Wafer defect detection method and device, computer equipment and storage medium
By performing global shooting of wafers and sub-region scanning combined with artificial intelligence technology, the problem of inaccurate judgment in existing wafer defect detection is solved, and more accurate and efficient defect detection is achieved and electronic diagrams are generated.
Patent Information
- Application Number
- CN202510489199.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-17
- Publication Date
- 2025-07-22
AI Technical Summary
The existing wafer defect detection methods rely on manual judgment and cannot detect defects comprehensively and accurately. The automatic visual inspection machine is expensive and Fab factory cannot purchase in large quantities.
The detection machine is used to capture the entire image of the wafer globally, and scan it in different regions along the preset scanning path. Combined with artificial intelligence and image processing technology, the macroscopic and microscopic defect points on the wafer are comprehensively judged.
It realizes more accurate and comprehensive defect detection, improves detection efficiency, reduces costs, and automatically generates defect electronic diagrams.
Smart Images
Figure CN120352431A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of semiconductor detection technologies, and particularly to a method, apparatus, computer device, and storage medium for detecting wafer defects. Background Art
[0002] With the continuous development of the semiconductor industry, more and more customers have begun to demand defect maps when shipping semiconductor products.
[0003] In existing detection solutions, more often than not, inspectors manually conduct sampling inspections. When using this method for detection, inspectors generally need to subjectively determine defects, and it is impossible to comprehensively and accurately detect defects. Summary of the Invention
[0004] Based on this, it is necessary to provide a method, apparatus, computer device, and storage medium for detecting wafer defects to address the problem of being unable to comprehensively and accurately detect defects.
[0005] To achieve the above object, on the one hand, the present invention provides a method for detecting wafer defects, including:
[0006] Controlling a detection machine to globally photograph a wafer and obtaining a first overall image of the wafer;
[0007] Controlling the detection machine to perform sub-region scanning and photographing on the wafer along a preset scanning path and obtaining multiple local second images;
[0008] Determining target defect points on the wafer based on the first image and the multiple second images.
[0009] In one embodiment, the controlling the detection machine to perform sub-region scanning and photographing on the wafer along a preset scanning path includes:
[0010] Obtaining the size of the wafer and the positions of the chips on the wafer;
[0011] According to the size of the wafer and the positions of the chips on the wafer, using a path planning algorithm to plan the preset scanning path;
[0012] Moving the detection machine along the preset scanning path to perform scanning and photographing on the wafer.
[0013] In one embodiment, after obtaining the first overall image of the wafer, it includes:
[0014] Determining information about first defect points based on the first image;
[0015] After obtaining the multiple local second images, it includes:
[0016] Determine the information of the second defect points according to the second image;
[0017] Determining the target defect points on the wafer based on the first image and the multiple second images includes:
[0018] Determine the target defect points on the wafer based on the information of the first defect points and the information of the second defect points.
[0019] In one embodiment, the information of the first defect points includes the information of the first position and the information of the first type;
[0020] The information of the second defect points includes the information of the second position and the information of the second type.
[0021] In one embodiment, determining the target defect points on the wafer based on the information of the first defect points and the information of the second defect points includes:
[0022] Obtain the information of the first position and the information of the first type;
[0023] Mark the position and type of the first defect points based on the information of the first position and the information of the first type;
[0024] Obtain the information of the second position and the information of the second type;
[0025] Mark the position and type of the second defect points based on the information of the second position and the information of the second type;
[0026] Generate the position and type of the target defect points on the wafer according to the positions and types of the first defect points and the second defect points.
[0027] In one embodiment, the inspection machine includes an optical microscope and a control system.
[0028] On the other hand, the present application also provides a wafer defect detection device, including:
[0029] A first control module, configured to control the inspection machine to perform a global shooting on the wafer and obtain an overall first image of the wafer;
[0030] A second control module, configured to control the inspection machine to perform a sub-region scanning and shooting on the wafer along a preset scanning path and obtain a plurality of partial second images;
[0031] A first determination module, configured to determine the target defect points on the wafer based on the first image and the multiple second images.
[0032] On the other hand, the present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of any one of the above-mentioned methods are implemented.
[0033] On the other hand, the present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of any one of the above-mentioned methods are implemented.
[0034] On the other hand, the present application also provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of any one of the above-mentioned methods are implemented.
[0035] Compared with the prior art, the above technical solutions have the following advantages:
[0036] The present application provides a method, device, computer device and storage medium for detecting wafer defects. Among them, the detection method first controls a detection machine to perform a global photographing on a wafer and obtains a first overall image of the wafer, then controls the detection machine to perform a sub-region scanning and photographing on the wafer along a preset scanning path and obtains a plurality of local second images, and then determines target defect points on the wafer based on the first image and the plurality of second images.
[0037] Since the plurality of second images are scanned along a preset scanning path, it is more accurate than sampling detection. And macroscopic defects of the wafer are obtained based on the overall first image, and then microscopic defects of the wafer are obtained based on the local second images. The target defect points on the wafer are judged according to the first image and the plurality of second images, that is, the macroscopic defects and the microscopic defects are comprehensively judged to determine the target defect points on the wafer, which is more comprehensive and accurate than the existing single detection. And the entire detection process is automatically detected and automatically identified, improving the detection efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0039] Figure 1 It is a schematic flowchart of a wafer detection method provided by an embodiment of the present application;
[0040] Figure 2 It is a schematic diagram of marked defect points provided by an embodiment of the present application.
[0041] Explanation of the reference numerals: 01 - first defect point; 02 - second defect point; 03 - mixed defect point. DETAILED DESCRIPTION
[0042] In order to facilitate understanding of the present application, the present application will be described more fully below with reference to the relevant drawings. Embodiments of the present application are provided in the drawings. However, the present application can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.
[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.
[0044] When used herein, the singular forms "a", "an", and "said / the" may also include plural forms, unless the context clearly indicates otherwise. It should also be understood that the terms "include / comprise" or "have" etc. specify the presence of stated features, wholes, steps, operations, components, parts or combinations thereof, but do not exclude the possibility of the presence or addition of one or more other features, wholes, steps, operations, components, parts or combinations thereof.
[0045] Based on the content in the background technology, an existing detection method requires the use of an automatic visual inspection machine (Automatic Visual Inspection, referred to as AVI) to scan the wafer, but the AVI equipment is expensive, and the Fab factory cannot purchase a large number of AVI equipment to meet customer requirements. More often, inspectors use an electron microscope (Optical Microscope, referred to as OM) for manual inspection, but this method requires inspectors to make subjective judgments on defects, and cannot comprehensively and accurately detect defects, and cannot output defect electronic images.
[0046] Based on this, the present application provides a wafer defect detection method, device, computer equipment and storage medium, wherein the detection method first controls the detection machine to take a global shot of the wafer and obtain a first image of the entire wafer, and then controls the detection machine to scan and shoot the wafer in different areas along a preset scanning path, and obtain multiple local second images, and then determines the target defect points on the wafer based on the first image and the multiple second images.
[0047] In this detection method, since multiple second images are scanned along a preset scanning path, it is more accurate than sampling detection. Moreover, macroscopic defects of the wafer are obtained based on the overall first image, and then microscopic defects of the wafer are obtained based on the local second images. The target defect points on the wafer are determined according to the first image and the multiple second images, that is, the macroscopic defects and microscopic defects are comprehensively used to judge the target defect points on the wafer, which is more comprehensive and accurate than the existing separate detection.
[0048] In order to make the above objects, features, and advantages of the present application more obvious and understandable, the present application will be further described in detail below with reference to the accompanying drawings and specific embodiments.
[0049] Refer to Figure 1 , Figure 1 which is a schematic flowchart of a wafer detection method provided by an embodiment of the present application. The detection steps include:
[0050] S10: Control the inspection machine to perform a global shot of the wafer and obtain an overall first image of the wafer;
[0051] S20: Control the inspection machine to perform a sub-region scan and shot of the wafer along a preset scanning path and obtain multiple local second images;
[0052] S30: Determine the target defect points on the wafer based on the first image and the multiple second images.
[0053] Specifically, when performing wafer detection, the method of combining artificial intelligence with an inspection machine can be adopted, and the wafer is automatically detected and automatically identified through a control system.
[0054] In step S10, control the inspection machine to perform a global shot of the wafer. That is to say, an overall image of the wafer is taken as the first image, and this first image can detect macroscopic defects, including but not limited to surface stains, mechanical damages (scratches, cracks, notches), and color differences on the wafer surface caused by uneven thickness or process problems.
[0055] In step S20, control the inspection machine to perform a sub-region scan and shot of the wafer. The scan and shot need to be performed along a preset scanning path, and the wafer can be comprehensively detected along this preset scanning path. It should be noted that the multiple second images taken are magnified microscopic images. That is to say, the second images can detect microscopic defects, including but not limited to point defects, line defects, surface defects, impurity precipitation, etching defects, lattice defects, etc. of the wafer.
[0056] In step S30, by combining the first image and multiple second images, the defects detected macroscopically and microscopically can be obtained, and then based on the defects detected macroscopically and microscopically, the final target defects can be determined. The defect detection is more comprehensive, and the entire detection process is automatically detected and automatically identified, improving the detection efficiency.
[0057] It should be noted that at least some macroscopic defects cannot be detected microscopically. Therefore, by combining macroscopic defects and microscopic defects, defect points can be detected more comprehensively and accurately.
[0058] In this embodiment, since the multiple second images are scanned along a preset scanning path, it is more accurate than sampling detection. And based on the overall first image, macroscopic defects of the wafer are obtained, and then based on the local second images, microscopic defects of the wafer are obtained. The target defect points on the wafer are judged according to the first image and the multiple second images, that is, the target defect points on the wafer are comprehensively judged by combining macroscopic defects and microscopic defects, which is more comprehensive and accurate than the existing separate detection. And the entire detection process is automatically detected and automatically identified, improving the detection efficiency.
[0059] In another embodiment of the present application, controlling the inspection machine to perform area scanning and shooting on the wafer along a preset scanning path includes:
[0060] S201: Obtain the size of the wafer and the positions of the chips on the wafer;
[0061] S202: According to the size of the wafer and the positions of the chips on the wafer, use a path planning algorithm to plan a preset scanning path;
[0062] S203: Move the inspection machine along the preset scanning path to perform scanning and shooting on the wafer.
[0063] Specifically, when controlling the inspection machine to perform scanning and shooting, it is necessary to first obtain the size of the wafer and the positions of the chips. It should be noted that the obtaining methods may include but are not limited to optical measurement, laser measurement, contact measurement, etc. In this embodiment, it can be obtained while taking the global image in step S10.
[0064] According to the size of the wafer and the positions of the chips on the wafer, the path planning algorithm can select the optimal scanning path as the preset scanning path. It should be noted that the path planning algorithm can dynamically plan the scanning path according to needs, improve the scanning efficiency, and avoid repeated scanning or missed scanning. It should be noted that the planning of the preset scanning path can be a global path planning for the wafer or a path planning for fixed points according to needs, and no specific limitation is made here.
[0065] After planning the preset scanning path, the inspection machine is controlled to move along the preset scanning path. It should be noted that the inspection machine can move automatically through program settings, enabling high-precision mechanical movement, thereby improving the inspection efficiency and accuracy.
[0066] In this embodiment, after obtaining the size of the wafer and the positions of the chips on the wafer, the preset scanning path is dynamically planned through a path planning algorithm, which can improve the scanning efficiency and inspection accuracy, and avoid repeated scanning or missed scanning.
[0067] In another embodiment of the present application, after obtaining the overall first image of the wafer, it includes:
[0068] Determining the information of the first defect points according to the first image;
[0069] After obtaining multiple local second images, it includes:
[0070] Determining the information of the second defect points according to the second image;
[0071] Determining the target defect points on the wafer based on the first image and the multiple second images, including:
[0072] Determining the target defect points on the wafer based on the information of the first defect points and the information of the second defect points.
[0073] Specifically, after obtaining the overall first image of the wafer, it is necessary to determine the information of the first defect points according to the first image. This process includes uploading the first image to the image processing software, and then using artificial intelligence deep learning for automatic image judgment to identify the information of the first defect points. In this process, the deep learning algorithm is used to perform real-time analysis on the collected images to automatically identify defects without manual intervention. It should be noted that the image processing software can include, but is not limited to, ADC software.
[0074] Similarly, after obtaining multiple local second images of the wafer, it is necessary to determine the information of the second defect points according to the second image. This process includes uploading the second image to the image processing software, and then using artificial intelligence deep learning for automatic image judgment to identify the information of the second defect points. In this process, the deep learning algorithm is used to perform real-time analysis on the collected images to automatically identify defects without manual intervention.
[0075] It should be noted that automatically discriminating the defect point information in the first image and the second image according to artificial intelligence and the image processing software is more accurate and fast compared to the existing manual image judgment by inspectors, and can automatically generate defect electronic diagrams, saving costs.
[0076] After that, the information of the first defect point and the information of the second defect point are comprehensively analyzed to determine the information of the target defect point, thereby determining the target defect point. For example, all the first defect points and the second defect points are target defect points; or, some of the first defect points and some of the second defect points are target defect points.
[0077] In this embodiment, the method of combining the information of the first defect point and the information of the second defect point can more accurately and comprehensively identify the defect points.
[0078] In another embodiment of the present application, the information of the first defect point includes the information of the first position and the information of the first type;
[0079] The information of the second defect point includes the information of the second position and the information of the second type.
[0080] Specifically, the wafer includes a plurality of chips arranged in an array, and the position information and the type information can locate the position and type of the defect point.
[0081] The information of the first position represents that there is a macroscopic defect at the first position, and the information of the first type represents the type of the macroscopic defect. The information of the first position and the information of the first type correspond to determine the macroscopic defect. For example, there is a color difference defect at the first position.
[0082] The information of the second position represents that there is a microscopic defect at the second position, and the information of the second type represents the type of the microscopic defect. The information of the second position and the information of the second type correspond to determine the microscopic defect. For example, there is a lattice defect at the second position.
[0083] It should be noted that when the information of the first position is the same as the information of the second position, there is both a first defect point and a second defect point at this position.
[0084] In this embodiment, the information of the first defect point includes the first position information and the first type information, and the information of the second defect point includes the second position information and the second type information. The position information and the type information can more accurately identify the defect points.
[0085] In another embodiment of the present application, refer to Figure 2 , Figure 2 is a schematic diagram of a marked defect point provided by an embodiment of the present application; determining the target defect point on the wafer based on the information of the first defect point 01 and the information of the second defect point 02 includes:
[0086] Obtain the information of the first position and the information of the first type;
[0087] Based on the information of the first position and the information of the first type, mark the position and type of the first defect point 01;
[0088] Obtain the information of the second position and the information of the second type;
[0089] Mark the position and type of the second defect point 02 based on the information of the second position and the information of the second type;
[0090] Generate the position and type of the target defect point on the wafer according to the markings of the first defect point 01 and the second defect point 02.
[0091] Specifically, upload the first image to the image processing software, and then use artificial intelligence deep learning for automatic image judgment to identify the information of the first position and the information of the first type of the first defect point 01. Mark the position and type of the first defect point 01 in the defect electronic diagram based on the information of the first position and the information of the first type. It should be noted that at this time, the first defect point 01 can include multiple types, and it is marked with different colors or symbols according to different types.
[0092] Upload the second image to the image processing software, and then use artificial intelligence deep learning for automatic image judgment to identify the information of the second position and the information of the second type of the second defect point 02. Mark the position and type of the second defect point 02 in the defect electronic diagram based on the information of the second position and the information of the second type. It should be noted that at this time, the second defect point 02 can include multiple types, and it is marked with different colors or symbols according to different types.
[0093] It should be noted that the marking can be cancelled according to specific needs. For example, when the defect is within the allowable specification range, the inspector cancels the marking of the marked defect.
[0094] After marking the types of the positions of the first defect point 01 and the second defect point 02, the position and type of the target defect point on the wafer can be directly and intuitively seen through the marking.
[0095] It should be noted that the markings of the first defect point 01 and the second defect point 02 may overlap, and in this case, it is marked as a mixed defect point 03. For example, after marking the first defect point 01 according to the information of the first position and the information of the first type, and then marking the second defect point 02 according to the information of the second position and the information of the second type, if the second position is the same as the first position, it means that there is both the first defect point 01 and the second defect point 02 at this position, and in this case, this position is marked as a mixed defect point 03.
[0096] In this embodiment, using marking to confirm the target defect point can more intuitively observe the position and type of the target defect point.
[0097] In another embodiment of the present application, the inspection machine includes an optical microscope and a control system.
[0098] Specifically, a macroscopic defect electron map is imported into the control system. The control system controls the first image captured by the optical microscope. The first image includes the entire wafer, and the captured photo is transmitted into the control system for processing. Then, the stage of the optical microscope is precisely mechanically moved along a preset scanning path, and multiple local second images are scanned and photographed simultaneously. The second images are magnified microscopic images.
[0099] It should be noted that the control system can include artificial intelligence, and deep learning algorithms can be used to perform real-time analysis on the collected images, automatically identify and classify defect types (such as particles, scratches, lattice defects, etc.). Without manual intervention, the system can automatically optimize the recognition model by continuously learning new defect samples to adapt to changes in different processes and materials. Compared with the traditional AVI method that relies on manual setting of thresholds and rules, it has higher accuracy and adaptability, and lower costs.
[0100] In this embodiment, an optical microscope and a control system are used as the inspection station, which can automatically output a defect electron map and save costs at the same time.
[0101] In another embodiment of the present application, a wafer inspection device is provided, including: a first control module, a second control module, and a first determination module, where:
[0102] The first control module is used to control the inspection station to perform a global photographing of the wafer and obtain the overall first image of the wafer;
[0103] The second control module is used to control the inspection station to perform sub-region scanning and photographing of the wafer along a preset scanning path and obtain multiple local second images;
[0104] The first determination module is used to determine the target defect points on the wafer based on the first image and the multiple second images.
[0105] Specifically, the first control module controls the inspection station to perform a global photographing of the wafer. That is to say, it controls to take an overall image of the wafer as the first image, and this first image can detect macroscopic defects, including but not limited to surface stains, mechanical damages (scratches, cracks, notches), and color differences on the wafer surface caused by uneven thickness or process problems.
[0106] The second control module controls the inspection station to perform sub-region scanning and photographing of the wafer. The scanning and photographing need to be carried out along a preset scanning path, and the wafer can be comprehensively inspected along this preset scanning path. It should be noted that the multiple second images captured are magnified microscopic images. That is to say, the second images can detect microscopic defects, including but not limited to point defects, line defects, surface defects, impurity precipitation, etching defects, etc. of the wafer.
[0107] The first determination module combines the first image with multiple second images to obtain macroscopically detected defects and microscopically detected defects, and then determines the final target defects based on the first image and the multiple second images.
[0108] In this embodiment, since the multiple second images are scanned along a preset scanning path, it is more accurate than sampling detection. Moreover, macroscopic defects of the wafer are obtained based on the overall first image, and then microscopic defects of the wafer are obtained based on the local second images. The target defect points on the wafer are judged according to the first image and the multiple second images, that is, the macroscopic defects and the microscopic defects are comprehensively judged to determine the target defect points on the wafer, which is more comprehensive and accurate than the existing separate detection. And the entire detection process is automatically detected and automatically identified, improving the detection efficiency.
[0109] In another embodiment of the present application, the second control module further includes:
[0110] The first acquisition unit is used to acquire the size of the wafer and the positions of the chips on the wafer;
[0111] The planning unit is used to plan a preset scanning path by using a path planning algorithm according to the size of the wafer and the positions of the chips on the wafer;
[0112] The scanning unit is used to move the inspection machine along the preset scanning path to scan and photograph the wafer.
[0113] In this embodiment, after acquiring the size of the wafer and the positions of the chips on the wafer, the preset scanning path is dynamically planned by using a path planning algorithm, which improves the scanning efficiency and avoids repeated scanning or missed scanning.
[0114] In another embodiment of the present application, the wafer detection device further includes:
[0115] The second determination module is used to determine the information of the first defect points according to the first image;
[0116] The third determination module is used to determine the information of the second defect points according to the second image;
[0117] The fourth determination module is used to determine the target defect points on the wafer based on the information of the first defect points and the information of the second defect points.
[0118] In this embodiment, the defect point information in the first image and the second image is automatically discriminated according to artificial intelligence and image processing software, which is more accurate and fast than the existing manual judgment by inspection personnel, and can automatically generate defect electronic diagrams, saving costs.
[0119] In another embodiment of the present application, the fourth determination module further includes:
[0120] A first acquisition unit, configured to acquire information on a first position and information on a first type;
[0121] A first marking unit, configured to mark the position and type of a first defect point based on the information on the first position and the information on the first type;
[0122] A second acquisition unit, configured to acquire information on a second position and information on a second type;
[0123] A second marking unit, configured to mark the position and type of a second defect point based on the information on the second position and the information on the second type;
[0124] A processing unit, configured to generate the position and type of target defect points on the wafer according to the markings of the first defect points and the second defect points.
[0125] In this embodiment, by marking to confirm the target defect points, the position and type of the target defect points can be observed more intuitively.
[0126] It should be noted that for the specific limitations of the wafer detection device, reference can be made to the limitations on the wafer detection method in the foregoing text, which will not be elaborated here. Each module in the above wafer detection device can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.
[0127] In another embodiment of the present application, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the data migration method described in any of the above embodiments is implemented.
[0128] In another embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the data migration method described in any of the above embodiments is implemented.
[0129] In another embodiment of the present application, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the data migration method described in any of the above embodiments is implemented.
[0130] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above various methods. Among them, any reference to a memory, storage, database, or other medium used in the various embodiments provided in the present application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, or optical memory, etc. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc.
[0131] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the various technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered to be within the scope described in this specification.
[0132] The above-described embodiments merely represent several implementation manners of the present application. Their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the patent application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the appended claims.
Claims
1. A method for detecting wafer defects, characterized in that, Including: Controlling the inspection machine to perform a global photographing of the wafer and obtaining a first overall image of the wafer; Controlling the inspection machine to perform sub-region scanning and photographing of the wafer along a preset scanning path and obtaining a plurality of local second images; Determining target defect points on the wafer based on the first image and the plurality of second images.
2. The detection method of wafer defects according to claim 1, characterized in that, The controlling the inspection machine to perform sub-region scanning and photographing of the wafer along a preset scanning path includes: Obtaining the size of the wafer and the positions of the chips on the wafer; Planning the preset scanning path by using a path planning algorithm according to the size of the wafer and the positions of the chips on the wafer; Moving the inspection machine along the preset scanning path to perform scanning and photographing of the wafer.
3. The method for detecting wafer defects according to claim 1, wherein After obtaining the first overall image of the wafer, it includes: Determining information about first defect points according to the first image; After obtaining the plurality of local second images, it includes: Determining information about second defect points according to the second images; The determining the target defect points on the wafer based on the first image and the plurality of second images includes: Determining the target defect points on the wafer based on the information about the first defect points and the information about the second defect points.
4. The method for detecting wafer defects according to claim 3, wherein The information about the first defect points includes information about the first positions and information about the first types; The information about the second defect points includes information about the second positions and information about the second types.
5. The method for detecting wafer defects according to claim 4, wherein The determining the target defect points on the wafer based on the information about the first defect points and the information about the second defect points includes: Obtaining the information about the first positions and the information about the first types; Marking the positions and types of the first defect points based on the information about the first positions and the information about the first types; Obtaining the information about the second positions and the information about the second types; Marking the positions and types of the second defect points based on the information about the second positions and the information about the second types; Generating the positions and types of the target defect points on the wafer according to the positions and types of the first defect points and the second defect points.
6. The method for detecting wafer defects according to claim 1, characterized in that, The inspection machine includes an optical microscope and a control system.
7. A detection device for wafer defects, characterized in that, Including: A first control module for controlling the inspection machine to perform a global photographing of the wafer and obtaining a first overall image of the wafer; A second control module for controlling the inspection machine to perform sub-region scanning and photographing of the wafer along a preset scanning path and obtaining a plurality of local second images; A first determination module for determining target defect points on the wafer based on the first image and the plurality of second images.
8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.
9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.
10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method according to any one of claims 1 to 6.