# US 12,334,299 B2 · Charged particle beam device

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

- Number: US 12,334,299 B2
- Document ID: US12334299B2
- Status: Granted
- Kind: B2
- Application number: 17/915,034
- Filed: 2020-03-31
- Published: 2023-05-25
- Granted: 2025-06-17
- Earliest claimed: 2020-03-31
- Assignees: Hitachi High-Tech Corporation
- Applicants: Hitachi High-Tech Corporation
- Inventors: U Oh; Minoru Yamazaki; Yuko Sasaki
- Web page: https://patentgrep.com/patent/US12334299B2

## CPC

- H01J 37/222: {Image processing arrangements associated with the tube}
- G01N 23/2251: using incident electron beams, e.g. scanning electron microscopy [SEM]
- G06F 16/2455: Query execution
- H01J 37/265: {Controlling the tube; circuit arrangements adapted to a particular application not otherwise provided, e.g. bright-field-dark-field illumination}
- H01J 37/28: with scanning beams {(H01J37/268, H01J37/292, H01J37/2955 take precedence)}
- G01N 2223/07: secondary emission
- G01N 2223/304: electric circuits, signal processing
- G01N 2223/306: computer control
- G01N 2223/32: adjustments of elements during operation
- G01N 2223/401: image processing
- G01N 2223/418: electron microscope
- G01N 2223/507: secondary-emission detector
- G01N 2223/6116: semiconductor wafer
- G06N 20/00: Machine learning
- H01J 2237/24521: Beam diameter
- H01J 2237/24564: Measurements of electric or magnetic variables, e.g. voltage, current, frequency
- H01J 2237/24578: Spatial variables, e.g. position, distance
- H01J 2237/2485: Electric or electronic means
- H01J: ELECTRIC DISCHARGE TUBES OR DISCHARGE LAMPS (spark-gaps H01T; electric arc lamps H05B31/00; particle accelerators H05H)
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

The present invention provides a charged particle beam device with which optimal parameters for the device can be effectively derived in a short time period. This charged particle beam device comprises: an electron gun (1) that irradiates a sample (10) with an electron beam (2); an image processing unit (901) that acquires an image of the sample (10) from a signal (12) generated by the sample (10) due to the electron beam (2); a database (604) that holds correspondence between a first parameter that is an optical condition, a second parameter that is a value pertaining to device performance, and a third parameter that is information pertaining to the device configuration, and stores a plurality of analysis values and measurement values; and a learning machine (605) that searches the database (604) and derives a first parameter that satisfies a target value of the second parameter.

## Claims

### Claim 1

A charged particle beam device comprising:
an electron gun that irradiates a sample with an electron beam;
an image processing unit that acquires an image of the sample from a signal generated by the sample due to the electron beam;
a database that holds correspondence between a first parameter that is an optical condition, a second parameter that is a value related to device performance, and a third parameter that is information on the device configuration, and stores a plurality of analysis values and measurement values; and
a learning machine that searches the database and obtains the first parameter that satisfies a target value of the second parameter.

### Claim 2 (depends on 1)

The charged particle beam device according to claim 1, wherein
the learning machine searches and obtains the third parameter from the database using the first parameter, and
searches and obtains the first parameter satisfying the target value of the second parameter from the database under the condition of the third parameter obtained by searching the database.

### Claim 3 (depends on 1)

The charged particle beam device according to claim 1, wherein
when the second parameter measured by the charged particle beam device using the first parameter obtained by searching the database does not satisfy the target value, the learning machine stores the measured second parameter and the obtained first parameter in the database in association with each other.

### Claim 4 (depends on 1)

The charged particle beam device according to claim 1, wherein
the database includes a standard database connected to a plurality of the charged particle beam devices, and
the standard database stores an analysis result performed for each of the charged particle beam devices by the learning machine of each of the charged particle beam devices.

### Claim 5 (depends on 1)

The charged particle beam device according to claim 1, wherein
the database is provided outside the charged particle beam device.

### Claim 6 (depends on 1)

The charged particle beam device according to claim 1, further comprising
an operation screen unit that displays the first parameter stored in the database.
