Recipe creation device and recipe creation tool integration device

Abstract

The present invention relates to a recipe creation device 130 for creating a recipe for causing a system that performs inspection or measurement to automatically perform inspection or measurement. The recipe creation device 130 includes: an image classification execution unit 403 that obtains an image classification code of first image data by using an image classification model 140; a cryptographic conversion unit 405 that converts the image classification code of the first image data into a first cryptographic code by using an irreversible cryptographic method; and a recipe search unit 407 that extracts a recommended recipe by collating the first cryptographic code with a recipe database 150. The image classification model has been trained with training image data, and the first image data and the training image data have been acquired under the same default conditions. Furthermore, the recipe database has registered therein: cryptographic codes obtained by converting image classification codes by using the cryptographic method in the cryptographic conversion unit; and recommended recipes obtained by deleting unique information from existing recipes for training image data classified into the image classification codes.

Description

Recipe creation device and recipe creation tool integration device

[0001] The present disclosure relates to a recipe creation device that creates recipes for automatic inspection or automatic measurement of semiconductor devices and the like, and a recipe creation tool integration device that integrates recipe creation tools created by the recipe creation device.

[0002] In recent years, semiconductor devices have become increasingly miniaturized and multi-layered, and their manufacturing processes have become extremely complex. For this reason, in order to improve the yield of semiconductor device production lines and ensure stable operation, it is important to be able to quickly and accurately inspect for defects caused by the manufacturing process.

[0003] Semiconductor device production lines are equipped with review SEMs (Scanning Electron Microscopes), which review defects based on coordinate information of defects detected by optical inspection equipment, and critical dimension SEMs (Critical Dimension-SEMs), which measure pattern dimensions. These instruments are used for detailed defect inspection and pattern measurement. Accurate inspection and measurement require the acquisition of SEM images with desirable image quality. The desirable image quality differs depending on whether the desired circuit pattern image captured in the SEM image is an edge or a flat surface. Therefore, each time an inspection or measurement is performed, workers must rely on their experience to adjust numerous parameters that affect the image quality of the circuit pattern image.

[0004] Adjusting the parameters of an inspection system is a very time-consuming task, and for example, Japanese Patent Laid-Open No. 2003-144999 discloses a technique for improving the efficiency of such parameter adjustment (recipe development).

[0005] Special table 2015-514311 publication

[0006] As such, recipe creation takes time, hindering improvements in production efficiency. Furthermore, many parameters are adjusted by workers (inline engineers) relying on their experience, making recipe creation highly dependent on individual skills. A shortage of engineers can become a bottleneck during production ramp-ups. In particular, image data included in recipes contains user intellectual property (IP), such as circuit layout information, making it difficult for anyone other than the user to share it.

[0007] A recipe creation device that is one embodiment of the present disclosure is a recipe creation device that acquires image data of a circuit pattern on a wafer using a charged particle beam device and creates a recipe for automatically inspecting or measuring the circuit pattern from the image data.The recipe creation device has an image classification execution unit that uses an image classification model to determine an image classification code of first image data acquired by the charged particle beam device according to a first initial recipe including default conditions, an encryption conversion unit that converts the image classification code of the first image data into a first encryption code using a non-reversible encryption method, and a recipe search unit that compares the first encryption code with a recipe database to extract a recommended recipe.The image classification model is trained using training image data, and the training image data is image data acquired by the charged particle beam device according to a second initial recipe.The second initial recipe is a recipe that has been modified from an existing recipe created for a specified inspection or measurement to include default conditions.The recipe database is characterized in that it registers the encryption code converted by the encryption conversion unit using the encryption method from the image classification code and a recommended recipe that has unique information deleted from the existing recipe for the training image data classified with the image classification code.

[0008] This reduces the time required to create a recipe, improves the availability of the production line, and leads to a reduction in product costs. Other objects and novel features will become apparent from the description of this specification and the accompanying drawings.

[0009] 1 is a diagram illustrating an overview of a semiconductor inspection system; FIG. 1 is an example of the hardware configuration of an information processing device (computer); FIG. 2 is a flowchart of an inspection performed by a semiconductor inspection system; FIG. 3 is a conventional inspection recipe creation flow; FIG. 4 is an example of a recipe creation screen; FIG. 5 is a functional block diagram of a recipe creation device (operation phase); FIG. 6 is an inspection recipe creation flow of Example 1; FIG. 7 is an example of a recipe creation screen of Example 1; FIG. 8 is a diagram for explaining image classification processing; FIG. 9 is a diagram for explaining image classification processing; FIG. 10 is an example of a data structure of a recipe database; FIG. 11 is a functional block diagram of a recipe creation device (preparation phase); FIG. 12 is a diagram illustrating an image classification database and recipe database creation flow of Example 1; FIG. 13 is an example of a learning screen of Example 1; FIG. 14 is a functional block diagram of a recipe creation device; FIG. 15 is a diagram illustrating a state in which a plurality of semiconductor inspection systems and a recipe creation tool integration device are connected via a network; FIG. 16 is a functional block diagram of a recipe creation tool integration device; FIG. 17 is an example of a federated learning screen of Example 2; FIG. 18 is an example of a recipe creation tool update screen of Example 2; FIG. 19 is a diagram for explaining version management of a recipe creation tool.

[0010] Hereinafter, embodiments of the present disclosure will be described with reference to the drawings.

[0011] FIG. 1A is a diagram showing an overview of a semiconductor inspection system, which is an example of a system for inspecting or measuring a wafer according to the present disclosure. The semiconductor inspection system 801 acquires image data of a circuit pattern on a wafer and analyzes the acquired image data to inspect the circuit pattern. The semiconductor inspection system 801 includes an imaging unit 101, a control unit 120, and a recipe creation device 130. The imaging unit 101 and the control unit 120 constitute a charged particle beam device for acquiring image data and performing inspection, and in this example, a scanning electron microscope (SEM) is used. Note that a semiconductor measurement system for measuring a circuit pattern has a similar configuration. Furthermore, the object to be inspected is not limited to a semiconductor wafer.

[0012] In the imaging unit 101, a primary electron beam 105 emitted from an electron source 102 is accelerated by an acceleration electrode 103 to a desired acceleration voltage value and irradiated onto a sample 109 such as a wafer. When inspecting the sidewalls or bottom portion of a circuit pattern, a control signal 113 from the control unit 120 controls a tilt deflector 107 to tilt the primary electron beam 105 and irradiate the sample 109. Methods for imaging the sidewalls of a circuit pattern include a method of controlling the irradiation angle of the primary electron beam (tilt control) and a method of tilting a stage 110 (stage control).

[0013] Irradiation with the primary electron beam 105 causes secondary electrons (SE) as signal electrons and backscattered electrons (BSE) to be emitted from the sample 109. The SEs are detected by an SE detector 112, and the BSEs are detected by a BSE detector 108, and are converted into a digital signal 114 by an A / D converter 111. The digital signal 114 is input to a control unit 120 and stored in a memory 122.

[0014] In the control unit 120, a CPU (Central Processing Unit) 121 and image processing hardware 123 perform image processing according to the purpose, and the circuit pattern on the wafer is inspected. Examples of the image processing hardware 123 include an ASIC (Application Specific Integrated Circuit), an FPGA (Field Programmable Gate Array), a DSP (Digital Signal Processor), and a GPU (Graphical Processing Unit).

[0015] In order for the semiconductor inspection system 801 to perform an appropriate inspection, it is necessary to set appropriate parameters in the imaging unit 101 and the control unit 120. The recipe creation device 130 is a device that creates an inspection recipe that determines these parameters in accordance with the circuit pattern to be inspected.

[0016] The recipe creation device 130 is realized by an information processing device (computer) 10, which includes, as shown in FIG. 1B , a processor (CPU) 11, a memory 12, a storage device 13, an input interface (I / F) 14, an output I / F 15, a communication I / F 16, and a bus 17 as its main components. The processor 11 functions as a functional unit that provides predetermined functions by executing processes according to programs loaded in the memory 12. The storage device 13 stores data and programs used by the functional unit. The input I / F 14 is connected to input devices such as a keyboard, a pointing device, and an operation panel, and the output I / F 15 is connected to a display device. The communication device I / F 16 enables communication with other information processing devices via a network. These devices are communicatively connected to each other via the bus 17. The recipe creation device 130 does not need to be realized by a single information processing device, but may be realized by multiple information processing devices. It may also be virtualized. Furthermore, some or all of the functions of the recipe creation device 130 may be realized as a cloud-based application.

[0017] In the following description, when describing processing by a program, the program or functional units may be described as the main components, but the main hardware components are a processor or an information processing device configured to include the processor. The information processing device executes processing according to a program read into memory using resources such as memory and a communication interface as appropriate through the processor. While FIG. 1B shows an example of a CPU as the processor, a GPU or the like may also be used. Furthermore, processing to realize a function is not limited to software program processing, but can also be implemented using a dedicated circuit. The dedicated circuit may be an FPGA, an ASIC, or the like.

[0018] FIG. 2 is a flowchart of the inspection of the sample 109 performed by the semiconductor inspection system 801. The sample 109 is placed on the imaging unit 101, and the inspection flow begins. First, the recipe creation device 130 performs imaging condition setting S01, which sets imaging conditions such as the number of imaging frames and the scan direction and acquires a template image for alignment, and inspection condition setting S02, which sets inspection conditions related to the inspection location and inspection detection function. The values ​​of various parameters set by the imaging condition setting S01 and inspection condition setting S02, and the template image for alignment, are called an inspection recipe. The inspection recipe created by the recipe creation device 130 is transmitted to the control unit 120, which then performs wafer imaging S03 and inspection S04 in accordance with the inspection recipe. For example, the wafer is imaged to acquire a circuit pattern image, and defect locations are identified from the circuit pattern image. Finally, the inspection result output S05 is performed. For example, the identified defect locations are displayed on the GUI of the control unit 120 together with image information and brightness information. In this way, an inspection recipe is created and the semiconductor inspection system operates in accordance with the inspection recipe, making it possible to automatically inspect wafers coming down the production line one after another.

[0019] FIG. 3A shows a conventional inspection recipe creation flow, and FIG. 3B shows a GUI for creating an inspection recipe according to the flow shown in FIG. 3A. This GUI is displayed on the display device of the recipe creation device 130. Creation of an inspection recipe begins after the name of the recipe to be created is first specified in the recipe name specification section 201 of the recipe creation screen 200. First, an imaging position setting S11 is performed to set the position to be inspected on the sample, and a template image for alignment is acquired. The template image includes an OM template image for rough alignment at low magnification using an optical microscope and an SEM template image for precise alignment at high magnification using an electron microscope. The OM alignment adjustment section 202 sets the acquisition conditions for the OM template image, and the set acquisition conditions are transmitted to the control section 120. The desired OM template image is acquired by the optical microscope (not shown) of the imaging section 101. Similarly, the SEM alignment adjustment section 203 sets the acquisition conditions for the SEM template image, and the set acquisition conditions are transmitted to the control section 120. The desired SEM template image is acquired by the imaging section 101.

[0020] Next, the imaging optical condition setting step S12 is performed. The imaging optical conditions are optical conditions set in the imaging unit 101, such as the scan speed, scan direction, and frame count, for acquiring a circuit pattern image for inspection. These optical conditions are set in the SEM imaging parameter setting section 206 on the recipe creation screen 200. The imaging optical conditions (imaging parameters) may be set as numerical values ​​or as mode selections. The set imaging optical conditions are transmitted to the control unit 120, and the imaging unit 101 performs wafer imaging S13. The captured circuit pattern image is transmitted to the recipe creation device 130. The operator creating the inspection recipe visually checks the image quality of the circuit pattern image displayed on the display device S14 and determines whether the image quality is satisfactory for the image to be inspected. If the image quality is determined to be insufficient, the process returns to the imaging optical condition setting step S12, and steps S12 to S14 are repeated until a circuit pattern image with satisfactory image quality is obtained.

[0021] If satisfactory image quality is obtained in the visual image quality confirmation S14, the process proceeds to inspection condition setting S15, where inspection parameters such as the inspection location, inspection method, and defect detection accuracy are set. The inspection location is selected by selecting a coordinate list that lists the coordinates of the inspection location in the inspection location designation section 204 of the recipe creation screen 200. The inspection parameters are selected by the defect detection function selection section 205 of the recipe creation screen 200. The set optical conditions for imaging (imaging parameters) and inspection conditions (inspection parameters) are sent to the control unit 120, which then performs inspection S16 and obtains inspection results such as defect positions and defect feature amounts from the circuit pattern image.

[0022] In the visual confirmation of inspection results S17, the operator visually confirms the inspection results obtained in the inspection S16, and returns to the setting of optical conditions for imaging S12 and repeats the processes from steps S12 to S17 until the expected results are reached.

[0023] If satisfactory inspection results are obtained in visual confirmation of the inspection results S17, the process proceeds to image quality improvement condition setting S18. In the semiconductor inspection system 801, an operator visually classifies defects from an improved image obtained by improving the image quality of a circuit pattern image. For this reason, it is desirable to improve the image quality of the circuit pattern image by adjusting the image quality so that the characteristics of the defects are clearly expressed. The image quality improvement conditions for the circuit pattern image are set in the image quality adjustment parameter adjustment unit 207 on the recipe creation screen 200. The set image quality improvement conditions are sent to the control unit 120, which then executes image quality improvement processing S19 for the circuit pattern image. In the present disclosure, the image quality improvement conditions are also treated as part of the inspection conditions (inspection parameters).

[0024] In visual confirmation S20 of the improved image, the worker visually checks the improved image obtained in the image quality improvement process S19, and returns to image quality improvement condition setting S18 and repeats steps S18 to S20 until the worker is satisfied with the image quality. A slide bar is used to adjust the parameters of the image quality adjustment parameter adjustment unit 207 so that the worker can improve the image quality intuitively.

[0025] Finally, all the parameter values ​​set from the step of setting the optical conditions for image pickup (S12) to the step of visually checking the improved image (S20) and the template image are stored as an inspection recipe (S21).

[0026] As described above, in conventional inspection recipe creation, a lot of time is required to determine appropriate parameters in the steps of setting optical conditions for imaging (S12), setting inspection conditions (S15), and setting image quality improvement conditions (S18).

[0027] In contrast, the recipe creation device 130 of this embodiment can extract existing usable inspection recipe data based on image data acquired under predetermined default conditions and keywords assigned to the image data, significantly reducing the time required for recipe creation. Furthermore, the image data required for recipe creation is confidential information that contains circuit patterns, and it is necessary to prevent such information related to user IP addresses from leaking to the outside. For this reason, the recipe creation device 130 of this embodiment conceals image classification data indicating the image data trends through encryption, and also deletes user-specific information from existing inspection recipes registered in the recipe database. Below, the functions of the recipe creation device 130 will be described separately for the operation phase in which an inspection recipe is created and the preparation phase in which an image classification database and recipe database required for the operation phase are created.

[0028] (Operation Phase) Fig. 4 is a functional block diagram of the recipe creation device 130 (operation phase) of this embodiment, Fig. 5 shows the inspection recipe creation flow of this embodiment, and Fig. 6 shows a GUI for creating an inspection recipe according to the flow of Fig. 5. Note that Fig. 5 shows an extracted flow characteristic of this embodiment in the inspection recipe creation flow, and in order to explain the overall picture of the inspection recipe creation of this embodiment, the explanation will be given with appropriate reference to the inspection recipe creation flow of Fig. 3A.

[0029] 6 is displayed on the display device of the recipe creation device 130. First, the name of the recipe to be created is specified in the recipe name specification section 201 of the recipe creation screen 200a, and creation of the inspection recipe according to this embodiment is started when the AI ​​proposal acquisition button 211 is pressed at this time. First, imaging position setting S11 is performed in the same manner as in the conventional method (see FIG. 3A).

[0030] Next, the keyword specification unit 401 receives a keyword specification S31 from the AI ​​proposal specification unit 212 on the recipe creation screen 200a. Keywords are not limited to specific content, but are preferably set so that words indicating the direction of image quality improvement processing can be selected. Even for the same circuit pattern image, the image quality that prominently expresses defect features differs depending on whether the inspection position is on an edge portion or a flat portion. To identify the direction of such image improvement processing, the AI ​​proposal specification unit 212 displays a keyword group 213, allowing the operator to select keywords indicating features of interest. Keywords may include general words that indicate image features, as well as words that indicate user-specific image features.

[0031] The recipe adjustment unit 409 creates an initial recipe in which an operator selects an inspection location in the coordinate list in the inspection location designation unit 204 of the recipe creation screen 200a, and other imaging parameters are set to predetermined default conditions. The "other imaging parameters and inspection parameters" specifically refer to parameters set in the defect detection function selection unit 205, SEM imaging parameter setting unit 206, and image quality adjustment parameter adjustment unit 207 of the recipe creation screen 200a. The recipe adjustment unit 409 transmits the initial recipe thus created to the control unit 120. The control unit 120 acquires a circuit pattern image using the imaging unit 101 in accordance with the initial recipe and transmits it to the recipe creation device 130 (S32). Note that the circuit pattern image acquired at this time does not necessarily have to be for all inspection locations in the coordinate list, but may be one or a small number of circuit pattern images.

[0032] Next, the image classification execution unit 403 performs image classification S33 on the circuit pattern image based on the specified keyword and the acquired initial recipe using the image classification model 140. The image classification process S33 will be described with reference to FIGS. 7A and 7B.

[0033] FIG. 7A shows the image classification space formed by the image classification model 140 to classify images, and FIG. 7B shows the classification results of training image data (circuit pattern images) using the image classification space in tabular form. While the image classification space 300 is shown as an example of a three-dimensional space for simplicity, it is actually an n-dimensional space in which circuit pattern images are positioned. Circles indicate the coordinates of images positioned in the image classification space 300. The coordinate axes corresponding to each dimension represent features extracted from circuit pattern images or keywords. Features extracted from circuit pattern images include high-frequency fluctuation intensity of luminance that reflects the state of edges and low-frequency fluctuation intensity of luminance that reflects the state of the background. Features extracted from keywords include combination patterns of selected keywords. In a preparation phase described below, the number of dimensions n of image classification space 300 and the n-dimensional coordinate axes are defined, and training is performed using, as learning image data, circuit pattern images captured in image classification space 300 using an initial recipe created by semiconductor inspection system 801 by applying the above-mentioned default conditions to an existing recipe previously created in image classification space 300, to obtain image classification model 140 that classifies multiple circuit pattern images that are similar to each other into image groups. Here, "similar" means that the images are located nearby in image classification space 300. Image groups 301 to 303 shown in FIG. 7A correspond to image classification codes 1 to 3 shown in FIG. 7B, respectively.

[0034] The image classification execution unit 403 inputs the circuit pattern image according to the specified keyword and the acquired initial recipe into the image classification model 140 and infers which image group the image will be classified into. The inference process corresponds to, for example, the following process: The coordinates of the acquired circuit pattern image in the image classification space 300 are calculated, and it is assumed that these coordinates are coordinates 311 shown in FIG. 7A . In this example, the image group closest to coordinates 311 is image group 303 with image classification code "3," so the image classification code "3" is output as the image classification result. Note that, although the description here is given of outputting only the image classification code of the image group closest in the image classification space 300, if there are multiple image groups within a predetermined distance from coordinates 311, the image classification codes of multiple image groups may also be output. In this case, it is preferable to add a priority order or classification certainty according to the distance from coordinates 311 to the output.

[0035] The image classification code ("3" in this example) is transferred from the image classification execution unit 403 to the encryption conversion unit 405, which then performs an encryption code calculation (S34) based on the image classification code. Here, the encryption conversion unit 405 uses a non-reversible encryption method. As an example, a cryptographic hash function is employed, and the encryption code is also referred to as a hash value. However, the algorithm used should be one published after SHA-224, such as SHA-224, SHA-256, SHA-384, SHA-512, SHA3-224, SHA3-256, SHA3-512, Tiger(2)-192 / 140128, Whirlpool, MINMAX, RIPEMD-128 / 256, or RIPEMD-140320. A cryptographic hash function is a hash function with cryptographic mathematical properties suitable for applications in information security, such as encryption, and converts an input of any length into an output of a fixed length. The original image classification code cannot be determined from the hash value, so even if the user's IP address or a related name is actually used as the image classification code to make it easier for the worker creating the recipe to understand, this information will not be leaked to the outside.

[0036] The encryption code calculated by the encryption conversion unit 405 is transferred to the recipe search unit 407, which compares it with the recipe database 150 to extract a recommended recipe (S35). Figure 8 shows the data structure of the recipe database 150. The hash value of the image classification code is registered in the encryption code 151, the recipe name 152 is registered with the name of an inspection recipe created for inspecting the circuit pattern image included in the image classification code, and the pure recipe 153 is registered with the content of the inspection recipe corresponding to the recipe name. The content of the inspection recipe registered in the pure recipe 153 is the inspection recipe minus the unique information related to the user IP (hereinafter referred to as unique information), and is hereinafter referred to as the pure recipe. For example, the parameters set in the defect detection function selection unit 205, SEM imaging parameter setting unit 206, and image quality adjustment parameter adjustment unit 207 on the recipe creation screen 200 correspond to the content registered as the pure recipe.

[0037] The recipe adjustment unit 409 creates a trial recipe by replacing the default conditions set as the initial recipe with the imaging optical conditions and inspection conditions specified in the extracted pure recipe of the recommended recipe. The recipe adjustment unit 409 transmits the created trial recipe to the control unit 120. The control unit 120 performs a trial inspection (S36) according to the trial recipe. The trial results are confirmed (S37), and if the expected results are obtained, the control unit 120 selects the trial recipe as the inspection recipe. On the other hand, if the expected results are not obtained, the control unit 120 adjusts the parameters from the imaging optical condition setting (S12) according to the flow of FIG. 3A until the expected results are achieved. If the expected results are obtained, the control unit 120 selects the trial recipe with the adjusted parameters as the inspection recipe. The new recipe storage unit 411 stores the selected inspection recipe (S21). Note that if multiple recommended recipes are available, multiple trial recipes may be created based on each recommended recipe, and an operator may select the trial recipe that produces the best trial results and adjust its parameters as necessary.

[0038] Note that irreversible encryption methods are not limited to cryptographic hash functions, and lossy compression functions, etc., can also be used. When a lossy compression function is used, the encryption code is a compressed code, and the hash value is converted into the compressed code.

[0039] In the method for creating an inspection recipe according to this embodiment, not only can the trial recipe be determined as the inspection recipe as is, but even in cases where parameter adjustment is required, adjustment can be started from parameters that already provide relatively good image quality, making it possible to create an inspection recipe more quickly than the conventional recipe creation method that requires adjustment from scratch.

[0040] (Preparation Phase) Figure 9 shows a functional block diagram of the recipe creation device 130 (preparation phase) of this embodiment, Figure 10 shows the flow for creating an image classification database and a recipe database, and Figure 11 shows a GUI for creating an image classification database in the flow of Figure 10.

[0041] The GUI shown in Fig. 11 is displayed on the display device of the recipe creation device 130. First, in the learning target designation section 501 of the learning screen 500, settings are made to acquire circuit pattern images to be registered in the image classification model 140 (see Fig. 7B). First, an inspection recipe is designated in the recipe designation section 502 (S41). Below, an example will be described in which an existing inspection recipe is designated and the preparation phase is executed, but the preparation phase may also be executed in parallel with the creation of a new inspection recipe as shown in Fig. 3A.

[0042] Next, the keyword designation unit 401 receives a keyword designation S42 from the feature of interest designation unit 504 on the learning screen 500. The keyword group 505 selectable in the feature of interest designation unit 504 is the same as the keyword group 213 selectable in the AI ​​proposal designation unit 212 on the recipe creation screen 200a.

[0043] Next, circuit pattern images (learning image data) to be used for training the image classification model 140 are acquired (S43). The circuit pattern images to be used for training the image classification model 140 are circuit pattern images acquired according to an initial recipe in which the imaging parameters and inspection parameters of the inspection recipe are replaced with predetermined default conditions. These default conditions are the same as the default conditions of the initial recipe created in the operation phase. If the operator selects the acquisition method "Execute initial recipe and capture images" in the learning image data acquisition section 503 of the learning screen 500, the recipe adjustment section 409 creates an initial recipe by replacing part of the specified inspection recipe with the default conditions. The recipe adjustment section 409 transmits the initial recipe thus created to the control unit 120. The control unit 120 acquires circuit pattern images using the imaging unit 101 according to the initial recipe and transmits them to the recipe creation device 130 (S43). Note that if a circuit pattern image already exists that has been captured according to the initial recipe, the operator selects "Existing Image" in the learning image data acquisition section 503 of the learning screen 500 and inputs the data path in which the image is saved. The image classification learning unit 413 can acquire the circuit pattern image by accessing the input data path. If learning image data is to be added (Yes in S44), the process repeats from step S41. If learning image data is not to be added (No in S44), the process proceeds to step S45.

[0044] The image classification learning unit 413 trains the image classification model 140 using the training image data (S45). For example, by projecting each circuit pattern image into an n-dimensional image classification space based on features extracted from the acquired circuit pattern image and specified keywords, multiple similar circuit pattern images are classified into image groups. Image classification can be performed using techniques such as the K-means algorithm, mixed normal distribution, Ward's method, centroid analysis, shortest (longest) distance analysis, group average analysis, and a support vector machine (a pattern recognition model using supervised learning). Alternatively, image classification using deep learning or a deep learning network such as ChatGPT, which applies transformer technology, may be used without calculating features. To perform image classification (S45), an operator sets parameters required for training the image classification model 140 in the learning control parameter setting unit 511. The types of parameters that need to be set vary depending on the image classification model. Furthermore, the learning progress display section 521 of the learning screen 500 may display the image classification space 300, and may display the projection status of the circuit pattern images into the image classification space 300 and the classification status of the circuit pattern images. The image classification learning section 413 assigns image classification codes (labels) that uniquely identify the classified image groups. For example, image classification codes 1 to 3 are assigned to the image groups 301 to 303 shown in FIG. 11 .

[0045] The image classification code (in this example, "1" to "3") set by the image classification learning unit 413 is transferred from the image classification learning unit 413 to the encryption conversion unit 405, and the encryption conversion unit 405 performs encryption code calculation S46 based on the image classification code.

[0046] On the other hand, the recipe adjustment unit 409 deletes the unique information from the inspection recipe designated in step S41 to create a pure recipe (S47).

[0047] The recipe registration unit 417 creates a recipe database 150 (see FIG. 8 ) using the image classification model 140, the encryption code obtained in step S46, and the pure recipe obtained in step S47. Specifically, it identifies which existing inspection recipe's initial recipe the circuit pattern image included in the image group with image classification code 1 was acquired using, identifies the recipe name 152 corresponding to the encryption code with the registered hash value of the image classification code, and registers the pure recipe, thereby constructing and registering the recipe database 150 (S48). The original image classification code cannot be determined from the hash value. Therefore, even if a name related to the user IP address is actually used as the image classification code to make it easier for the operator creating the recipe to understand, this information will not be leaked to the outside.

[0048] (Modification) Fig. 12 corresponds to a functional block diagram that integrates the functional block diagram of the recipe creation device 130 (operation phase) shown in Fig. 4 and the functional block diagram of the recipe creation device 130 (preparation phase) shown in Fig. 9. In Fig. 12, the actions between the functional blocks in the operation phase are indicated by solid lines, and the actions between the functional blocks in the preparation phase are indicated by dashed lines.

[0049] For example, in this embodiment, assume that an inspection recipe for which parameters have been adjusted is newly saved by the new recipe saving unit 411. In this case, the image classification model 140 and the recipe database 150 can be updated by carrying out the above-described preparation phase for the newly created inspection recipe and performing additional learning.

[0050] In Example 2, multiple semiconductor inspection systems 801 integrate the image classification models 140 and recipe databases 150 created by each semiconductor inspection system 801 via a network 802 to create an integrated image classification model 812 and an integrated recipe database 813. Typically, information related to a user IP is kept under confidential information management by the user and is not permitted to be taken outside the factory, for example. However, in the semiconductor inspection system 801 of Example 1, the output of the image classification model 140 is converted into an encrypted code, and the image classification code is converted into an encrypted code and registered in the recipe database 150. This allows the user IP information to be taken outside without being leaked to the outside. In Example 2, the high confidentiality of the method disclosed herein is utilized to integrate the image classification models created by multiple semiconductor inspection systems 801 to create an integrated image classification model.

[0051] FIG. 13A shows three semiconductor inspection systems 801a-c and a recipe creation tool integration device 803 connected via a network 802. Here, semiconductor inspection systems 801a-b are semiconductor inspection systems arranged on different production lines in the same factory (FabXX), and semiconductor inspection system 801c is a semiconductor inspection system arranged on a production line in a different factory (FabAA). FIG. 13B also shows a functional block diagram of recipe creation tool integration device 803. Recipe creation tool integration device 803 is also realized by information processing device (computer) 10 shown in FIG. 1B. Some or all of the functions of recipe creation tool integration device 803 may be realized as a cloud application.

[0052] The integration unit 811 creates an integrated image classification model 812 by performing federated learning on the image classification models 140 created by each of the recipe creation devices 130 of the semiconductor inspection systems 801a-c. By performing federated learning, the recipe creation tool integration device 803 can acquire the image classification models 140 and perform federated learning to create an integrated image classification model without sending highly confidential information, such as learning image data used to train the image classification models 140, to the recipe creation tool integration device 803, which is an external device. The integration unit 811 integrates multiple image classification spaces through federated learning and also integrates the recipe databases 150 created by each recipe creation device 130 to create an integrated recipe database 813. This allows the recipe creation tools created by each of the multiple semiconductor inspection systems to be consolidated into one, integrating the knowledge and experience of engineers.

[0053] FIG. 14 shows a GUI for causing the integration unit 811 to perform associative learning. The GUI shown in FIG. 14 is displayed on the display device of the recipe creation tool integration device 803. First, a semiconductor inspection system to be the target of associative learning is specified in the associative learning information specification section 601 of the associative learning screen 600. When a data path is specified in the integrated data path specification section 602, a list 604 of semiconductor inspection systems accessible by the recipe creation tool integration device 803 is displayed in the associative learning target selection section 603. The operator specifies the semiconductor inspection system for which associative learning is to be performed and presses the learning start button 605 to start associative learning. At this time, the operator sets parameters required for associative learning in the associative learning control parameter setting section 611. It is also preferable to display the progress of associative learning in the learning process display section 621 of the associative learning screen 600.

[0054] The integrated image classification model 812 and integrated recipe database 813 created by the recipe creation tool integration device 803 are transmitted to the recipe creation devices 130 of the semiconductor inspection systems 801a-c via the network 802 and used as the image classification model 140 and the recipe database 150. FIG. 15A shows a GUI used by the recipe creation device 130 of each semiconductor inspection system 801 to update the recipe creation tool (image classification model and recipe database) to the recipe creation tool (integrated image classification model and integrated recipe database) created by the recipe creation tool integration device 803. The GUI shown in FIG. 15A is displayed on the display device of the recipe creation device 130. Because the image classification model and recipe database used as the basis for each integrated image classification model and integrated recipe database are different, version management is performed by the integration management database 815 of the integration unit 811. For example, in the version management example shown in FIG. 15B, version management is performed using the creation date as a key. Note that the key for version management is not limited to creation timing and may be searchable from multiple perspectives, for example. The worker updates the recipe creation tool using the recipe creation tool update screen 700. When a data path is specified in the AI ​​component path specification section 701, version management information is read from the integrated management database 815, and a version list 703 is displayed in the federated learning target selection section 702. By specifying one of the versions in the version list 703 and pressing the update start button 704, the update of the recipe creation tool in the recipe creation device 130 is started.

[0055] The present disclosure is not limited to the above-described embodiments and includes various modifications. For example, the above-described embodiments have been described in detail to make the present disclosure easier to understand, and are not necessarily limited to those including all of the described configurations. Furthermore, it is possible to replace part of the configuration of one embodiment or modification with the configuration of another embodiment or modification, and it is also possible to add the configuration of another embodiment or modification to the configuration of one embodiment or modification. Furthermore, it is possible to add, delete, or replace part of the configuration of each embodiment or modification with other configurations.

[0056] 10: Information processing device (computer), 11: Processor (CPU), 12: Memory, 13: Storage device, 14: Input interface, 15: Output interface, 16: Communication interface, 17: Bus, 101: Imaging unit, 102: Electron source, 103: Acceleration electrode, 105: Primary electron beam, 107: Tilt deflector, 108: BSE detector, 109: Sample, 110: Stage, 111: A / D converter, 112: SE detector, 113: Control signal, 114: Digital signal, 120: Control unit, 121: CPU, 122: Memory, 123: Image processing hardware hardware, 130: recipe creation device, 140: image classification model, 150: recipe database, 151: encryption code, 152: recipe name, 153: pure recipe, 200: recipe creation screen, 201: recipe name specification section, 202: OM alignment adjustment section, 203: SEM alignment adjustment section, 204: inspection location specification section, 205: defect detection function selection section, 206: SEM imaging parameter setting section, 207: image quality adjustment parameter adjustment section, 211: AI proposal acquisition button, 212: AI proposal specification section, 213, 505: keyword group, 300: image classification space, 30 1, 302, 303: Image group, 311: Coordinates, 401: Keyword specification unit, 403: Image classification execution unit, 405: Encryption conversion unit, 407: Recipe search unit, 409: Recipe adjustment unit, 411: New recipe storage unit, 413: Image classification learning unit, 417: Recipe registration unit, 500: Learning screen, 501: Learning target specification unit, 502: Recipe specification unit, 503: Learning image data acquisition unit, 504: Noteworthy feature specification unit, 506: Learning start button, 511: Learning control parameter setting unit, 521: Learning process display unit, 600: Associative learning screen, 601: Associative learning information specification unit, 602: Integration Combined data path designation unit, 603: combined learning target selection unit, 604: list, 605: start learning button, 611: combined learning control parameter setting unit, 621: learning process display unit, 700: recipe creation tool update screen, 701: AI component path designation unit, 702: combined learning target selection unit, 703: version list, 704: update start button, 801: semiconductor inspection system, 802: network, 803: recipe creation tool integration device, 811: integration unit, 812: integrated image classification model, 813: integrated recipe database, 815: integration management database.

Claims

1. A recipe creation device that creates a recipe for automatically performing inspection or measurement on a circuit pattern in an image of image data obtained by a charged particle beam device on a wafer, the recipe creation device comprising: An image classification execution unit that obtains an image classification code of first image data obtained according to a first initial recipe including default conditions by the charged particle beam device using an image classification model; An encryption conversion unit that converts the image classification code of the first image data into a first encrypted code by a non-reversible encryption method; A recipe search unit that collates the first encrypted code with a recipe database to extract a recommended recipe; The image classification model is trained using learning image data, the learning image data is image data obtained according to a second initial recipe by the charged particle beam device, and the second initial recipe is an existing recipe created for a predetermined inspection or measurement, modified to include the default conditions, The recipe database registers an encrypted code obtained by converting an image classification code by the encryption conversion unit using the encryption method and a recommended recipe obtained by deleting unique information from an existing recipe of learning image data classified into the image classification code. A recipe creation device characterized by that.

2. In claim 1, The image classification model obtains an image classification code of the first image data based on the first image data and a first keyword attached to the first image data, The image classification model is trained using the learning image data and a second keyword attached to the learning image data, The first keyword and the second keyword are selected from a predetermined group of keywords including keywords indicating the direction of image quality improvement processing performed on the image of the image data. A recipe creation device characterized by that.

3. In claim 1, The recipe includes at least imaging parameters that define imaging optical conditions when the charged particle beam device acquires the image data and inspection or measurement parameters that define inspection or measurement conditions when inspecting or measuring the circuit pattern from the image of the image data. A recipe creation device characterized by that.

4. The recipe creation device according to claim 3, wherein the default conditions include the imaging optical conditions and the inspection or measurement conditions.

5. The recipe creation device according to claim 4, further comprising a recipe adjustment unit that creates a trial recipe by replacing the default conditions of the first initial recipe with the recommended recipe extracted by the recipe search unit.

6. The recipe creation device according to claim 5, further comprising a new recipe storage unit that stores a new recipe created by adjusting the imaging parameters or inspection or measurement parameters included in the trial recipe.

7. A recipe creation device that creates a recipe for automatically performing the inspection or measurement in a system that acquires image data of a circuit pattern on a wafer by a charged particle beam device and performs the inspection or measurement of the circuit pattern from the image of the image data, the recipe creation device comprising: an image classification learning unit that trains an image classification model for classifying the image data using learning image data; an encryption conversion unit that converts each image classification code classified by the image classification model into an encrypted code by an irreversible encryption method; and a recipe registration unit that creates a recipe database for registering the encrypted code obtained by converting the image classification code in association with a recommended recipe, wherein the learning image data is image data acquired by the charged particle beam device according to a second initial recipe, and the second initial recipe is a recipe obtained by modifying an existing recipe created for a predetermined inspection or measurement so as to include default conditions, and the recommended recipe is characterized in that specific information has been deleted from the existing recipe of the learning image data classified into the associated image classification code.

8. The recipe creation device according to claim 7, wherein the recipe includes at least an imaging parameter that defines imaging optical conditions when acquiring the image data by the charged particle beam device and an inspection or measurement parameter that defines inspection or measurement conditions when performing the inspection or measurement of the circuit pattern from the image of the image data.

9. The recipe creation device according to claim 8, wherein the default conditions include the imaging optical conditions and the inspection or measurement conditions.

10. In claim 9, the image classification model is trained using the learning image data and the second keyword attached to the learning image data, and the second keyword is selected from a predetermined group of keywords including a keyword indicating the direction of the image quality improvement process performed on the image of the image data. A recipe creation device characterized by this.

11. In claim 10, an image classification execution unit that obtains an image classification code of the first image data acquired according to the first initial recipe including the default conditions by the charged particle beam device using the image classification model, and the image classification code of the first image data is collated with the first encrypted code converted by the encryption method in the encryption conversion unit and the recipe database, and a recipe creation device characterized by having a recipe search unit that extracts a recommended recipe.

12. In claim 11, the image classification model obtains an image classification code of the first image data based on the first image data and the first keyword attached to the first image data, and the first keyword is selected from the group of keywords. A recipe creation device characterized by this.

13. In claim 12, further comprising a recipe adjustment unit that creates a trial recipe by replacing the default conditions of the first initial recipe with the recommended recipe extracted by the recipe search unit. A recipe creation device characterized by this.

14. In claim 13, further comprising a new recipe storage unit that stores a new recipe created by adjusting the imaging parameters or inspection or measurement parameters included in the trial recipe. A recipe creation device characterized by this.

15. In claim 14, when the new recipe is created, additional learning is performed to add the new recipe to the recipe database. A recipe creation device characterized by this.

16. A recipe creation tool integration device connected to a plurality of systems via a network, comprising a charged particle beam apparatus that acquires image data of a circuit pattern on a wafer and performs inspection or measurement of the circuit pattern from an image of the image data, and a recipe creation device that creates a recipe for automatically performing the inspection or measurement. Each of the recipe creation devices included in the plurality of systems includes an image classification learning unit that trains an image classification model for classifying the image data using learning image data, an encryption conversion unit that converts an image classification code classified by the image classification model into an encrypted code by a non-reversible encryption method, and a recipe registration unit that creates a recipe database for registering by associating the encrypted code obtained by converting the image classification code with a recommended recipe. The recipe creation tool integration device includes an integration unit that acquires the image classification model from each of the recipe creation devices of the plurality of systems, performs collaborative learning to create an integrated image classification model, and integrates the recipe databases from each of the recipe creation devices of the plurality of systems to create an integrated recipe database. The learning image data is image data acquired by the charged particle beam apparatus according to a second initial recipe, and the second initial recipe is a recipe obtained by modifying an existing recipe created for a predetermined inspection or measurement to include default conditions. The recommended recipe is characterized in that specific information has been deleted from the existing recipe of the learning image data classified into the associated image classification code.

17. The recipe creation tool integration device according to claim 16, wherein the integration unit is capable of selecting a system for integrating the image classification model and the recipe database among the plurality of systems.

18. The recipe creation tool integration device according to claim 16, wherein the integration unit manages versions of the integrated image classification model and the integrated recipe database using creation timing as a key.

19. In claim 16, for updating the image classification model and the recipe database of the recipe creation device included in each of the plurality of systems to the integrated image classification model and the integrated recipe database, respectively, the integrated image classification model and the integrated recipe database are transmitted to the recipe creation device. A recipe creation tool integration device characterized by this.

Images