# US 2025/0156729 A1 · Device and method for embedding knowledge graph

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

- Number: US 2025/0156729 A1
- Document ID: US20250156729A1
- Status: Published application
- Kind: A1
- Application number: 18/921,243
- Filed: 2024-10-21
- Published: 2025-05-15
- Earliest claimed: 2023-11-15
- Assignees: Electronics and Telecommunications Research Institute
- Applicants: Electronics and Telecommunications Research Institute
- Inventors: Chon Hee Lee; Dong-oh Kang
- Web page: https://patentgrep.com/patent/US20250156729A1

## CPC

- G06N 3/0985: Hyperparameter optimisation; Meta-learning; Learning-to-learn
- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N 3/0495: Quantised networks; Sparse networks; Compressed networks
- G06N 5/022: Knowledge engineering; Knowledge acquisition
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Provided are a device and method for embedding a knowledge graph. The device includes an acquisition module configured to acquire a knowledge graph embedding model and a tuning module configured to generate a low-dimensional embedding model by performing hyperparameter tuning on the acquired knowledge graph embedding model on the basis of grid search.

## Claims

### Claim 1

A device for embedding a knowledge graph, the device comprising:
an acquisition module configured to acquire a knowledge graph embedding model; and
a tuning module configured to generate a low-dimensional embedding model by performing hyperparameter tuning on the acquired knowledge graph embedding model on the basis of grid search.

### Claim 2 (depends on 1)

The device of claim 1, further comprising a quantization module configured to lightweight the low-dimensional embedding model by quantizing entity embedding vectors of the low-dimensional embedding model.

### Claim 3 (depends on 2)

The device of claim 2, wherein the quantization module performs quantization in a specified size of qt that is calculated using the following expression:
q
t
=
M
2
-
M
1
2
B
-
1
where B is a number of bits for storing one piece of data of an entity embedding vector, M1 is a smallest value among elements of the entity embedding vectors, and M2 is a largest value among the elements of the entity embedding vectors.

### Claim 4 (depends on 3)

The device of claim 3, wherein, when the knowledge graph embedding model is a TransE model, the quantization module quantizes the entity embedding vectors of the TransE model using the following expression:
Q
B
,
M
1
,
M
2
(
x
)
=
round
⁢
(
x
q
i
)
-
round
⁢
(
M
1
q
t
)
where round(y) is a function of rounding a value of y off at a first decimal place, and
the quantization module divides relation embedding vectors of the TransE model into a quantization size of the entity embedding vectors.

### Claim 5 (depends on 3)

The device of claim 3, wherein, when the knowledge graph embedding model is a SimplE model, a ComplEx model, or a RotatE model, the quantization module quantizes entity embedding vectors of the embedding model using the following expression:
Q
B
,
M
1
,
M
2
′
(
x
)
=
round
⁢
(
x
q
i
)
where round(y) is a function of rounding a value of y off at a first decimal place.

### Claim 6 (depends on 2)

The device of claim 2, further comprising a reordering module configured to reorder the lightweighted low-dimensional embedding model based on a specified criterion.

### Claim 7 (depends on 6)

The device of claim 6, wherein the reordering module calculates similarities between the lightweighted low-dimensional embedding model and a pivot vector and orders the lightweighted low-dimensional embedding model in order of the calculated similarities.

### Claim 8 (depends on 6)

The device of claim 6, further comprising a searcher configured to acquire a search result corresponding to a query from the lightweighted low-dimensional embedding model.

### Claim 9 (depends on 8)

The device of claim 8, wherein, when a first similarity distance between each of the entity embedding vectors and a pivot table is larger than or equal to a second similarity distance between the query and the pivot table, the searcher determines an entity embedding vector for which a difference obtained by subtracting the second similarity distance from the first similarity distance is a maximum of current top-k values as the search result corresponding to the query among the entity embedding vectors.

### Claim 10 (depends on 8)

The device of claim 8, wherein, when a first similarity distance between each of the entity embedding vectors and a pivot table is smaller than a second similarity distance between the query and the pivot table, the searcher determines an entity embedding vector for which a difference obtained by subtracting the first similarity distance from the second similarity distance is a maximum of current top-k values as the search result corresponding to the query among the entity embedding vectors.

### Claim 11

A device for embedding a knowledge graph, the device comprising:
a tuning module configured to generate a low-dimensional embedding model by performing hyperparameter tuning on a knowledge graph embedding model on the basis of grid search; and
a reordering module configured to reorder the low-dimensional embedding model based on a specified criterion.

### Claim 12 (depends on 11)

The device of claim 11, wherein the reordering module calculates similarities between the low-dimensional embedding model and a pivot vector and orders the lightweighted low-dimensional embedding model in order of the calculated similarities.

### Claim 13 (depends on 11)

The device of claim 11, further comprising a quantization module configured to lightweight the low-dimensional embedding model by quantizing entity embedding vectors of the low-dimensional embedding model.

### Claim 14 (depends on 11)

The device of claim 11, further comprising a searcher configured to acquire, when a query is acquired, a search result corresponding to the query on the basis of similarities between the query and the low-dimensional embedding model.

### Claim 15

A method of embedding a knowledge graph, the method comprising:
acquiring a knowledge graph embedding model; and
generating a low-dimensional embedding model by performing hyperparameter tuning on the acquired knowledge graph embedding model on the basis of grid search.

### Claim 16 (depends on 15)

The method of claim 15, comprising lightweighting the low-dimensional embedding model by quantizing entity embedding vectors of the low-dimensional embedding model in a specified size of qt that is calculated using the following expression:
q
t
=
M
2
-
M
1
2
B
-
1
where B is a number of bits for storing one piece of data of an entity embedding vector, M1 is a smallest value among elements of the entity embedding vectors, and M2 is a largest value among the elements of the entity embedding vectors.

### Claim 17 (depends on 16)

The method of claim 16, wherein the lightweighting of the low-dimensional embedding model comprises:
when the knowledge graph embedding model is a TransE model, quantizing the entity embedding vectors of the TransE model using the following expression:
Q
B
,
M
1
,
M
2
(
x
)
=
round
⁢
(
x
q
i
)
-
round
⁢
(
M
1
q
t
)
where round(y) is a function of rounding a value of y off at a first decimal place; and
dividing relation embedding vectors of the TransE model into a quantization size of the entity embedding vectors.

### Claim 18 (depends on 16)

The method of claim 16, wherein the lightweighting of the low-dimensional embedding model comprises:
when the knowledge graph embedding model is a SimplE model, a ComplEx model, or a RotatE model, quantizing entity embedding vectors of the embedding model using the following expression:
Q
B
,
M
1
,
M
2
′
(
x
)
=
round
⁢
(
x
q
i
)
where round(y) is a function of rounding a value of y off at a first decimal place.

### Claim 19 (depends on 16)

The method of claim 16, further comprising:
calculating similarities between the lightweighted low-dimensional embedding model and a pivot vector; and
ordering the lightweighted low-dimensional embedding model in order of the calculated similarities.

### Claim 20 (depends on 16)

The method of claim 16, further comprising acquiring a search result corresponding to a query on the basis of similarities between the query and the lightweighted low-dimensional embedding model.
