# US 2025/0148261 A1 · Cell-level analysis method of memory based on graph neural network and computing device for performing the same

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

- Number: US 2025/0148261 A1
- Document ID: US20250148261A1
- Status: Published application
- Kind: A1
- Application number: 18/622,741
- Filed: 2024-03-29
- Published: 2025-05-08
- Earliest claimed: 2023-11-02
- Assignees: Research Cooperation Foundation of Yeungnam University; Postech Research and Business Development Foundation
- Applicants: Research Cooperation Foundation of Yeungnam University; Postech Research and Business Development Foundation
- Inventors: Hyun Chul CHOI; Jeong Sik LEE; Rock Hyun BAEK; Kyeong Rae CHO
- Web page: https://patentgrep.com/patent/US20250148261A1

## CPC

- G06N 3/042: Knowledge-based neural networks; Logical representations of neural networks
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Disclosed are a cell-level analysis method of a memory and a computing device for performing the same. The cell-level analysis method of a memory is a cell-level analysis method of a memory that is executed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors, the cell-level analysis method including acquiring information on a location of each cell in the memory, generating graph-structured data for a target cell based on the location of each cell in the memory, and training a graph neural network model to predict one or more of an electrical characteristic of the target cell and a program and verify level (PV level) of the target cell by inputting the graph-structured data into the graph neural network model.

## Claims

### Claim 1

A cell-level analysis method of a memory that is executed in a computing device including one or more processors and a memory storing one or more programs executed by the one or more processors, the cell-level analysis method comprising:
acquiring information on a location of each cell in the memory;
generating graph-structured data for a target cell based on the location of each cell in the memory; and
training a graph neural network model to predict one or more of an electrical characteristic of the target cell and a program and verify level (PV level) of the target cell by inputting the graph-structured data into the graph neural network model.

### Claim 2 (depends on 1)

The cell-level analysis method of claim 1, wherein in the generating of the graph-structured data, the graph-structured data is generated by setting the target cell and a cell adjacent to the target cell as nodes in the memory and setting a connection between the target cell and the adjacent cell as an edge.

### Claim 3 (depends on 2)

The cell-level analysis method of claim 2, wherein in the generating of the graph-structured data, the target cell and the adjacent cell are determined to have a connection relationship of a joint word line when the target cell and the adjacent cell are connected in an XY axis direction based on the target cell, and the edge thereof is expressed as a first type of edge, and
the target cell and the adjacent cell are determined to have a connection relationship of a joint string line when the target cell and the adjacent cell are connected in a Z axis direction based on the target cell and the edge thereof is expressed as a second type of edge.

### Claim 4 (depends on 2)

The cell-level analysis method of claim 2, wherein the electrical characteristic is a threshold voltage of the target cell, and
in the training, the graph neural network model has a loss function of Equation below:
(Equation)
ℒ
V
th
=

V
_
th
,
2
-
V
th
,
2

2
2
Vth,2: Threshold voltage predicted by the graph neural network model
Vth,2: Threshold voltage as a correct answer.

### Claim 5 (depends on 2)

The cell-level analysis method of claim 2, wherein the training includes:
extracting a node feature from each node of the graph-structured data and extracting an edge feature from each edge;
inputting each of the extracted node feature and the edge feature into the graph neural network model; and
predicting the electrical characteristic of the target cell in one output channel among a plurality of output channels of the graph neural network model and predicting the PV level of the target cell in remaining output channels among the plurality of output channels.

### Claim 6 (depends on 2)

The cell-level analysis method of claim 2, wherein the electrical characteristic is a threshold voltage of the target cell, and
the cell-level analysis method further comprises predicting a PV level minimizing a cross-temperature effect on an erased cell in the memory using the previously trained graph neural network model.

### Claim 7 (depends on 6)

The cell-level analysis method of claim 6, wherein the predicting of the PV level minimizing the cross-temperature effect includes:
virtually programming any erased cell in the memory into a level of each of a plurality of preset states;
generating graph-structured data for a level of each state of the erased cell; and
predicting a threshold voltage for the level of each state of the erased cell by inputting the graph-structured data for the level of each state of the erased cell into the trained graph neural network model.

### Claim 8 (depends on 7)

The cell-level analysis method of claim 7, wherein the predicting of the PV level minimizing the cross-temperature effect further includes:
comparing a difference between the predicted threshold voltage for the level of each state of the erased cell and a preset threshold voltage for the level of the corresponding state; and
setting a level of a state having the smallest difference to the PV level minimizing the cross-temperature effect.

### Claim 9 (depends on 2)

The cell-level analysis method of claim 2, wherein the electrical characteristic is a threshold voltage of the target cell, and
the cell-level analysis method further comprises calculating an influence degree over a cross-temperature effect on each of the target cell and adjacent cells using the previously trained graph neural network model.

### Claim 10 (depends on 9)

The cell-level analysis method of claim 9, wherein the calculating of the influence degree includes:
selecting a target cell to be analyzed in the memory;
generating graph-structured data for the selected target cell;
inputting graph-structured data for the target cell into the trained graph neural network model and outputting a predicted threshold voltage for the target cell;
calculating a difference between the predicted threshold voltage for the target cell and an initial threshold voltage of the target cell;
calculating a gradient of each node of the graph-structured data by back-propagating the calculated difference; and
calculating the influence degree over the cross-temperature effect on each of adjacent cells of the target cell through the gradient of each node.

### Claim 11

A computing device comprising:
one or more processors;
a memory; and
one or more programs,
wherein the one or more programs are configured to be stored in the memory and executed by the one or more processors, and
the one or more programs include:
instructions for acquiring information on a location of each cell in the memory;
instructions for generating graph-structured data for a target cell based on the location of each cell in the memory; and
instructions for training a graph neural network model to predict one or more of an electrical characteristic of the target cell and a program and verify level (PV level) of the target cell by inputting the graph-structured data into the graph neural network model.

### Claim 12 (depends on 11)

The computing device of claim 11, wherein in the instructions for generating the graph-structured data, the graph-structured data is generated by setting the target cell and a cell adjacent to the target cell as nodes in the memory and setting a connection between the target cell and the adjacent cell as an edge.

### Claim 13 (depends on 12)

The computing device of claim 12, wherein in the instructions for generating the graph-structured data, the target cell and the adjacent cell are determined to have a connection relationship of a joint word line when the target cell and the adjacent cell are connected in an XY axis direction based on the target cell, and the edge thereof is expressed as a first type of edge, and
the target cell and the adjacent cell are determined to have a connection relationship of a joint string line when the target cell and the adjacent cell are connected in a Z axis direction based on the target cell and the edge thereof is expressed as a second type of edge.

### Claim 14 (depends on 12)

The computing device of claim 12, wherein the electrical characteristic is a threshold voltage of the target cell, and
the one or more programs further include instructions for predicting a PV level minimizing a cross-temperature effect on an erased cell in the memory using the previously trained graph neural network model.

### Claim 15 (depends on 14)

The computing device of claim 14, wherein the instructions for predicting a PV level minimizing a cross-temperature effect include:
instructions for virtually programming any erased cell in the memory into a level of each of a plurality of preset states;
instructions for generating graph-structured data for a level of each state of the erased cell; and
instructions for predicting a threshold voltage for the level of each state of the erased cell by inputting the graph-structured data for the level of each state of the erased cell into the trained graph neural network model.

### Claim 16 (depends on 15)

The computing device of claim 15, wherein the instructions for predicting a PV level minimizing a cross-temperature effect further include:
instructions for comparing a difference between the predicted threshold voltage for the level of each state of the erased cell and a preset threshold voltage for the level of the corresponding state; and
instructions for setting a level of a state having the smallest difference to the PV level minimizing the cross-temperature effect.

### Claim 17 (depends on 12)

The computing device of claim 12, wherein the electrical characteristic is a threshold voltage of the target cell, and
the one or more programs further include instructions for calculating an influence degree over a cross-temperature effect on each of the target cell and adjacent cells using the previously trained graph neural network model.

### Claim 18 (depends on 17)

The computing device of claim 17, wherein the instructions for calculating an influence degree include:
instructions for selecting a target cell to be analyzed in the memory;
instructions for generating graph-structured data for the selected target cell;
instructions for inputting graph-structured data for the target cell into the trained graph neural network model and outputting a predicted threshold voltage for the target cell;
instructions for calculating a difference between the predicted threshold voltage for the target cell and an initial threshold voltage of the target cell;
instructions for calculating a gradient of each node of the graph-structured data by back-propagating the calculated difference; and
instructions for calculating the influence degree over the cross-temperature effect on each of adjacent cells of the target cell through the gradient of each node.

### Claim 19

A computer program stored in a non-transitory computer readable storage medium, comprising one or more instructions that, when executed by a computing device having one or more processors, cause the computing device to perform operations of:
acquiring information on a location of each cell in the memory;
generating graph-structured data for a target cell based on the location of each cell in the memory; and
training a graph neural network model to predict one or more of an electrical characteristic of the target cell and a program and verify level (PV level) of the target cell by inputting the graph-structured data into the graph neural network model.
