JP2023171159A - Information processing device, information processing method, and program - Google Patents

Abstract

To assist users in adjusting or maintaining an electron microscope.SOLUTION: A control unit executes: acquiring a first image for confirmation that was imaged by an electron microscope from a sample for confirmation for confirming the state of the electron microscope after a prescribed adjustment is done; inputting the image for confirmation to a trained model having been trained using, as training data, a first image imaged from the sample for confirmation by the electron microscope when the adjustment results from the prescribed adjustment are good and a second image imaged from the sample for confirmation by the electron microscope when the adjustment results from the prescribed adjustment are not good, so as to acquire a first determination result of whether or not the adjustment results of the electron microscope after the prescribed adjustment is done are good; and forwarding the first determination result to an output device.SELECTED DRAWING: Figure 6

Description

The present invention relates to an information processing device, an information processing method, and a program.

Conventionally, various adjustment methods have been proposed for electron microscopes. For example, Patent Document 2 listed below describes that, when performing optical axis adjustment, a display device is provided that displays an optical axis adjustment image 15a obtained based on secondary electrons detected by a detector. .

Further, in Patent Document 3 listed below, it is an issue to quantify artificial criteria and to determine whether or not axis adjustment of a charged particle beam is necessary based on the quantified criteria. Patent Document 3 discloses that the adjustment conditions of an optical element that adjusts a charged particle beam are changed, a plurality of images are acquired under the different adjustment conditions, and the image quality is selected from among the plurality of acquired images. Selecting an acceptable image or an unacceptable image, obtaining a first image quality evaluation value based on the selected image, and using the obtained first image quality evaluation value and an image obtained by scanning the charged particle beam. A comparison is made with the second image quality evaluation value obtained from .

JP2020-74294A Japanese Patent Application Publication No. 2016-35800 Japanese Patent Application Publication No. 2010-182424 Japanese Patent Application Publication No. 2008-84565 Japanese Patent Application Publication No. 2015-2059 Japanese Patent Application Publication No. 6-325714

However, the above-mentioned conventional technology does not provide a sufficient support mechanism for users to adjust or maintain the electron microscope. Therefore, in adjusting or maintaining the electron microscope, variations may occur depending on the skill of the individual. As a result, the device may not be used in a desirable manner.

In one aspect, the present invention assists a user in adjusting or maintaining an electron microscope.

Embodiments of the present invention are exemplified by an information processing device including a control unit. The control unit is configured to obtain a first confirmation image taken by the electron microscope from a confirmation sample for confirming the state of the electron microscope after a predetermined adjustment is made, and to make adjustments based on the predetermined adjustment. A first image taken from the confirmation sample using the electron microscope when the result is good, and a second image taken from the confirmation sample using the electron microscope when the adjustment result by the predetermined adjustment is not good. The first step is to determine whether or not the adjustment result of the electron microscope is good after the predetermined adjustment is made by inputting the confirmation image to a trained model that has been trained using the images of 1 and 2 as teacher data. and outputting the first determination result to an output device.

According to this information processing device, it is possible to support the adjustment or maintenance of an electron microscope by a user.

FIG. 1 is a diagram illustrating the configuration of an information system including an electron microscope according to an embodiment. FIG. 2 is a diagram illustrating the state of the optical axis. FIG. 3 is a diagram illustrating a knob for adjusting the optical axis of the electron beam. FIG. 4 is a diagram illustrating electron microscope images taken of a sample in a state in which the optical axis of the electron beam is placed at an appropriate position and in a state in which the optical axis of the electron beam is shifted from the appropriate position. FIG. 5 is a diagram illustrating the hardware configuration of the information processing device. FIG. 6 is a diagram illustrating the program configuration and data flow in the information system. FIG. 7 is a diagram illustrating the number of learning data and the determination result of the confirmation image by the learned model. FIG. 8 is a diagram illustrating a processing flow of the information processing apparatus in this embodiment. FIG. 9 is a diagram illustrating processing of the information processing apparatus according to Modification 1 of the present embodiment. FIG. 10 is a diagram illustrating the processing of the information processing apparatus according to the second modification of the present embodiment.

Hereinafter, an electron microscope, an information system including the electron microscope, an information processing method, and a program will be described with reference to the drawings.

(System configuration)
FIG. 1 is a diagram illustrating the configuration of an information system including an electron microscope 3 according to the present embodiment. This information system includes an electron microscope 3 and an information processing device 1. The type of electron microscope 3 is not limited, and the electron microscope 3 may be, for example, a scanning electron microscope, a transmission electron microscope, or the like. Figure 1 illustrates the configuration of a scanning electron microscope.

As shown in FIG. 1, the electron microscope 3 includes an electron gun 32, an electron optical system 3EO that controls the electron beam emitted from the electron gun 32, a stage 39 on which the sample 4 is mounted, a detector 37, and a control circuit. 31.

The electron gun 32 extracts electrons from a filament or the like at a predetermined acceleration voltage and supplies an electron beam to the electron optical system 3EO. The electron optical system 3EO has functions such as shaping, converging, or deflecting an electron beam. Further, the electron optical system 3EO includes a converging lens 33, a converging aperture 34, an astigmatism correction coil 3A, an objective lens 35, and an objective aperture 36. However, the electron optical system 3EO may include a plurality of converging lenses 33 and a plurality of converging apertures 34.

The converging lens 33 controls the beam diameter of the electron beam passing through the converging aperture 34 and makes the electron beam enter the objective lens 35 and the objective aperture 36 . The astigmatism correction coil 3A controls the trajectory of the electron beam so that the cross-sectional shape of the electron beam becomes nearly circular. The objective lens 35 converges the electron beam controlled by the converging lens 33 to a minimum beam size at the surface of the sample 4, thereby forming an electron probe. The objective aperture 36 limits the electron beam converged by the converging lens 33 to the vicinity of the central axis, and converges the electron beam by the objective lens 35, thereby reducing aberrations.

The sample 4 is mounted on the stage 39. In this embodiment, the sample 4 mounted on the stage 39 when the electron microscope 3 is maintained, inspected, or adjusted is called a standard sample. The electron microscope 3 irradiates the sample 4 with an electron beam focused by an objective lens 35, detects secondary electrons or reflected electrons by a detector 37, and obtains an electron microscope image of the surface of the sample 4.

The control circuit 31 controls each part of the lens barrel and the stage 39 of the electron microscope 3 according to commands from the information processing device 1, or acquires detected values from the sensors of each part. For example, the control circuit 31 controls the emission of electrons from the electron gun 32 using a control signal C1 to the electron gun 32. For example, the control circuit 31 controls the voltage at which electrons are extracted from the electron gun 32. Further, for example, the control circuit 31 controls the convergence of the electron beam by a control signal C2 to the converging lens 33. Further, for example, the control circuit 31 corrects astigmatism of the electron beam using a control signal CA to the astigmatism correction coil 3A. Furthermore, for example, the control circuit 31 controls the electron beam to converge on the surface of the sample 4 and form a focal point using a control signal C3 to the objective lens 35. Further, the control circuit 31 deflects the electron beam using a deflection coil or an electrostatic deflection plate included in the electron optical system 3EO, and scans the sample 4. Further, the control circuit 31 generates an electron microscope image of the sample 4 based on the detection signal from the detector 37 and information on the deflection position of the electron beam. Further, the control circuit 31 controls the movement of the stage 39 using a control signal C4 to the stage 39.

The information processing device 1 sends various commands to the control circuit 31 to control each part of the electron microscope 3 or monitor each part. Further, the information processing device 1 displays an electron microscope image of the sample 4 on a display (for example, the display device 14 in FIG. 5). Note that the information processing device 1 communicates with various systems such as external computers, servers, and database systems via the network N1. The network N1 may be a Local Area Network (LAN) within the premises where the electron microscope 3 is installed, or may be a communication line connecting remote locations. The network N1 may be a dedicated line such as a Virtual Private Network (VPN) or a public network such as the Internet.

(Example of maintenance and adjustment of electron microscope)
Examples of maintenance and adjustment items for electron microscopes include the following.
(1) Replacing the filament when the filament breaks (2) Cleaning the Wehnelt electrode etc. when replacing the filament (3) Cleaning the anode (4) Replacing the focusing aperture 34 (5) Replacing the objective aperture 36 (6) Replacing the cooling fan Cleaning of the air intake port (7) Adjustment of the optical axis of the electron beam After performing steps (1) to (5), the adjustment of the optical axis (7) is performed.

FIG. 2 illustrates the state of the optical axis. FIG. 2A illustrates a state in which the optical axis of the electron beam is adjusted to an appropriate position. When the optical axis is in a proper state, the central axis of the electron beam extracted from the electron gun 32 passes through the center of the circular convergence aperture 34 and the center of the objective aperture 36, and is irradiated onto the sample 4, etc. on the stage 39. Ru.

FIG. 2B illustrates a state in which the optical axis of the electron beam is deviated from the proper position. When the optical axis of the electron beam is deviated from the proper position, for example, the central axis of the electron beam extracted from the electron gun 32 does not pass through the center of the circular convergence aperture 34, and is not aligned with the center of the convergence aperture 34. The light passes through the convergence aperture 34 with an asymmetrical cross-sectional shape. In this case, the electron beam tends to be insufficiently focused by the objective lens 35, and as a result, it becomes difficult to form an electron probe with the minimum beam size on the surface of the sample 4. Therefore, the electron microscope image obtained from sample 4 becomes difficult to focus. Note that in this case, the current of the electron beam is reduced compared to the state shown in (A) in which the optical axis is placed at an appropriate position. Furthermore, the S/N (signal/noise) ratio of the detection signal obtained from the detector 37 is lower than in the state shown in (A) in which the optical axis is placed at an appropriate position. Furthermore, the brightness of the electron microscope image of the sample 4 obtained from the detector 37 is reduced compared to the state shown in (A) in which the optical axis is placed at an appropriate position.

FIG. 3 illustrates a knob for adjusting the optical axis of the electron beam. In this embodiment, the optical axis of the electron beam is adjusted by moving the electron source of the electron gun 32 on a horizontal plane perpendicular to the central axis of the lens barrel of the electron microscope 3. The electron source of the electron gun 32 is, for example, a portion of the electron gun 32 that includes a cathode (filament), a Wehnelt electrode, and an anode. FIG. 3 illustrates knobs 32A to 32D provided on the outside of the housing of the electron gun 32. In this example, the knobs 32A and 32C adjust the position in the first axis (for example, the X axis) on a horizontal plane perpendicular to the central axis of the lens barrel. Furthermore, the knobs 32B and 32D adjust the position in the direction of a second axis (for example, the Y axis) that is perpendicular to the first axis on a horizontal plane perpendicular to the central axis of the lens barrel. The user or maintenance person of the electron microscope 3 adjusts the pair of knobs 32A and 32C or the pair of knobs 32B and 32D to align the optical axis of the electron beam with the central axis of the lens barrel of the electron microscope 3. Adjust to match. For example, the user or the maintenance person operates the knobs 32A and 32C to adjust the brightness of the electron microscope image of the sample 4 to be relatively the brightest.

FIG. 4 illustrates electron microscope images taken of the sample 4 with the optical axis of the electron beam placed at a proper position and with the optical axis of the electron beam shifted from the proper position. FIG. 4A is an electron microscope image of the sample 4 with the optical axis adjusted to an appropriate position. In addition, (B), (C), and (D) in FIG. 4 are 11.25 degrees, respectively, assuming that the positions of the knobs 32A and 32C (or knobs 32B and 32D) in the state of (A) in FIG. 4 are 0 degrees. FIG. 4 is an electron microscope image of sample 4 rotated by 22.5 degrees, 22.5 degrees, and 33.75 degrees. As already explained with reference to FIG. 3, the electron source of the electron gun 32 moves within the horizontal plane by a distance corresponding to the amount of rotation of the knobs 32A and 32C (or knobs 32B and 32D). As a result, (B), (C), and (D) in FIG. 4 are electron microscope images of the sample 4 in a state where the optical axis of the electron beam is shifted from the proper position. In FIG. 4, as shown in (A), (B), (C), and (D), as the amount of rotation of the knob, that is, the amount of deviation of the optical axis increases, the contrast of the electron microscope image decreases and the brightness decreases.

Hereinafter, in this embodiment, a correct label is set for the image in (A) of FIG. 4, an incorrect label is set for the images (B), (C), and (D) in FIG. 4, and deep learning is performed. Train the used learning system and create a trained model. In this embodiment, the information system acquires an electron microscope image taken from the sample 4 after adjusting the optical axis, inputs it into the trained model, and determines whether the optical axis of the electron beam is at an appropriate position or at a shifted position. Have them judge whether it is.

(composition)
FIG. 5 illustrates the hardware configuration of the information processing device 1. As shown in FIG. The configuration of the information processing device 1 is similar to that of a normal computer. The information processing device 1 includes a CPU 11, a main storage device 12, and external devices connected through an external interface (I/F), and executes information processing using a computer program. Examples of the external devices include the external storage device 13, the display device 14, the operating device 15, and the communication device 16. The CPU 11, main storage device 12, and external interface (I/F) can be called a control unit.

The CPU 11 executes a computer program executable loaded in the main storage device 12 and provides the functions of the information processing device 1 . The CPU 11 is also called a processor. However, the CPU 11 is not limited to a single processor, and may have a multiprocessor configuration. Further, the CPU 11 may be a single processor connected through a single socket, and may have a multi-core configuration. Further, at least part of the processing of the information processing device 1 may be a dedicated processor such as a Digital Signal Processor (DSP), a Graphics Processing Unit (GPU), a numerical calculation processor, a vector processor, an image processing processor, or an Application Specific Integrated Circuit (ASIC). may be provided by. Further, at least a portion of the information processing device 1 may be a dedicated large scale integration (LSI) such as a field-programmable gate array (FPGA) or other digital circuit. Further, at least a portion of the information processing device 1 may include an analog circuit.

The main storage device 12 is also simply called a memory, and stores computer programs executed by the CPU 11, data processed by the CPU 11, and the like. The main storage device 12 is Dynamic Random Access Memory (DRAM), Static Random Access Memory (SRAM), Read Only Memory (ROM), or the like. Further, the external storage device 13 is used, for example, as a storage area to supplement the main storage device 12, and stores computer programs executed by the CPU 11, data processed by the CPU 11, and the like. The external storage device 13 is a hard disk drive, solid state drive (SSD), or the like. Furthermore, the information processing device 1 may be provided with a drive device for a removable storage medium. The removable storage medium is, for example, a Blu-ray disc, a Digital Versatile Disc (DVD), a Compact Disc (CD), a flash memory card, or the like.

The information processing device 1 also includes a display device 14, an operating device 15, and a communication device 16. The display device 14 is, for example, a liquid crystal display, an electroluminescent panel, or the like. The operating device 15 is, for example, a keyboard, a pointing device, or the like. In this embodiment, a mouse is exemplified as the pointing device. The communication device 16 exchanges data with other devices on the network N1 (see FIG. 1).

FIG. 6 is a diagram illustrating the program configuration and data flow in this information system. This information system includes a device status acquisition program 101, a maintenance management support program 102, and a learning system 111. The device status acquisition program 101 and the maintenance management support program 102 are programs executed by the CPU 11 of the information processing device 1. The learning system 111 may be a program executed on a computer. In that case, the learning system 111 may be a system provided by the CPU 11 of the information processing device 1 executing a program in the main storage device 12. Further, the learning system 111 may be a system provided by executing a program by another computer that can communicate with the information processing device 1 through the network N1 (see FIG. 1).

Furthermore, the learning system 111 may be a system including a neural network as hardware. Furthermore, if the learning system 111 is a system including a neural network as hardware, the learning system 111 may be provided in the premises where the information processing device 1 is installed. Further, the learning system 111 may operate within the same housing as the information processing device 1. Further, in the case where the learning system 111 is a system including a neural network as hardware, the learning system 111 may be a system that can communicate with the information processing device 1 through the network N1 (see FIG. 1).

The learning system 111 creates a trained model A 112A as a first trained model, a trained model B 112B as a second trained model, etc. by learning the teacher data. The training data for creating the trained model A 112A is, for example, as explained in FIG. Including those marked with. Further, the teacher data includes data in which an incorrect label is attached to an electron microscope image taken of the sample 4 with the optical axis of the electron beam deviated from the proper position. The training data is a collection of data with these labels attached. Note that when creating such training data, adjustments other than the optical axis of the electron beam may be made, such as adjusting the convergence aperture 34.
The adjustment has been made so that there is no contamination of the lens or the objective aperture 36. The electron microscope image taken of the sample 4 with the optical axis of the electron beam adjusted to an appropriate position is the first image taken of the confirmation sample with the electron microscope 3 when the adjustment result by the predetermined adjustment is good. This is an example of an image. In addition, the electron microscope image taken of the sample 4 with the optical axis of the electron beam deviated from the proper position is the second image taken from the confirmation sample with the electron microscope 3 when the adjustment result by the predetermined adjustment was not good. This is an example of an image.

The learning system 111 includes, for example, a convolutional layer network for deep learning. The convolutional layer network may be a hardware network or may be a virtual network constructed by a computer program in the CPU 11. The learning system 111 generates a trained model A 112A in which filtering coefficients of a plurality of convolutional layers included in the convolutional layer network are adjusted by inputting the above-mentioned training data. For example, in the trained model A 112A, when a confirmation electron microscope image is input from the maintenance management support program 102, the optical axis adjustment of the electron microscope 3 from which the confirmation electron microscope image was acquired is completed. (correct answer) or unadjusted (incorrect answer). Note that, as described with reference to FIG. 4, an electron microscope image in which the optical axis has not been adjusted has lower contrast and brightness than an electron microscope image in which the optical axis has been adjusted (correct).

FIG. 7 illustrates the number of learning data and the determination result of the confirmation electron microscope image by the trained model A 112A. FIG. 7A illustrates the structure of the teacher data and the number of electron microscope images. In the example of FIG. 7, the number of electron microscope images is 60 each for correct data (TRUE) and incorrect data (FALSE). Furthermore, among the incorrect data, there are 15 pieces each with the rotation angle of the knob (see FIG. 3) of 11.25 degrees, 22.5 degrees, 33.75 degrees, and 45 degrees. In this case, when correct data and incorrect data are photographed, all adjustment items other than the optical axis have already been adjusted. Therefore, for example, the teacher data is obtained with the converging diaphragm 34, the objective diaphragm 36, etc. free from contamination and with astigmatism corrected.

FIG. 7B shows an example of the determination result for the confirmation electron microscope image by the trained model A 112A. In the judgment using trained model A 112A, the recall rate is 75%, the precision rate is 88.2%, and A result of F value of 81.1% was obtained. In addition, for electron microscope images that were taken when the optical axis had been adjusted and should be determined as correct data (TRUE), the recall rate was 90%, the precision rate was 78.3%, and the F value was 83.7%. is obtained. In this case, when the confirmation electron microscope image is taken, all adjustment items other than the optical axis have already been adjusted.

Here, the recall rate is the ratio of images determined by the learning system to be "correct" to electron microscope images whose true value is "correct." Further, the precision rate is generally an index representing how accurate the output results are in a learning system that makes judgments based on machine learning. For example, it is the percentage of electron microscope images that the learning system determines as "correct" that actually have the correct true value. The F value refers to the harmonic mean of recall and precision.

Further, for example, the training data for creating the trained model B 112B may include images taken corresponding to the degree of contamination of one or more of the convergence aperture 34 and the objective aperture 36. For example, the teacher data may include data in which a correct label is attached to an electron microscope image taken of the sample 4 when the level of contamination of the convergence aperture 34 and the objective aperture 36 is sufficiently low. In addition, the training data includes an incorrect label on an electron microscope image taken of the sample 4 when the level of contamination of one or more of the convergence aperture 34 and the objective aperture 36 has deteriorated beyond a predetermined limit. It may also include the attached data. The training data may be a collection of data with such labels. In this case, when the confirmation electron microscope image is taken, all adjustment items other than the convergence aperture 34 and the objective aperture 36 have been adjusted. An electron microscope image taken of the sample 4 when the level of contamination of the convergence aperture 34 and the objective aperture 36 is sufficiently low is an example of the third image. Further, an electron microscope image taken of the sample 4 in a state where the level of contamination of either the convergence aperture 34 or the objective aperture 36 has deteriorated beyond a predetermined limit is an example of the fourth image.

The learning system 111 generates a learned model B 112B by inputting such teacher data. As illustrated in FIG. 6, the learned model B 112B determines the state of the converging aperture 34 and objective aperture 36 of the electron microscope 3 when an electron microscope image for confirmation is input from the maintenance management support program 102. Determine. For example, the learned model B 112B determines that the contamination of the convergence aperture 34 and the objective aperture 36 in the electron microscope 3 from which the confirmation electron microscope image was acquired is sufficiently low (correct). The learned model B 112B also determines that the level of contamination of at least one of the convergence aperture 34 and the objective aperture 36 exceeds a predetermined limit (incorrect). Note that when at least one of the converging diaphragm 34 and the objective diaphragm 36 is contaminated, astigmatism increases, and the pattern in the electron microscope image taken of the surface of the sample 4 is distorted to some extent uniformly in a certain direction. It often appears as if it has been stretched in that direction.

The device status acquisition program 101 acquires various information via the control circuit 31 of the electron microscope 3. The information acquired by the device status acquisition program 101 is, for example, an electron microscope image of the sample 4, various physical quantities, and the like. Examples of various physical quantities include brightness of an electron microscope image, change in an electron microscope image during focus adjustment, astigmatism correction amount, and image contrast.

The brightness of the electron microscope image can be calculated, for example, as the average value of each pixel in the pixel array in the electron microscope image of the sample 4. The brightness of the electron microscope image may be the result of a user's judgment of relative brightness. For example, when the user operates the optical axis adjustment knobs 32A and 32C illustrated in FIG. 3, the user determines that the electron microscope image displayed on the display device 14 becomes relatively bright or dark. , the optical axis may be adjusted. The information processing device 1 may receive such adjustment results from the user.

The way the electron microscope image changes during focus adjustment is, for example, when the current of the objective lens 35 is changed, the electron microscope image displayed on the display device 14 is accompanied by parallel movement on the screen of the display device 14. The question is whether it will change or not. If the optical axis of the electron beam is deviated from the center of the lens barrel (for example, the center of the aperture of the convergence diaphragm 34), changing the current of the objective lens 35 and changing the focus of the electron beam causes electrons to appear on the surface of the sample 4. The beam irradiation position is shifted. As a result, the electron microscope image displayed on the display device 14 moves in parallel on the screen. In this way, it can be determined that the optical axis of the electron beam is deviated from the center of the lens barrel by the parallel movement on the screen of the electron microscope image corresponding to the change in the current value of the objective lens 35.

The astigmatism correction amount can be specified as the current value of the astigmatism correction coil 3A. The presence or absence of astigmatism can be identified by the deformation of the shape in the electron microscope image taken of the sample 4. For example, if the sample 4 has a known surface structure, it may be detected that a pattern in an electron microscope image of the sample 4 is uniformly distorted in a specific direction with respect to the known surface structure. Note that the presence or absence of astigmatism may be determined by the user. Furthermore, even if the user maximizes the current value of the astigmatism correction coil 3A, if the astigmatism cannot be corrected and the electron microscope image is uniformly distorted in a specific direction, the convergence diaphragm 34 or the objective diaphragm 36 There is a high possibility that the contamination has exceeded the limit. This information system judges the state of the electron microscope based on the judgment of the electron microscope image based on the learned teacher data and the input from the user. This information system supports maintenance work and adjustment work for the electron microscope 3.

(Processing flow)
FIG. 8 illustrates a processing flow of the information processing device 1 in this embodiment. This process is executed by the CPU 11 of the information processing device 1 according to a computer program executable loaded in the main storage device 12. In this process, the information processing device 1 receives an input that the optical axis adjustment of the electron beam has been adjusted (hereinafter referred to as an input that the optical axis adjustment has been completed) as an example of a predetermined adjustment (S1). Instead of the input that the optical axis has been adjusted, for example, a command from the user to determine the state of the electron microscope 3 after the optical axis adjustment may be input to the information processing device 1. When the information processing device 1 receives the input with the optical axis adjusted, it acquires an electron microscope image of the sample 4 for confirmation (S2). The electron microscope image acquired in S2 is an example of a first confirmation image, and the process of S2 is an example of acquiring the first confirmation image.

Then, the information processing device 1 inputs the electron microscope image of the sample 4 to the trained model A 12A, and obtains the determination result (S3). As described above, the learned model A 12A has already learned the electron microscope image of the sample 4 when the optical axis adjustment is good and the electron microscope image of the sample 4 when the optical axis adjustment is not good. Further, the determination result in S3 is an example of the first determination result.

In the determination result of the trained model A 12A, if the optical axis adjustment is good (OK), the information processing device 1 directly outputs to the display device 14 that the optical axis adjustment is good (S5). On the other hand, if the optical axis adjustment is not satisfactory (OK) in the determination result of the learned model A 12A, the information processing device 1 outputs an instruction to re-execute the optical axis adjustment to the display device 14 (S6). The processing in S5 and S6 is an example of outputting the first determination result.

(Effects of embodiment)
As described above, the information system of this embodiment uses the learned electron microscope image of the sample 4 when the optical axis adjustment is good and the electron microscope image of the sample 4 when the optical axis adjustment is not good. It has trained model A 12A. The information system then uses the learned model A 12A to determine the electron microscope image of the sample 4 after the optical axis adjustment. Conventionally, the quality of optical axis adjustment has been determined by, for example, a change in relative brightness of an electron microscope image displayed on the display device 4, or an electron microscope image on the screen of the display device 4 when adjusting the objective lens 35. This is determined by the user based on the presence or absence of parallel movement. As in this embodiment, by acquiring the determination result using the trained model A 12A, a determination that is not based on the user's subjectivity can be obtained in a short time. Therefore, this information system can improve functionality and usability, especially in terms of maintenance management, for electron microscope users or service personnel in charge of maintenance management.

(Modified example)
FIG. 9 illustrates the processing of the information processing device 1 according to the first modification of the present embodiment. In the process of FIG. 8, if the optical axis adjustment is not good (OK) in the determination result of the learned model A 12A, the information processing device 1 outputs an instruction to re-execute the optical axis adjustment to the display device 14, Finish the process. However, the information processing device 1 may perform further determination according to the user's operation.

In FIG. 9, the processes from S1 to S5 are the same as those in FIG. 8, so the explanation thereof will be omitted. If the optical axis adjustment is not good (OK) in the determination result of the learned model A 12A, the information processing device 1 outputs an instruction to the user to check the optical axis adjustment to the display device 14, and Waits for confirmation (S11). As explained in FIG. 8, trained model A 12A
The determination result is an example of the first determination result. Further, the process in S11 is an example of outputting an instruction to readjust the optical axis of the electron beam to the display device 14, which is an output device, when the first determination result is not favorable.

Then, the user confirms the optical axis adjustment again. Here, for example, the user operates the knobs 32A and 32C (or knobs 32B and 32D) illustrated in FIG. 3 to check whether the electron microscope image is relatively at its brightest. Further, for example, when the user adjusts the current value of the objective lens 35, the user confirms that there is no parallel movement of the electron microscope image on the screen of the display device 4, and that the movement is minimal. Through these steps, the user can confirm that the optical axis is adjusted to an appropriate position. Note that if the user recognizes that the optical axis is not adjusted to an appropriate position, the user may adjust the optical axis again using a predetermined procedure. That is, confirmation of optical axis adjustment includes readjustment of the optical axis.

Then, the information processing device 1 receives the confirmation result of the optical axis adjustment. Then, in the user's confirmation result, if the optical axis adjustment is not good (OK) (N in S12), the information processing device 1 outputs an error (S13). In this case, for example, the maintenance manager will be notified of error information and a request for maintenance work. This is because there may be a problem that cannot be resolved by user adjustment.

On the other hand, if the optical axis adjustment is found to be satisfactory (OK) in the user's confirmation result (Y in S12), the information processing device 1 acquires an electron microscope image of the sample 4 for confirmation again. Then, the information processing device 1 inputs the acquired electron microscope image of the sample 4 to the learned model B 12B and acquires the determination result (S14). Here, acquiring the electron microscope image of the confirmation sample 4 again means that the second confirmation image taken from the sample 4, which is the confirmation sample, with the electron microscope 3 after the optical axis has been readjusted. This is an example of obtaining. Further, the process in S14 is an example of obtaining a second determination result as to whether the contamination state of the aperture is below the standard.

Here, the learned model B 12B shows an electron microscope image of the sample 4 when either the convergence aperture 34 or the objective aperture 36 is contaminated, and an image when either the convergence aperture 34 or the objective aperture 36 is not contaminated. The electron microscope image of sample 4 has already been learned. If the determination result of the trained model B 12B is good (OK) (Y in S15), the information processing device 1 ends the process.

On the other hand, if the determination result of the trained model B 12B is not good (OK) (N in S15), the information processing device 1 outputs to the display device 14 an instruction to have the user correct astigmatism. The information processing device 1 then waits for the user to input the correction results (S16). Correction of astigmatism is performed by adjusting the current of the astigmatism correction coil 3A. If it is input that the result of astigmatism correction is good (OK) (Y in S17), the information processing device 1 ends the process. Note that if the determination result of the trained model B 12B is not good (OK) (N in S15), the information processing device 1 may immediately perform the process in S18 without performing the processes in S16 and S17. . In this case, the information processing device 1 outputs to the display device 14 an instruction to the user to replace at least one of the converging aperture 34 and the objective aperture 36, and to correct astigmatism after the replacement.

On the other hand, if it is input that the result of astigmatism correction is not good (OK) (N in S17), the information processing device 1 replaces at least one of the converging aperture 34 and the objective aperture 36, An instruction to the user to correct astigmatism after replacement is output to the display device 14. Then, the information processing device 1 waits for the user to input the result of the subsequent astigmatism correction (S18). When the astigmatism correction result is not good (OK), it means that the astigmatism of the electron beam cannot be adjusted to the reference range by performing the astigmatism correction. In this case, at least one of the converging diaphragm 34 and the objective diaphragm 36 is replaced. Note that the user may replace all of the converging aperture 34 and the objective aperture 36. The user then performs astigmatism correction after replacing the aperture. If it is input that the result of astigmatism correction after aperture replacement is good (OK) (Y in S19), the information processing device 1 ends the process. Note that at this time, the information processing device 1 may input the electron microscope image of the sample 4 into the learned model B 12B again and obtain the determination result.

On the other hand, if it is input that the result of astigmatism correction after replacing all of the converging aperture 34 and the objective aperture 36 is not good (OK) (N in S19), the information processing device 1 1 outputs an error (S20). In this case, for example, the maintenance manager will be notified of error information and a request for maintenance work.

According to the process of the above-described modified example, if the determination result of the trained model A 12A after optical axis adjustment is not good (OK), the information processing device 1 issues a request to confirm the optical axis adjustment again. An instruction to the user is output to the display device 14. As a result, the information processing device 1 determines the electron microscope image of the confirmation sample 4 using the learned model B 12B while confirming that the optical axis adjustment has been performed. Therefore, the information processing device 1 can more reliably determine contamination of the convergence diaphragm 34, objective diaphragm 36, etc., while excluding the state where the optical axis is not adjusted. Furthermore, if the determination result of the learned model B 12B is not good (OK) (N in S15), the information processing device 1 instructs correction of astigmatism. Therefore, even if it is determined that there is a possibility of contamination in the convergence diaphragm 34, objective diaphragm 36, etc., the information processing device 1 first instructs the user to correct astigmatism. As a result, even if there is a possibility that the convergence aperture 34, the objective aperture 36, etc. are contaminated, if it can be corrected by correcting astigmatism, there is no need to replace the convergence aperture 34, the objective aperture 36, etc. On the other hand, if the result of astigmatism correction is not satisfactory (OK), the information processing device 1 instructs replacement of at least one of the converging aperture 34 and the objective aperture 36. That is, when it is determined that the astigmatism cannot be corrected by correcting the astigmatism, the information processing device 1 instructs replacement of at least one of the converging aperture 34 and the objective aperture 36. In this way, the information processing device 1 combines the judgments made by the learned model A 12A and the learned model B 12B regarding the electron microscope image of the confirmation sample 4 with the results of the user's maintenance work on the electron microscope 3. It can support users' maintenance and management work.

FIG. 10 illustrates the processing of the information processing device 1 according to the second modification of the present embodiment. In FIG. 8 (Modification 1) above, after the user reconfirms the optical axis adjustment, the information processing device 1 inputs the electron microscope image of the sample 4 to the learned model B 12B, and determines whether or not astigmatism correction is necessary. was determined. However, instead of having the trained model B 12B make such a determination, the information processing device 1 may prompt the user to confirm. That is, when the reconfirmation result of the optical axis adjustment by the user is good (OK) (Y in S12), the information processing device 1 acquires an electron microscope image of the sample 4 for confirmation again. Then, the user is instructed to check the obtained electron microscope image of the confirmation sample 4 (S14A). As described in FIG. 9, the electron microscope image of the confirmation sample 4 that is acquired again is the second confirmation image. Therefore, the process in S14A can be considered as an example of receiving a determination regarding the image quality of the second confirmation image from the user.

If the user inputs that the confirmation result is OK (Y in S15A), the information processing device 1 ends the process. On the other hand, if the user inputs that the confirmation result is not good (OK) (N in S15A), the information processing device 1 instructs astigmatism correction (S16) and executes the following processes, as in FIG. do it.

As described above, as in Modification 1, the information processing apparatus 1 performs judgment using the learned model A 12A on the electron microscope image of the sample 4 for confirmation, and maintenance of the electron microscope 3 by the user. Combined with the management work situation. By combining these, the information processing device 1 can determine the state of the electron microscope 3 and support the user's maintenance work.

In the above embodiment, a scanning electron microscope is used as an example, and judgment of an image taken of a sample 4 using trained model A 12A, trained model B 12B, etc., optical axis adjustment, astigmatism correction, and An example of processing to support aperture replacement is illustrated. However, implementation of the present invention is not limited to the case where the electron microscope 3 is a scanning electron microscope. That is, even if the electron microscope 3 is a transmission electron microscope, the information processing device 1 can perform processing to support the user, as in the above embodiment. Note that when the electron microscope 3 is a transmission electron microscope, the image taken of the sample 4 may be, for example, an image taken from a CCD camera or a CMOS camera that takes a photo of a fluorescent screen irradiated with transmitted electrons. .

(Computer-readable recording medium)
A program that causes a computer or other machine or device (hereinafter referred to as a computer or the like) to realize any of the above functions can be recorded on a computer-readable recording medium. Then, by causing a computer or the like to read and execute the program on this recording medium, the function can be provided.

Here, a computer-readable recording medium is a recording medium that stores information such as data and programs through electrical, magnetic, optical, mechanical, or chemical action and can be read by a computer, etc. means. Among these recording media, those that can be removed from computers etc. include memory such as flexible disks, magneto-optical disks, CD-ROMs, CD-R/W, DVDs, Blu-ray discs, DAT, 8mm tapes, and flash memory. There are cards etc. In addition, there are hard disks, read only memories (ROM), and the like as recording media fixed to computers and the like. In addition, Solid State Drive
(SSD) can be used as a recording medium that is removable from a computer or the like, or as a recording medium that is fixed to the computer or the like.

1 Information processing device 3 Electron microscope 4 Sample 31 Control circuit 32 Electron gun 33 Converging lens 34 Converging aperture 35 Objective lens 36 Objective aperture 39 Stage 3A Astigmatism correction coil

Claims (9)

obtaining a first confirmation image taken by the electron microscope from a confirmation sample for confirming the state of the electron microscope after predetermined adjustments have been made;
A first image taken of the confirmation sample using the electron microscope when the adjustment result by the predetermined adjustment is good; and a first image taken from the confirmation sample by the electron microscope when the adjustment result by the predetermined adjustment is not good. The adjustment result of the electron microscope after the predetermined adjustment is made by inputting the first confirmation image to a trained model that has been trained using a second image taken from as teacher data. obtaining a first determination result as to whether or not the condition is good;
An information processing device including a control unit configured to output the first determination result to an output device. The predetermined adjustment is an optical axis adjustment of the electron beam,
The control unit outputs an instruction to readjust the optical axis of the electron beam to the output device when the first determination result is not good;
obtaining a second confirmation image taken from the confirmation sample with the electron microscope after the optical axis has been readjusted;
A third image taken from the confirmation sample by the electron microscope when the contamination state of all apertures provided in the electron microscope is below the standard and the contamination state of any aperture provided in the electron microscope are below the standard. The second image for confirmation is applied to a second trained model that has been trained using the fourth image taken from the sample for confirmation using the electron microscope as training data when the condition has deteriorated beyond the limit. obtaining a second determination result as to whether the contamination state of the aperture is below a standard by inputting the second determination result;
outputting an instruction to the output device to correct astigmatism of the electron beam when the second determination result is not good;
outputting an instruction to the output device to replace at least one aperture provided in the electron microscope when the astigmatism of the electron beam cannot be adjusted to a reference range by performing the astigmatism correction; The information processing apparatus according to claim 1, which executes the information processing apparatus. The predetermined adjustment is an optical axis adjustment of the electron beam,
The control unit outputs an instruction to readjust the optical axis of the electron beam to the output device when the first determination result is not good;
After the optical axis is readjusted, obtaining a second confirmation image taken by the electron microscope from the confirmation sample;
A determination regarding the image quality of the second confirmation image is received from a user, and when a determination that the image quality is insufficient is input, an instruction to correct astigmatism of the electron beam is output to the output device. And,
outputting an instruction to the output device to replace at least one aperture provided in the electron microscope when the astigmatism of the electron beam cannot be adjusted to a reference range by performing the astigmatism correction; The information processing apparatus according to claim 1, which executes the information processing apparatus. A computer obtains a first confirmation image taken by the electron microscope from a confirmation sample for confirming the state of the electron microscope after predetermined adjustments have been made;
A first image taken of the confirmation sample using the electron microscope when the adjustment result by the predetermined adjustment is good; and a first image taken from the confirmation sample by the electron microscope when the adjustment result by the predetermined adjustment is not good. The adjustment result of the electron microscope after the predetermined adjustment is made by inputting the first confirmation image to a trained model that has been trained using a second image taken from as teacher data. obtaining a first determination result as to whether or not the condition is good;
An information processing method comprising: outputting the first determination result to an output device. The predetermined adjustment is an optical axis adjustment of the electron beam,
The computer outputs an instruction to readjust the optical axis of the electron beam to the output device if the first determination result is not good;
obtaining a second confirmation image taken from the confirmation sample with the electron microscope after the optical axis has been readjusted;
A third image taken from the confirmation sample by the electron microscope when the contamination state of all apertures provided in the electron microscope is below the standard and the contamination state of any aperture provided in the electron microscope are below the standard. The second image for confirmation is applied to a second trained model that has been trained using the fourth image taken from the sample for confirmation using the electron microscope as training data when the condition has deteriorated beyond the limit. obtaining a second determination result as to whether the contamination state of the aperture is below a standard by inputting the second determination result;
outputting an instruction to the output device to correct astigmatism of the electron beam when the second determination result is not good;
outputting an instruction to the output device to replace at least one aperture provided in the electron microscope when the astigmatism of the electron beam cannot be adjusted to a reference range by performing the astigmatism correction; The information processing method according to claim 4, wherein the information processing method is executed. The predetermined adjustment is an optical axis adjustment of the electron beam,
The computer outputs an instruction to readjust the optical axis of the electron beam to the output device if the first determination result is not good;
After the optical axis is readjusted, obtaining a second confirmation image taken by the electron microscope from the confirmation sample;
A determination regarding the image quality of the second confirmation image is received from a user, and when a determination that the image quality is insufficient is input, an instruction to correct astigmatism of the electron beam is output to the output device. And,
outputting an instruction to the output device to replace at least one aperture provided in the electron microscope when the astigmatism of the electron beam cannot be adjusted to a reference range by performing the astigmatism correction; The information processing method according to claim 4, wherein the information processing method is executed. acquiring a first confirmation image taken by the electron microscope from a confirmation sample for confirming the state of the electron microscope after predetermined adjustments have been made to the computer;
A first image taken of the confirmation sample using the electron microscope when the adjustment result by the predetermined adjustment is good; and a first image taken from the confirmation sample by the electron microscope when the adjustment result by the predetermined adjustment is not good. The adjustment result of the electron microscope after the predetermined adjustment is made by inputting the first confirmation image to a trained model that has been trained using a second image taken from as teacher data. obtaining a first determination result as to whether or not the condition is good;
A program for outputting the first determination result to an output device. The predetermined adjustment is an optical axis adjustment of the electron beam,
outputting an instruction to the output device to cause the computer to readjust the optical axis of the electron beam when the first determination result is not good;
obtaining a second confirmation image taken from the confirmation sample with the electron microscope after the optical axis has been readjusted;
A third image taken from the confirmation sample by the electron microscope when the contamination state of all apertures provided in the electron microscope is below the standard and the contamination state of any aperture provided in the electron microscope are below the standard. The second image for confirmation is applied to a second trained model that has been trained using the fourth image taken from the sample for confirmation using the electron microscope as training data when the condition has deteriorated beyond the limit. obtaining a second determination result as to whether the contamination state of the aperture is below a standard by inputting the second determination result;
outputting an instruction to the output device to correct astigmatism of the electron beam when the second determination result is not good;
outputting an instruction to the output device to replace at least one aperture provided in the electron microscope when the astigmatism of the electron beam cannot be adjusted to a reference range by performing the astigmatism correction; 8. The program according to claim 7, for execution. The predetermined adjustment is an optical axis adjustment of the electron beam,
outputting an instruction to the output device to cause the computer to readjust the optical axis of the electron beam when the first determination result is not good;
After the optical axis is readjusted, obtaining a second confirmation image taken by the electron microscope from the confirmation sample;
A determination regarding the image quality of the second confirmation image is received from a user, and when a determination that the image quality is insufficient is input, an instruction to correct astigmatism of the electron beam is output to the output device. And,
outputting an instruction to the output device to replace at least one aperture provided in the electron microscope when the astigmatism of the electron beam cannot be adjusted to a reference range by performing the astigmatism correction; 8. The program according to claim 7, for execution.

Images