of items; and
combining the respective outputs to determine whether a quantity of detected mismatches is at least a predetermined threshold;
when the quantity of detected mismatches is at least the predetermined threshold, separating at least one of the set of items from the group; and
when the quantity of detected mismatches is not at least the predetermined threshold, maintaining each item of the set of items in the group.

### Claim 12 (depends on 11)

The method of claim 11, wherein:
the set of items consists of two items; and
the group comprises three or more items.

### Claim 13 (depends on 12)

The method of claim 12, wherein:
multiple respective instances of the ensemble mismatch detection are performed in parallel with each other on each pair of the items of the three or more items.

### Claim 14 (depends on 11)

The method of claim 11, wherein the multiple detection models comprise:
a Siamese network model with contrastive loss based at least in part on at least one of a respective title or a respective description for each of the set of items.

### Claim 15 (depends on 14)

The method of claim 14, wherein the multiple detection models further comprises:
the Siamese network model with contrastive loss based at least in part on one or more respective attributes for each of the set of items.

### Claim 16 (depends on 11)

The method of claim 11, wherein the multiple detection models comprise:
a convolutional neural network based on a respective title word matrix for each of the items.

### Claim 17 (depends on 11)

The method of claim 11, wherein the multiple detection models comprise:
a fuzzy matching based on respective titles of the items.

### Claim 18 (depends on 11)

The method of claim 11, wherein the predetermined threshold is one.

### Claim 19 (depends on 11)

The method of claim 11, wherein the multiple detection models are performed in parallel with each other on the set of items.

### Claim 20 (depends on 11)

The method of claim 11, wherein a quantity of the multiple detection models is at least three.
