Problem machine positioning method and device, medium and product

Abstract

The embodiment of the invention relates to the technical field of semiconductor processing, and discloses a defective machine positioning method and device, a medium and a product. The method comprises the following steps: acquiring a production wafer picture acquired in a production process and a contrast wafer picture in an in-plant defect knowledge base; processing the production wafer picture and the contrast wafer picture through a visual algorithm, extracting feature points, and converting the feature points into feature vectors; performing similarity calculation on the feature vector of the production wafer picture and the feature vector of the contrast wafer picture; according to a preset matching threshold value, outputting the production wafer pictures of which the similarity is greater than the matching threshold value to obtain a defect wafer set; and classifying and concluding the defective wafer set, and positioning a defective machine. The technical problem that a faulty machine cannot be accurately positioned can be solved at least.

Description

Technical Field

[0001] The present application relates to the field of semiconductor processing technology, and in particular to a method, device, medium and product for positioning a problem machine. Background Art

[0002] In the semiconductor production process, it is crucial to quickly and accurately detect equipment problems and defects to ensure product quality. The wafer manufacturing process is complex and involves multiple process steps and equipment. Each process step may cause defects due to equipment abnormalities or deviations in process parameters. If these defects are not discovered and handled in a timely manner, they will affect the performance and yield of the final product. Therefore, how to effectively monitor the equipment status during the production process and quickly locate and solve the problem machine (dog tool) is one of the important technical challenges in the field of semiconductor production.

[0003] At present, in semiconductor manufacturing, defect detection mainly relies on various advanced detection equipment, such as optical microscopes, electron microscopes, etc., which capture high-resolution images of the wafer surface and analyze the images to find defects. These detection equipment can detect various defects including particles, scratches, pits, etc. However, relying solely on the static image information provided by the detection equipment, it is difficult to monitor the equipment status in real time and cannot quickly locate the specific source of the equipment problem. The application of image processing methods in semiconductor manufacturing still faces some challenges. For example, how to effectively extract key image features related to equipment problems and how to accurately calculate the similarity of these features in order to quickly identify and locate the problem machine still needs further research and optimization. Summary of the invention

[0004] One purpose of the present application is to provide a method, device, medium and product for locating a problematic machine, at least to solve the problem of being unable to accurately locate the problematic machine.

[0005] To achieve the above objectives, some embodiments of the present application provide the following aspects:

[0006] In the first aspect, some embodiments of the present application also provide a method for locating a problematic machine, comprising obtaining production wafer images collected during the production process and reference wafer images in a defect knowledge base within the factory; processing the production wafer images and the reference wafer images through a visual algorithm, extracting feature points, and converting the feature points into feature vectors; performing similarity calculations on the feature vectors of the production wafer images and the feature vectors of the reference wafer images; based on a pre-set matching threshold, outputting production wafer images whose similarity is greater than the matching threshold to obtain a defective wafer set; classifying and summarizing the defective wafer set to locate the problematic machine.

[0007] In a second aspect, some embodiments of the present application further provide an electronic device, comprising: one or more processors; and a memory storing computer program instructions, wherein the computer program instructions, when executed, cause the processor to perform the steps of the method described above.

[0008] In a third aspect, some embodiments of the present application further provide a computer-readable medium having computer program instructions stored thereon, wherein the computer program instructions can be executed by a processor to implement the method as described above.

[0009] In a fourth aspect, some embodiments of the present application further provide a computer program product, comprising a computer program / instruction, which implements the steps of the method described above when executed by a processor.

[0010] Compared with the related art, the solution provided in the embodiment of the present application introduces a positioning method based on the similarity of feature point images, which significantly improves the efficiency and accuracy of defect detection and problem machine positioning in the semiconductor production process. Using advanced visual algorithms and multi-dimensional feature point extraction technology, this method can quickly analyze the defect characteristics on the surface of the wafer and achieve accurate similarity calculation and matching. Compared with the prior art, this method not only improves the accuracy and speed of detection, but also provides richer and more detailed defect information, which helps to identify equipment problems more quickly and perform effective maintenance, thereby improving product yield and production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] One or more embodiments are exemplarily described by pictures in the corresponding drawings, and these exemplified descriptions do not constitute limitations on the embodiments. Elements with the same reference numerals in the drawings represent similar elements, and unless otherwise stated, the figures in the drawings do not constitute proportional limitations.

[0012] Figure 1 A schematic diagram of a flow chart of a method for locating a problematic machine according to an embodiment of the present application;

[0013] Figure 2 The present invention is a schematic diagram of the structure of an electronic device provided according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] In order to make the purpose, technical solution and advantages of the embodiments of the present application clearer, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0015] First embodiment

[0016] The first embodiment of the present application relates to a method for locating a problem machine. Figure 1 As shown, the method may include the following steps:

[0017] S101, obtaining production wafer images collected during the production process and reference wafer images in a defect knowledge base within the factory;

[0018] S102, processing the production wafer image and the control wafer image by a visual algorithm, extracting feature points, and converting the feature points into feature vectors;

[0019] S103, performing similarity calculation on the feature vector of the production wafer image and the feature vector of the reference wafer image;

[0020] S104, according to a preset matching threshold, outputting production wafer images whose similarity is greater than the matching threshold to obtain a defective wafer set;

[0021] S105, classifying and summarizing the defective wafer set and locating the problematic machine.

[0022] The following is a detailed description of each of the above steps.

[0023] For step S101, production wafer images and reference wafer images are obtained. During the semiconductor production process, production equipment will produce various defects on the wafer. This step includes obtaining images of the currently produced wafers from the production line and obtaining reference wafer images from the defect knowledge base within the factory. Production wafer images are high-resolution images that can be captured by online detection equipment (such as optical microscopes, electron microscopes, etc.), which contain actual defect information on the current wafer surface. The reference wafer images are selected from historical data, including various typical defects previously detected and corresponding root cause information. These reference images are used as references for subsequent feature matching and defect location.

[0024] For step S102 feature point extraction and feature vector conversion, this step uses a visual algorithm to process the production wafer image and the control wafer image. First, edge detection, corner detection, and spot detection algorithms are used to extract key feature points in the image. Edge detection can highlight the edge and contour information of the wafer surface; corner detection is used to find corners or corner points in the image; spot detection identifies local features such as dots and spots. After extracting these feature points, they are further converted into feature vectors. The generation of feature vectors allows the features of each image to be digitized and standardized for subsequent similarity calculations.

[0025] For step S103 similarity calculation, after obtaining the feature vectors of the production wafer image and the reference wafer image, similarity calculation is performed. The purpose of similarity calculation is to measure the similarity between the defect features in the production wafer image and the existing defects in the reference wafer image.

[0026] For step S104 of screening defective wafer sets, based on the results of similarity calculation, the production wafer images with similarity greater than the threshold will be screened out according to the pre-set matching threshold. The matching threshold is set based on experience and experimental data, with the aim of minimizing the missed detection rate while ensuring the accuracy of the matching results. The screened production wafer images are regarded as samples with potential defects to form a defective wafer set.

[0027] For step S105 classification and induction and location of problematic machines, after obtaining the defective wafer set, these samples are further classified and summarized. The classification criteria include the type of defect (such as particles, scratches, pits, etc.), the location of the defect (such as a specific layer, area), and the severity of the defect. Through these classifications, different types of defect patterns can be identified, and these patterns can be compared and analyzed with the problematic machine information in the historical data. Finally, based on the results of the comprehensive analysis, possible equipment problems and specific faulty machines are determined, and the problematic machines are located. This process helps to quickly identify and solve equipment problems that occur during the production process, prevent further defects from occurring, and improve production efficiency and product quality.

[0028] It is not difficult to find that compared with the related art, the solution provided in the embodiment of the present application can quickly screen and classify the defective wafer sets that appear in the production process by using visual algorithms to extract feature points of wafer images and perform feature vectorization, combined with similarity calculation methods and preset matching thresholds, so as to accurately locate the problem machine. The speed and accuracy of defect detection are significantly improved, the possibility of misjudgment and missed judgment is reduced, and more abundant defect information is provided, which helps to identify equipment problems in a timely manner and implement effective maintenance and repair measures, thereby improving production yield and product quality.

[0029] Second embodiment

[0030] The second embodiment of the present application relates to a method for locating a problem machine. The second implementation is an improvement on the first embodiment, and the specific improvements are:

[0031] Extracting feature points includes edge detection, corner detection and spot detection. These feature points can also be other local features related to the equipment status. The results of edge detection, corner detection and spot detection will provide different types of feature point information respectively. These feature point information will form the feature vector of the wafer image through further feature vectorization processing, which will serve as the basis for subsequent similarity calculation. Each detection method has its own focus. Edge detection mainly captures shape contours, corner detection is used to capture significant corners in the image, and spot detection focuses on specific brightness areas in the image. By combining the results of the three detection methods, richer and more comprehensive feature point information can be obtained, which helps to improve the accuracy of defect detection and problem machine positioning.

[0032] Edge detection is to extract image edge features by identifying the parts of the image where the grayscale value changes significantly. The Canny edge detection algorithm can be used, which includes the following steps: use a Gaussian filter to smooth the wafer image to reduce the impact of noise; calculate the gradient amplitude and direction of each pixel in the image to identify the direction and intensity of grayscale changes; suppress the gradient of non-edge points and retain the pixels with the largest amplitude in the local gradient direction to accurately locate the edge; set two high and low thresholds, determine the edge pixels through the double threshold connection method, and extract the complete edge information of the image.

[0033] Corner detection is used to identify feature points with obvious corners or turning points in an image. The Harris corner detection algorithm can be used, and its main steps are as follows: calculate the gradient of the image in the x and y directions; use the image gradient to construct the Harris matrix to represent the autocorrelation matrix of the local window of the image; use the Harris corner response function to calculate the corner response value of each pixel to determine whether it is a corner point; corner location screens out points with larger response values ​​by setting a threshold, and performs non-maximum suppression on these points to accurately locate the corner point position.

[0034] Blob detection is used to identify areas with specific brightness or color in an image (such as small dots, spots, etc.). The Laplacian of Gaussian (LoG) algorithm can be used, and its main steps include: using the Gaussian filter to smooth the image and reduce noise; applying the Laplacian operator: applying the Laplacian operator to the smoothed image, calculating the second-order derivative of the image, and highlighting the blob features in the image; through multi-scale detection, normalizing the response value of the blob to ensure that the blob features of different sizes are detected; setting a threshold according to the response value of the blob to identify and locate the location of the blob.

[0035] The conversion of feature points into feature vectors includes generating a feature descriptor for each feature point using a SIFT algorithm or a SURF algorithm, and constructing a feature vector of the image.

[0036] The SIFT (Scale Invariant Feature Transform) algorithm is a widely used feature extraction algorithm. Its main steps are as follows: Generate a multi-scale representation of the image through Gaussian blur. At each scale, calculate the Gaussian difference (DoG) of the image to detect potential feature points; locate the potential feature points by performing extreme value detection on the DoG image, and further determine the key points through precise positioning; assign one or more main directions to each key point based on the gradient direction distribution of the key point neighborhood to make it rotation invariant; in the local area around the key point, use a 128-dimensional vector to represent the feature descriptor, which consists of statistical information of the local gradient direction and can describe the local image characteristics of the key point.

[0037] The SURF (Speeded Up Robust Features) algorithm is a feature extraction algorithm that is faster than SIFT. Its main steps include: constructing an integral image of the image to accelerate feature point detection and feature descriptor calculation; calculating the determinant of the Hessian matrix at different scales to detect potential feature points. The Haar wavelet response is used to determine the main direction of the feature point; detecting the local extreme points of the Hessian determinant, determining the key points, and assigning the main direction to each key point through the Haar wavelet response; in the local area around the key point, a 64-dimensional vector is used to represent the feature descriptor. The SURF descriptor generates a compact descriptor by statistically analyzing the gradient information of the local area.

[0038] Feature vector construction, for each detected feature point, the feature descriptors generated by the SIFT or SURF algorithm are used to combine these descriptors into a feature vector. Each feature vector is composed of a collection of multiple feature descriptors, and the dimension of the descriptor determines the dimension of the feature vector (128 dimensions for SIFT and 64 dimensions for SURF). The feature vector is normalized to reduce the impact of illumination changes or image scaling. The standardized feature vector is stored as the final form of image feature representation for subsequent similarity calculations.

[0039] Through the above process, the feature points in the production wafer image and the control wafer image are converted into standardized feature vectors. The feature vector effectively captures the local information of different feature points in the image, making the subsequent similarity calculation more reliable and accurate. This method can handle complex image features, provide robust feature matching capabilities, and is suitable for different image conditions.

[0040] Similarity calculation includes calculation through cosine similarity or Euclidean distance. In the specific implementation process, cosine similarity and Euclidean distance each have their own advantages and disadvantages. Cosine similarity is sensitive to the direction of the vector, but does not consider the size of the vector, and is suitable for measuring directional similarity; Euclidean distance directly measures the absolute distance between vectors, and is suitable for measuring size similarity. According to actual needs and the nature of image features, a suitable method can be selected for similarity calculation. Regardless of which method is used, an appropriate matching threshold must be set to determine whether there is a valid feature match, so as to screen out wafer image sets that may have defects.

[0041] Cosine similarity is used to calculate the cosine value of the angle between two vectors to measure their similarity. The specific steps include obtaining the feature vectors of the production wafer image and the control wafer image; calculating the dot product of the two feature vectors, that is, the numerator; calculating the modulus of the two feature vectors, that is, the denominator; dividing the dot product by the product of the modulus of the two vectors to obtain the cosine similarity value. The value range of cosine similarity is [-1, 1 =, where 1 means that the two vectors are completely similar, 0 means no similarity, and -1 means completely dissimilar.

[0042] Euclidean distance is used to measure the straight-line distance between two vectors and is one of the most commonly used distance metrics. The specific steps include obtaining the feature vectors of the production wafer image and the control wafer image; calculating the difference between each component in the two feature vectors; squaring each component difference and summing them; taking the square root of the square sum to obtain the Euclidean distance value. The value range of Euclidean distance is [0, +∞), where 0 means that the two vectors are exactly the same, and the larger the distance, the greater the difference.

[0043] Locating the problem machine includes querying the historical problem machine corresponding to the defective wafer set based on the root cause record in the defect knowledge base; combining the production history data, comparing the equipment status and operation records of similar defects, and locating the problem machine; generating a comprehensive analysis report based on the functions of each machine in the production process and the type of the defective wafer set, and locating the problem machine according to the comprehensive analysis report.

[0044] To query historical problem machines based on root cause records, first use the root cause record information in the defect knowledge base to query each wafer in the defect wafer set and find historical records similar to these defects. The root cause record contains detailed information such as the defect type that occurred in the past, the corresponding equipment problem, and the solution. By matching the defect features in the current defect wafer set with the defect features in the historical records, it is possible to preliminarily identify the problem machines that may be involved.

[0045] Combined with the comparative analysis of production history data, after the possible problem machines are initially identified, further comparative analysis is performed in combination with production history data. Production history data includes information such as equipment status, process parameters, and operation records, which can provide detailed information on equipment operation. By comparing the equipment status and operation records of similar defects, the root cause of the equipment problem can be analyzed more deeply.

[0046] Generate a comprehensive analysis report and locate the problem machine. Finally, generate a comprehensive analysis report based on the functions of each machine in the production process and the type of defective wafer set. The comprehensive analysis report includes detailed content such as the functional description of the equipment, the defect type and its distribution, possible equipment problems and their impact. Through comprehensive analysis of the report, the problem machine can be accurately located and corresponding maintenance and repair strategies can be formulated.

[0047] Classifying and summarizing the defective wafer set includes: classifying the wafers in the defective wafer set based on defect type, defect location and defect severity. Different types of defects usually correspond to different equipment problems and process anomalies, so by classifying the defect types, it can help to quickly identify potential sources of equipment failure. The classification of defect locations helps to locate problems that may occur in specific process steps or equipment parts. The location information may include the coordinates of the defects on the wafer, the distribution at different levels, etc. The severity can be assessed based on factors such as the size, quantity, and scope of impact of the defects. Severity classification can help prioritize the most impactful defects and ensure that the most urgent problems in production are resolved in a timely manner.

[0048] Use image analysis technology to identify the type of defects and mark the category of each defect; assign a corresponding category label to each defective wafer based on the identification results; classify wafers with the same type of defects into one category for subsequent analysis; record the specific location coordinates of each defect on the wafer; assign defects to corresponding areas based on different areas of the wafer (such as the center area, edge area); classify defective wafers located in the same or similar positions, and analyze whether these locations are related to specific equipment problems; use quantitative or qualitative methods to evaluate the severity of defects, for example, using indicators such as defect area, depth or density; based on the evaluation results, classify defects into different severity levels (such as mild, moderate, severe); classify defective wafers according to the severity level to give priority to wafers with severe defects.

[0049] By classifying and summarizing defective wafer sets, and conducting multi-dimensional analysis based on defect type, location, and severity, we can fully understand the defects that occur during the production process. This classification method not only helps to accurately locate the problem machine, but also provides data support for equipment maintenance and process optimization. The classified and summarized data can more clearly reveal the root cause of the problem and help develop effective solutions, thereby improving production efficiency and product quality.

[0050] Based on the classification and summarization results, a maintenance report for the problematic machine is generated, wherein the maintenance report includes maintenance measures and preventive maintenance suggestions.

[0051] Maintenance reports can include the following parts: Problem overview, describing the type, location and severity of defects found, summarizing the affected equipment or process steps, and explaining the urgency and potential impact of the problem. Maintenance measures, describing in detail the specific faults or abnormal conditions of the problem machine, including the manifestation and location of the specific defects; root cause analysis, based on the classification and summary results, analyzing the possible causes of the defects, such as wear and tear of equipment parts, operating errors, environmental factors, etc.; immediate measures, providing specific maintenance measures for the problem, such as replacing damaged parts, adjusting equipment parameters, cleaning pollution, etc.

[0052] Preventive maintenance recommendations may include the following: routine inspection recommendations, which recommend regular inspections of specific equipment parts, process parameters or environmental conditions to detect potential problems early; optimization measures, which propose recommendations for optimizing equipment operations or process flows, such as equipment calibration, improving operating procedures, and training operators; long-term monitoring plans, which recommend the establishment of long-term monitoring mechanisms, such as adding sensors to monitor equipment status and using data analysis tools to monitor defect trends; spare parts management, which recommends preparing spare parts for key equipment to ensure timely replacement and avoid production interruptions due to equipment failures.

[0053] It is not difficult to find that the embodiments of the present application combine multiple detection technologies such as edge detection, corner detection and spot detection to further enrich the information content of feature points, and use SIFT or SURF algorithms to generate feature descriptors to form accurate feature vectors. In addition, the embodiments also include a complete process based on similarity calculation, classification and induction, and comprehensive analysis report generation. These improvements not only improve the accuracy of defect detection and the accuracy of problem machine positioning, but also provide detailed maintenance measures and preventive suggestions, which help to promptly discover and solve equipment problems and prevent similar failures from occurring, thereby significantly improving production efficiency and product quality.

[0054] The step division of the above methods is only for the purpose of clear description. When implemented, they can be combined into one step or some steps can be split and decomposed into multiple steps. As long as they include the same logical relationship, they are all within the scope of protection of this patent; adding insignificant modifications to the algorithm or process or introducing insignificant designs without changing the core design of the algorithm and process are all within the scope of protection of this patent.

[0055] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be a digital computer in various forms, such as a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, etc. The electronic device may also be a mobile device in various forms, such as a personal digital processing, a cellular phone, a smart phone, a wearable device, and other similar computing devices.

[0056] The electronic device includes: one or more processors; and a memory storing computer program instructions, wherein when the computer program instructions are executed, the processor executes the steps of the method provided in any one or more of the above embodiments. Figure 2 An exemplary structural diagram of the electronic device is disclosed. Figure 2 As shown, the electronic device includes: one or more processors 1101, memory 1102, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. The various components are connected to each other using different buses and can be installed on a common mainboard or installed in other ways as needed. The processor can process instructions executed in the electronic device, including instructions stored in or on the memory to display graphical information of the GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple electronic devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Among them, the components shown in this article, their connections and relationships, and their functions are only used as examples, and are not intended to limit the implementation of the present application described and / or required herein.

[0057] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103 and the output device 1104 may be connected via a bus or other means. Figure 2 The example of connecting through bus is taken in the following.

[0058] The input device 1103 can receive input digital or character information, and generate key signal input related to the user settings and function control of the electronic device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick and other input devices. The output device 1104 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The display device may include, but is not limited to, a liquid crystal display (LCD), a light emitting diode (LED) display and a plasma display. In some embodiments, the display device may be a touch screen.

[0059] To provide interaction with a user, the electronic device may be a computer. The computer has: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide input to the computer. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0060] In the embodiments of the present application, a computer program / instruction is stored on a computer-readable medium, and when the computer program / instruction is executed by a processor, the steps of the method provided by any one or more of the above embodiments are implemented. The computer-readable medium may be included in the electronic device described in the above embodiments; or it may exist independently without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0061] The memory 1102 can be used as a non-transient computer-readable storage medium, which can be used to store non-transient software programs, non-transient computer executable programs and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transient software programs, instructions and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more embodiments in the embodiments of the present application.

[0062] The memory 1102 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the electronic device, etc. In addition, the memory 1102 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some embodiments, the memory 1102 may optionally include a memory remotely arranged relative to the processor 1101, and these remote memories may be connected to the electronic device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0063] It should be noted that the computer-readable medium described in the present application can be a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. Computer-readable medium can be, for example, - but not limited to - a system, device or device of electricity, magnetism, light, electromagnetic, infrared or semiconductor, or any combination of the above. More specific examples of computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM, Random Access Memory), a read-only memory (ROM, Read-Only Memory), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, a device or a device or used in combination with it.

[0064] Computer readable media include permanent and non-permanent, removable and non-removable media, and information storage can be achieved by any method or technology. Information can be computer-readable instructions, data structures, modules of programs or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, read-only compact disk (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device.

[0065] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0066] In the above-described embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. For example, it can be implemented by using an application specific integrated circuit (ASIC), a general-purpose computer or any other similar hardware device. In certain embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program of the present application (including relevant data structures) can be stored in a computer-readable recording medium, for example, a RAM memory, a magnetic or optical drive or a floppy disk and similar devices. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with a processor to perform each step or function.

[0067] The computer program product provided in the embodiment of the present application includes one or more computer programs / instructions, and when the computer program / instructions are executed by the processor, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from a computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, a computer, a server or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or a data center that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid state disk (SSD)), etc.

[0068] The flow chart or block diagram in the accompanying drawings shows the possible architecture, function and operation of the equipment, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented with a dedicated system for hardware that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0069] The scope of the present application is defined by the appended claims rather than the above description, and it is intended that all changes that fall within the meaning and scope of the equivalent elements of the claims are included in the present application. Any figure mark in the claims should not be regarded as limiting the claims involved. In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or devices stated in the device claim may also be implemented by one unit or device through software or hardware. The words "first", "second", etc. are only used to distinguish the description, and do not indicate any particular order, nor can they be understood as indicating or implying relative importance.

[0070] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art can easily mention changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-restrictive.

Claims

1. A method for locating a problem machine, characterized in that: The method comprises: Obtain production wafer images collected during the production process and reference wafer images from the factory defect knowledge base; Processing the production wafer image and the control wafer image by a visual algorithm, extracting feature points, and converting the feature points into feature vectors; Performing similarity calculation on the feature vector of the production wafer image and the feature vector of the control wafer image; According to a preset matching threshold, production wafer images with a similarity greater than the matching threshold are output to obtain a defective wafer set: the defective wafer set is classified and summarized to locate the problematic machine.

2. The method according to claim 1, characterized in that The feature point extraction includes edge detection, corner point detection and spot detection.

3. The method according to claim 2, characterized in that The converting of the feature points into feature vectors includes: using a SIFT algorithm or a SURF algorithm to generate a feature descriptor for each feature point, and constructing a feature vector of the image.

4. The method according to claim 3, characterized in that The similarity calculation includes: calculating by cosine similarity or Euclidean distance.

5. The method according to any one of claims 1 to 4, characterized in that: The positioning problem machine includes: Based on the root cause records in the defect knowledge base, query the historical problem machine corresponding to the defective wafer set; Combined with historical production data, the equipment status and operation records of similar defects are compared to locate the problematic machine; A comprehensive analysis report is generated according to the functions of each machine in the production process and the type of the defective wafer set, and the problematic machine is located according to the comprehensive analysis report.

6. The method according to claim 5, characterized in that The classifying and summarizing the defective wafer set includes: classifying the wafers in the defective wafer set based on defect type, defect location and defect severity.

7. The method according to claim 6, characterized in that The method further comprises: A maintenance report for the problem machine is generated based on the classification and summarization results, and the maintenance report includes maintenance measures and preventive maintenance suggestions.

8. An electronic device, characterized in that: The electronic device comprises: one or more processors; and A memory storing computer program instructions, which, when executed, cause the processor to perform the steps of the method as claimed in any one of claims 1 to 7.

9. A computer readable medium having a computer program / instructions stored thereon, characterized in that: When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images