# US 2024/0193488 A1 · Systems and methods for leveraging a knowledge graph

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

- Number: US 2024/0193488 A1
- Document ID: US20240193488A1
- Status: Published application
- Kind: A1
- Application number: 18/063,671
- Filed: 2022-12-08
- Published: 2024-06-13
- Earliest claimed: 2022-12-08
- Assignees: JPMorgan Chase Bank, N.A.
- Applicants: Jpmorgan Chase Bank, N.A.
- Inventors: Sadra AMIRI MOGHADAM; Reza MOMENIFAR; Gupta GUNDLAPALLI; Janelle GHANEM; Wanying DING; Anagha RUMADE; Javier ORTIZ
- Web page: https://patentgrep.com/patent/US20240193488A1

## CPC

- G06N 20/20: Ensemble learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N 20/00: Machine learning
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

In some aspects, the techniques described herein relate to a method including: embedding a graph with an embedding model, wherein the embedding generates node and edge vectors for each node and each edge, respectively, in the graph; generating peer node groups based on the node vectors and the edge vectors; generating edge predictions based on the node vectors and the edge vectors; training a machine learning model based on the node vectors and the edge vectors; inputting the node vectors and the edge vectors into the machine learning model; receiving, as output from the machine learning model, a prediction of a future action based on the node vectors and the edge vectors; generating a plurality of insights based on the peer node groups, the edge predictions, and the prediction of a future action; storing the plurality of insights in an insight database, and providing an interface to the insight database.

## Claims

### Claim 1

A method comprising:
embedding a graph with an embedding model, wherein the embedding generates node vectors and edge vectors for each node and each edge, respectively, in the graph;
generating peer node groups based on the node vectors and the edge vectors;
generating edge predictions based on the node vectors and the edge vectors, wherein the edge predictions are further based on a distance between a head node and a tail node;
training a machine learning model based on the node vectors and the edge vectors;
inputting the node vectors and the edge vectors into the machine learning model;
receiving, as output from the machine learning model, a prediction of a future action based on the node vectors and the edge vectors;
generating a plurality of insights based on the peer node groups, the edge predictions, and the prediction of a future action; and
storing the plurality of insights in an insight database.

### Claim 2 (depends on 1)

The method of claim 1, wherein the machine learning model is a gradient-boosted decision tree model.

### Claim 3 (depends on 1)

The method of claim 1, wherein the peer node groups are based on inclusion in a predefined vector space.

### Claim 4 (depends on 1)

The method of claim 1, comprising:
performing dynamic embedding of the graph, including periodic embedding of historical graphs generated over predefined time periods.

### Claim 5 (depends on 1)

The method of claim 1, comprising:
exposing node and edge attributes to the machine learning model, wherein the prediction of the future action is further based on the node and edge attributes.

### Claim 6 (depends on 1)

The method of claim 1, wherein the graph data is stored in a graph database.

### Claim 7 (depends on 6)

The method of claim 6, comprising:
providing a user application, wherein the user application includes an interface to the graph database and an interface to the insight database.

### Claim 8

A system comprising at least one computer wherein the at least one computer includes a processor, and wherein the at least one computer is configured to:
embed a graph with an embedding model, wherein the embedding generates node vectors and edge vectors for each node and each edge, respectively, in the graph;
generate peer node groups based on the node vectors and the edge vectors;
generate edge predictions based on the node vectors and the edge vectors, wherein the edge predictions are further based on a distance between a head node and a tail node;
train a machine learning model based on the node vectors and the edge vectors;
input the node vectors and the edge vectors into the machine learning model;
receive, as output from the machine learning model, a prediction of a future action based on the node vectors and the edge vectors;
generate a plurality of insights based on the peer node groups, the edge predictions, and the prediction of a future action; and
store the plurality of insights in an insight database.

### Claim 9 (depends on 8)

The system of claim 8, wherein the machine learning model is a gradient-boosted decision tree model.

### Claim 10 (depends on 8)

The system of claim 8, wherein the peer node groups are based on inclusion in a predefined vector space.

### Claim 11 (depends on 8)

The system of claim 8, wherein the at least one computer is configured to perform dynamic embedding of the graph, including periodic embedding of historical graphs generated over predefined time periods.

### Claim 12 (depends on 8)

The system of claim 8, wherein the at least one computer is configured to expose node and edge attributes to the machine learning model, wherein the prediction of the future action is further based on the node and edge attributes.

### Claim 13 (depends on 8)

The system of claim 8, wherein the graph data is stored in a graph database.

### Claim 14 (depends on 13)

The system of claim 13, wherein the at least one computer is configured to provide a user application, wherein the user application includes an interface to the graph database and an interface to the insight database.

### Claim 15

A non-transitory computer readable storage medium, including instructions stored thereon, which instructions, when read and executed by one or more computer processors, cause the one or more computer processors to perform steps comprising:
embedding a graph with an embedding model, wherein the embedding generates node vectors and edge vectors for each node and each edge, respectively, in the graph;
generating peer node groups based on the node vectors and the edge vectors;
generating edge predictions based on the node vectors and the edge vectors, wherein the edge predictions are further based on a distance between a head node and a tail node;
training a machine learning model based on the node vectors and the edge vectors;
inputting the node vectors and the edge vectors into the machine learning model;
receiving, as output from the machine learning model, a prediction of a future action based on the node vectors and the edge vectors;
generating a plurality of insights based on the peer node groups, the edge predictions, and the prediction of a future action; and
storing the plurality of insights in an insight database.

### Claim 16 (depends on 15)

The non-transitory computer readable storage medium of claim 15, wherein the machine learning model is a gradient-boosted decision tree model.

### Claim 17 (depends on 15)

The non-transitory computer readable storage medium of claim 15, wherein the peer node groups are based on inclusion in a predefined vector space.

### Claim 18 (depends on 15)

The non-transitory computer readable storage medium of claim 15, comprising:
performing dynamic embedding of the graph, including periodic embedding of historical graphs generated over predefined time periods.

### Claim 19 (depends on 15)

The non-transitory computer readable storage medium of claim 15, comprising:
exposing node and edge attributes to the machine learning model, wherein the prediction of the future action is further based on the node and edge attributes.

### Claim 20 (depends on 15)

The non-transitory computer readable storage medium of claim 15, wherein the graph data is stored in a graph database, wherein the at least one computer is configured to provide a user application, and wherein the user application includes an interface to the graph database and an interface to the insight database.
