A wafer identification and positioning method, device, equipment and storage medium

Abstract

The present invention discloses a wafer identification and positioning method, device, equipment and storage medium. The method includes: obtaining a target image captured of a target wafer, and establishing a target coordinate system according to the target image; identifying the size information of the target wafer according to the target image, and if the identification is successful, extracting the notch shape feature of the target wafer; determining the target position of the target wafer, and determining the target attitude of the target wafer according to the notch shape feature. The wafer identification and positioning method disclosed by the present invention can extract the key features of the wafer through visual recognition, and then adjust the position and attitude of the wafer, which can be applicable to various types of wafers, and solves the problem that traditional lithography machines can only identify specific types of wafers singly.

Description

Technical Field

[0001] The present invention relates to the field of computer vision technology, and particularly to a method, device, equipment and storage medium for wafer identification and positioning. Background Art

[0002] With the technological development and update of the semiconductor industry, the manufacturing technology of wafers is getting better and better, the types of wafers are increasing, and the testing requirements are also getting higher and higher. The positioning accuracy requirements for wafers are also getting higher and higher.

[0003] Traditional wafers need to cut a notch to confirm the coordinate system of the wafer. According to the different shapes of the notch, they are divided into two types, namely Flat and Notch, and are further divided into 4-inch, 6-inch, 8-inch, etc. according to different sizes. In the prior art, traditional lithography machines can generally only identify specific types of wafers singly. If you want to identify other types of wafers, you can only modify the edge-finding and identification module of the lithography machine, which requires a relatively high cost. Summary of the Invention

[0004] The present invention provides a method, device, equipment and storage medium for wafer identification and positioning to realize the identification and positioning of multiple types of wafers.

[0005] According to one aspect of the present invention, a method for wafer identification and positioning is provided, including:

[0006] Obtain a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image;

[0007] Identify the size information of the target wafer according to the target image. If the identification is successful, extract the notch shape feature of the target wafer;

[0008] Determine the target position of the target wafer, and determine the target posture of the target wafer according to the notch shape feature.

[0009] Further, identifying the size information of the target wafer according to the target image includes:

[0010] Use a set target detection algorithm to identify the size feature of the target wafer according to the target image;

[0011] Obtain preset size data, compare the size feature with the preset size data, and determine the size information of the target wafer according to the comparison result.

[0012] Further, extracting the notch shape feature of the target wafer includes:

[0013] Use a set target detection algorithm to identify the notch shape feature of the target wafer according to the target image;

[0014] Match according to the notch shape feature in the preset feature database. If the match is successful, it is determined that the notch shape feature recognition is completed.

[0015] Further, determining the target position of the target wafer includes:

[0016] Using a set target detection algorithm, extract the feature points in the target image, and generate the initial position information of the target wafer in the target coordinate system;

[0017] Determine the wafer center of the target wafer according to the initial position information, and determine the offset between the wafer center and the origin of the target coordinate system;

[0018] Determine the target position of the target wafer according to the offset.

[0019] Further, determining the target attitude of the target wafer according to the notch shape feature includes:

[0020] Determine the wafer angle of the target wafer according to the notch shape feature;

[0021] Determine the target attitude of the target wafer according to the angle deviation between the wafer angle and the preset standard angle.

[0022] Further, the method further includes:

[0023] When the target wafer moves to the target position and the target attitude, correct the target position and the target attitude.

[0024] Further, correcting the target position and the target attitude includes:

[0025] Obtain the current image of the target wafer at the target position and the target attitude;

[0026] Using a set target detection algorithm, extract the wafer features of the current image, and determine the current position and the current angle of the target wafer;

[0027] Correct the target position according to the offset between the current position and the origin of the target coordinate system, and correct the target attitude according to the angle deviation between the current angle and the preset standard angle.

[0028] According to another aspect of the present invention, there is provided a wafer identification and positioning device, including:

[0029] A target coordinate system establishment module, configured to obtain a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image;

[0030] A feature extraction module, configured to recognize the size information of the target wafer according to the target image, and extract the notch shape feature of the target wafer if the recognition is successful;

[0031] A target position and target attitude determination module, configured to determine the target position of the target wafer, and determine the target attitude of the target wafer according to the notch shape feature.

[0032] Optionally, the feature extraction module is further configured to:

[0033] Use a set target detection algorithm to recognize the size feature of the target wafer according to the target image;

[0034] Obtain preset size data, compare the size feature with the preset size data, and determine the size information of the target wafer according to the comparison result.

[0035] Optionally, the feature extraction module is further configured to:

[0036] Use a set target detection algorithm to recognize the notch shape feature of the target wafer according to the target image;

[0037] Match according to the notch shape feature in a preset feature database, and if the match is successful, determine that the recognition of the notch shape feature is completed.

[0038] Optionally, the target position and target attitude determination module is further configured to:

[0039] Use a set target detection algorithm to extract feature points in the target image, and generate initial position information of the target wafer in the target coordinate system;

[0040] Determine the wafer center of the target wafer according to the initial position information, and determine the offset between the wafer center and the origin of the target coordinate system;

[0041] Determine the target position of the target wafer according to the offset.

[0042] Optionally, the target position and target attitude determination module is further configured to:

[0043] Determine the wafer angle of the target wafer according to the notch shape feature;

[0044] Determine the target attitude of the target wafer according to the angle deviation between the wafer angle and a preset standard angle.

[0045] Optionally, the device further includes a correction module, configured to correct the target position and the target attitude when the target wafer moves to the target position and the target attitude.

[0046] Optionally, the correction module is further configured to:

[0047] Obtain a current image of the target wafer at the target position and in the target pose;

[0048] Utilize a set target detection algorithm to extract the wafer features of the current image and determine the current position and current angle of the target wafer;

[0049] Correct the target position according to the offset between the current position and the origin of the target coordinate system, and correct the target pose according to the angular deviation between the current angle and the preset standard angle.

[0050] According to another aspect of the present invention, there is provided an electronic device, the electronic device includes:

[0051] At least one processor; and

[0052] A memory communicatively connected to the at least one processor; wherein,

[0053] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the wafer recognition and positioning method according to any embodiment of the present invention.

[0054] According to another aspect of the present invention, there is provided a computer-readable storage medium, the computer-readable storage medium stores computer instructions, and the computer instructions are used to implement the wafer recognition and positioning method according to any embodiment of the present invention when executed by a processor.

[0055] According to another aspect of the present invention, there is provided a computer program product, the computer program product includes computer programs / instructions, and the computer programs / instructions implement the steps of the wafer recognition and positioning method according to any embodiment of the present invention when executed by a processor.

[0056] The wafer recognition and positioning method disclosed in the present invention first obtains a target image obtained by photographing a target wafer, and establishes a target coordinate system according to the target image; then identifies the size information of the target wafer according to the target image, and if the identification is successful, extracts the notch shape feature of the target wafer; finally determines the target position of the target wafer, and determines the target pose of the target wafer according to the notch shape feature. The wafer recognition and positioning method disclosed in the present invention can extract the key features of the wafer through visual recognition, and then adjust the position and pose of the wafer, and can be applicable to various types of wafers, solving the problem that traditional lithography machines can only identify specific types of wafers singly.

[0057] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0059] Figure 1 is a flowchart of a wafer identification and positioning method provided in Embodiment 1 of the present invention;

[0060] Figure 2 is a flowchart of a wafer identification and positioning method provided in Embodiment 2 of the present invention;

[0061] Figure 3 is a schematic diagram of a wafer identification and positioning process provided in Embodiment 2 of the present invention;

[0062] Figure 4 is a schematic structural diagram of a wafer identification and positioning device provided in Embodiment 3 of the present invention;

[0063] Figure 5 is a schematic structural diagram of an electronic device for implementing the wafer identification and positioning method of Embodiment 4 of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0064] In order to enable those skilled in the art to better understand the solutions of the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0065] It should be noted that the terms "first", "second", etc. in the description, claims and above-mentioned drawings of the present invention are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0066] Embodiment 1

[0067] Figure 1 FIG. is a flowchart of a wafer identification and positioning method provided for Embodiment 1 of the present invention. This embodiment is applicable to the situation of identifying and positioning various types of wafers. This method can be executed by a wafer identification and positioning device, which can be implemented in the form of hardware and / or software, and the wafer identification and positioning device can be configured in an electronic device. As Figure 1 shown, the method includes:

[0068] S110. Obtain a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image.

[0069] Among them, a wafer refers to a silicon wafer used to fabricate silicon semiconductor circuits. The target wafer is the wafer that needs to be identified and positioned in the embodiments of the present invention. The target image is an image obtained by photographing the target wafer, and the target coordinate system is a coordinate system established with the center of the field of view as the origin in the field of view of photographing the target wafer.

[0070] In this embodiment, a camera can be used to photograph the wafer image to ensure that the image is clear and uniform, and preprocessing of the image such as grayscale conversion and noise removal can be performed to improve the quality of the obtained target image. After photographing the target image, a coordinate system of the target can be established with the center of the field of view as the origin in the field of view.

[0071] For example, in an ideal state (high contrast, low distortion), when photographing a six-inch target wafer, a coordinate system can be established according to the target image taken by the camera at a 1:1 size. Among them, the size of the entire coordinate system is the size of the field of view range, and a rectangular coordinate system is established with the center of the field of view as the origin. At the same time, points can be sampled on the peripheral contour of the wafer and converted into corresponding coordinates for subsequent identification and positioning. The more sampling points, the higher the positioning accuracy. The specific number of sampling points can be adjusted in the program according to the accuracy requirements of the corresponding lithography machine.

[0072] S120. Identify the size information of the target wafer based on the target image. If the identification is successful, extract the notch shape feature of the target wafer.

[0073] Among them, the size information represents the size of the target wafer. For example, common wafer sizes can be 2 inches, 4 inches, 6 inches, 8 inches, and 12 inches. Traditional wafers need to cut a notch on the wafer to confirm the coordinate system. According to the different shapes of the notch, they are divided into two types, namely Flat (flat-edge notch) and Notch (V-notch). The notch shape feature of the target wafer is the Flat / Notch classification of the target wafer.

[0074] In this embodiment, when identifying and positioning the wafer, the size of the wafer can be identified first. Any two points' coordinates (X1, X2) and (Y1, Y2) except the notch in the target image can be continuously collected. Through the formula Cmax 2 =(X1 - X2) 2 +(Y1 - Y2) 2 continuously calculate the coordinates of any two points except the notch in the target image, and compare to obtain the maximum value Cmax 2 as the square of the wafer diameter.

[0075] Preferably, when collecting the coordinates of any two points except the notch in the target image, any two points except the notch can be selected first, and then one of the points remains unchanged while the other point is changed to other points on the target wafer. Continuously calculate Cmax according to the above formula 2 , until all points are calculated, and finally compare to obtain the maximum value.

[0076] Furthermore, after determining the size information of the target wafer, the calculated size can be matched with the preset size data in the database. If the match is successful, the size identification is considered successful, and the next step can be continued.

[0077] Preferably, after the size classification is completed, the missing part relative to the wafer contour in the wafer can be classified as the notch shape feature, and the coordinates of the feature are read at the same time. For the different features of Flat (flat-edge notch) and Notch (V-notch), the flat-edge notch is a line segment, which can be regarded as a function, that is, y = ax + b. Then, calculate the function of the straight line where the two points are located through the coordinates of any two random points at the notch, and substitute the other coordinates at the notch for calculation. If all satisfy the function or the X coordinates are all equal, then the feature is a flat-edge notch; otherwise, it is a V-notch.

[0078] S130. Determine the target position of the target wafer, and determine the target attitude of the target wafer according to the notch shape feature.

[0079] Among them, the target position and target attitude of the target wafer are the position and attitude that the target wafer needs to reach in the identification and positioning task of the wafer.

[0080] In this embodiment, after determining the size information of the target wafer, the coordinates of the two end points on the diameter of the target wafer can be extracted, and then the center point of the two end points is determined as the center point of the wafer to obtain the coordinates of the wafer center point. According to the offset between the center point coordinates and the origin of the target coordinate system, the distance that the target wafer needs to be compensated in the opposite direction can be determined. Controlling the target wafer to move in the direction of the coordinate system origin according to the magnitude of the offset can make the target wafer reach the target position.

[0081] Furthermore, after extracting the notch shape feature of the target wafer, according to the notch shape feature, it can be determined whether the notch of the wafer is a flat-edge notch or a V-shaped notch. At the same time, the corresponding feature coordinates can be obtained, and the center point of the notch contour can be determined. According to the angle between the straight line where the two points of the wafer center and the center point of the notch contour are located and the X-axis in the target coordinate system, the current angle of the target wafer can be determined. According to the angle difference between the current angle and the preset standard angle, the target angle that the target wafer needs to rotate can be determined. Controlling the target wafer to rotate according to the target angle can make it reach the target attitude.

[0082] Furthermore, this method further includes: after the target wafer moves to the target position and target attitude, correcting the target position and target attitude.

[0083] In this embodiment, due to possible errors in the acquisition and coordinate calculation of the feature points in the target image, the target wafer may not reach the standard position and attitude through one movement. Therefore, the distance and angle that the target wafer needs to move can be re-determined after the target wafer moves, aiming to correct the target position and target attitude.

[0084] Optionally, the method for correcting the target position and target attitude can be: acquiring the current image of the target wafer at the target position and target attitude; using the set target detection algorithm to extract the wafer features of the current image and determine the current position and current angle of the target wafer; correcting the target position according to the offset between the current position and the origin of the target coordinate system, and correcting the target attitude according to the angle deviation between the current angle and the preset standard angle.

[0085] Specifically, after the movement of the position and angle of the target wafer is completed, the target wafer can be photographed again to obtain a new current image. Then, according to the above recognition and positioning method, the wafer features are extracted again, and the current position and current angle of the target wafer are obtained. Then, according to the error between it and the standard position and standard angle, the target wafer is controlled to perform reverse compensation, so as to complete the correction. The above correction steps can be executed multiple times until the error between the current position and current angle of the target wafer and the standard position and standard angle is less than the set value.

[0086] Preferably, the feature recognition of the current image can adopt the OverFeat object detection algorithm. The OverFeat algorithm is a feature extractor that can unify the classification, localization, and detection tasks into a single CNN network architecture and can perform localization by predicting the coordinates of the object bounding box. Among them, the localization and detection tasks can share the feature extraction layer of the CNN network with the classification task, and the feature extraction layer pre-trained for the classification task can be migrated to other tasks for feature extraction.

[0087] The wafer recognition and positioning method disclosed by the present invention first obtains a target image obtained by photographing a target wafer, and establishes a target coordinate system according to the target image; then identifies the size information of the target wafer according to the target image. If the identification is successful, the notch shape feature of the target wafer is extracted; finally, the target position of the target wafer is determined, and the target posture of the target wafer is determined according to the notch shape feature. The wafer recognition and positioning method disclosed by the present invention can extract the key features of the wafer through visual recognition, and then adjust the position and posture of the wafer, which can be applied to various types of wafers, and solves the problem that traditional lithography machines can only identify specific types of wafers singly.

[0088] Embodiment 2

[0089] Figure 2 It is a flowchart of a wafer recognition and positioning method provided by Embodiment 2 of the present invention, and this embodiment is a refinement of the above embodiment. As Figure 2 shown, the method includes:

[0090] S210. Obtain a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image.

[0091] In this embodiment, a camera can be used to photograph the wafer image to ensure that the image is clear and uniform, and image preprocessing such as grayscale conversion and noise removal can be performed to improve the quality of the obtained target image. After photographing the target image, a coordinate system of the target can be established in the field of view with the center of the field of view as the origin.

[0092] For example, under ideal conditions (high contrast and low distortion), when photographing a six-inch target wafer, a coordinate system can be established for the target image captured by the camera at a 1:1 scale. Among them, the size of the entire coordinate system is the same as the field of view range, and a rectangular coordinate system is established with the center of the field of view as the origin. At the same time, points can be sampled on the perimeter of the wafer and converted into corresponding coordinates for subsequent identification and positioning. The more points are sampled, the higher the positioning accuracy. The specific number of sampled points can be adjusted in the program according to the accuracy requirements of the corresponding lithography machine.

[0093] S220. Use the set target detection algorithm to identify the size characteristics of the target wafer based on the target image, obtain the preset size data, compare the size characteristics with the preset size data, and determine the size information of the target wafer according to the comparison result.

[0094] Among them, the size information represents the size of the target wafer, and the preset size data is the preset standard wafer size.

[0095] In this embodiment, the OverFeat algorithm can be used to process the target image to identify the size characteristics of the wafer. Then, the actual size data of the wafer is calculated based on the size characteristics, and the calculated actual size is compared with the preset size data in the database to confirm whether the identification is successful. If the identification is successful, the calculated actual size is determined as the size information of the target wafer and the next step is continued; if not, an alarm can be issued and this situation is saved for future algorithm training.

[0096] Specifically, after the size characteristics of the target wafer are identified by the OverFeat algorithm, the actual size of the target wafer can be calculated by operating on the size characteristics identified visually according to the optical magnification of the camera, and then it is determined whether the identification is successful by comparing with the preset size data in the database. If the identification fails, an alarm can be issued for manual operation and identification, and this situation is saved and entered into the database for simulation learning to avoid similar situations; if the identification is completed, the next step is carried out.

[0097] S230. Use the set target detection algorithm to identify the notch shape characteristics of the target wafer based on the target image, match the notch shape characteristics in the preset feature database, and if the match is successful, it is determined that the identification of the notch shape characteristics is completed.

[0098] In this embodiment, after the size of the wafer is identified, the OverFeat algorithm can also be used to process the target image to identify the notch shape features of the target wafer, that is, to determine whether the notch shape is Flat or Notch. Among them, in the network architecture of the OverFeat algorithm, feature extraction can be performed through the first five convolutional layers, and classification can be performed through the last three fully convolutional layers. After feature extraction, the OverFeat algorithm will preliminarily classify the Flat (flat-edge notch) or Notch (V-shaped notch) features in the image, calculate the shape and position of the features, and perform classification judgment on the features, and then match the identified notch shape features in the preset feature database. Various known wafer feature data (including Flat and Notch) are pre-stored in the preset feature database, and the accuracy of the extracted features can be confirmed by comparison. If the match is successful, it is confirmed that the recognition is completed. If not, the error handling process can be triggered.

[0099] Further, according to the matching result, if the notch shape recognition is successful, the system sends a confirmation signal and proceeds to the next step of processing; if the notch shape recognition fails, the system records the error and issues an alarm, and can check through manual intervention and mark it to accumulate data for subsequent model training.

[0100] Further, for the sample data with failed recognition, it can be stored to enrich the training database of the algorithm. And the OverFeat algorithm model can be updated and trained regularly according to the training database, and the accuracy and stability of the model can be improved by adding new data.

[0101] Preferably, during the process of feature recognition using the set target detection algorithm, the system recognition performance can be continuously monitored, and the algorithm parameters can be adjusted in real time to meet the production requirements, so as to ensure that the system can accurately identify the Flat / Notch features under different environments, lighting and other conditions.

[0102] S240. Use the set target detection algorithm to extract the feature points in the target image, generate the initial position information of the target wafer in the target coordinate system, determine the wafer center of the target wafer according to the initial position information, determine the offset between the wafer center and the origin of the target coordinate system, and determine the target position of the target wafer according to the offset.

[0103] Among them, the target position of the target wafer is the position that the target wafer needs to reach in the wafer identification and positioning task, and the initial position information is the position of the target wafer before moving.

[0104] In this embodiment, according to the target image captured by the camera, feature points in the target image can be extracted through the OverFeat algorithm, and the center of the target wafer can be determined. By comparing the coordinates of the wafer center with the origin of the target coordinate system, it is judged whether the target wafer is centered. If not, the target wafer needs to be driven to move to the target position according to the offset between the wafer center and the origin of the target coordinate system. Preferably, the target position can be the position corresponding to the origin of the target coordinate system.

[0105] Further, after determining the offset between the wafer center and the origin of the target coordinate system, the offset data can be fed back to the servo control system, and the servo system is made to perform position compensation on the motors in the X-axis and Y-axis directions according to the offset, converting the offset into an electrical signal, thereby controlling the rotation of the motors to drive the target wafer to the target position.

[0106] Preferably, after driving the target wafer to move, the target wafer can be photographed again, and the above process can be repeated to confirm that the target wafer reaches the target position. Specifically, when the offset between the wafer center of the target wafer and the origin of the target coordinate system is less than the set threshold, it can be considered that centering is completed and the next step can be carried out.

[0107] S250. Determine the wafer angle of the target wafer according to the notch shape feature, and determine the target posture of the target wafer according to the angle deviation between the wafer angle and the preset standard angle.

[0108] In this embodiment, according to the target image captured by the camera, the actual angle of the target wafer can be determined through the notch shape feature extracted by the OverFeat algorithm, and then compared with the preset standard angle to calculate the angle deviation, so as to determine the target posture of the target wafer and perform angle adjustment on the target wafer.

[0109] Specifically, the angle deviation between the wafer angle identified by the OverFeat algorithm and the preset standard angle can be fed back to the servo system, and the angle deviation is converted into an electrical signal, thereby controlling the rotation of the motor to correct the wafer angle.

[0110] Further, after performing angle adjustment on the target wafer, the target wafer can be photographed again, and the above process can be repeated to confirm the current angle of the target wafer. If there is still a slight deviation between the current angle and the preset standard angle, fine adjustment can be performed through the feedback mechanism to ensure that the wafer position is accurately centered and the angle is corrected.

[0111] Furthermore, during the entire wafer recognition and positioning process, real-time monitoring can be carried out for each link in the visual recognition and positioning process, and the movement of each control motor can be adjusted in a timely manner through a real-time feedback mechanism to ensure the accuracy and stability of the system. In case of failures in recognition or position correction, an alarm can be issued and data can be saved for subsequent model improvement. For the algorithms applied in the wafer recognition and positioning process, relevant data on recognition accuracy and positioning precision can be continuously accumulated during the wafer recognition and positioning process to enrich the training database, and the algorithm (such as the OverFeat algorithm) model can be retrained using the new data, and the algorithm parameters can be adjusted to improve the stability of system recognition and positioning and make it adaptable to the processing requirements of wafers of different sizes and types.

[0112] Figure 3 FIG. is a schematic diagram of a wafer recognition and positioning process provided by an embodiment of the present invention. As shown in the figure, the present wafer recognition and positioning method is applied to a lithography machine. In the visual recognition module, the OverFeat algorithm is used to sequentially execute steps of wafer size recognition, notch shape feature recognition, determination of the target position, and determination of the target attitude, and the results of each step are fed back to the main control system. The main control system compares the results of each step with the preset data in the database and determines whether the wafer size recognition and the notch shape feature recognition are successful. If successful, the next step is continued; otherwise, manual operation is initiated, and the process data is entered into the database. After the step of determining the target position is completed, the servo system compensates according to the deviation extracted by the visual recognition module, and controls the wafer movement through the drive system and the motor. Similarly, after the step of determining the target attitude is completed, the servo system compensates according to the deviation extracted by the visual recognition module, and controls the angle correction of the wafer through the drive system and the motor. After the wafer moves, the position and angle of the wafer are reconfirmed through the visual module. If there are still deviations from the target position and the target attitude, continuous compensation is performed through the servo system until the wafer reaches the target position and the target attitude.

[0113] The wafer recognition and positioning method disclosed by the present invention can extract the key features of the wafer through visual recognition, and then adjust the position and attitude of the wafer. It can be applied to various types of wafers, solving the problem that traditional lithography machines can only recognize specific types of wafers singly.

[0114] Embodiment III

[0115] Figure 4 FIG. is a schematic structural diagram of a wafer recognition and positioning device provided by Embodiment III of the present invention. As Figure 4 shown, the device includes: a target coordinate system establishment module 310, a feature extraction module 320, and a target position and target attitude determination module 330.

[0116] The target coordinate system establishment module 310 is configured to obtain a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image.

[0117] The feature extraction module 320 is configured to identify the size information of the target wafer according to the target image, and extract the notch shape feature of the target wafer if the identification is successful.

[0118] The target position and target attitude determination module 330 is configured to determine the target position of the target wafer, and determine the target attitude of the target wafer according to the notch shape feature.

[0119] Optionally, the feature extraction module 320 is further configured to:

[0120] Use a set target detection algorithm to identify the size features of the target wafer according to the target image; obtain preset size data, compare the size features with the preset size data, and determine the size information of the target wafer according to the comparison result.

[0121] Optionally, the feature extraction module 320 is further configured to:

[0122] Use a set target detection algorithm to identify the notch shape feature of the target wafer according to the target image; match according to the notch shape feature in a preset feature database, and if the match is successful, determine that the notch shape feature identification is completed.

[0123] Optionally, the target position and target attitude determination module 330 is further configured to:

[0124] Use a set target detection algorithm to extract feature points in the target image, and generate initial position information of the target wafer in the target coordinate system; determine the wafer center of the target wafer according to the initial position information, and determine the offset between the wafer center and the origin of the target coordinate system; determine the target position of the target wafer according to the offset.

[0125] Optionally, the target position and target attitude determination module 330 is further configured to:

[0126] Determine the wafer angle of the target wafer according to the notch shape feature; determine the target attitude of the target wafer according to the angle deviation between the wafer angle and a preset standard angle.

[0127] Optionally, the device further includes a correction module 340, configured to correct the target position and target attitude when the target wafer moves to the target position and target attitude.

[0128] Optionally, the correction module 340 is further configured to:

[0129] Obtain the current image of the target wafer at the target position and in the target posture; use the set target detection algorithm to extract the wafer features of the current image, and determine the current position and current angle of the target wafer; correct the target position according to the offset between the current position and the origin of the target coordinate system, and correct the target posture according to the angular deviation between the current angle and the preset standard angle.

[0130] The wafer identification and positioning device provided by the embodiments of the present invention can execute the wafer identification and positioning method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0131] Embodiment 4

[0132] Figure 5 The structural schematic diagram of the electronic device 10 that can be used to implement the embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described and / or claimed herein.

[0133] As Figure 5 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by at least one processor, and the processor 11 can execute various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.

[0134] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0135] The processor 11 may be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the wafer identification and positioning method.

[0136] In some embodiments, the wafer identification and positioning method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the wafer identification and positioning described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to execute the wafer identification and positioning method by any other suitable means (e.g., by means of firmware).

[0137] The various embodiments of the systems and techniques described above in this document may be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include: implemented in one or more computer programs that may be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.

[0138] The computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when the computer programs are executed by the processor, the functions / operations specified in the flowcharts and / or block diagrams are implemented. The computer programs may be executed entirely on the machine, partially on the machine, as a stand-alone software package partially on the machine and partially on a remote machine, or entirely on a remote machine or server.

[0139] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0140] To provide for interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: 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) by which the user can provide input to the electronic device. Other kinds of devices can also be used to provide for interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, speech input, or tactile input).

[0141] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0142] A computing system may include a client and a server. The client and the server are generally far from each other and usually interact via a communication network. The client-server relationship is created by computer programs running on respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0143] It should be understood that various forms of processes shown above can be used, steps can be reordered, added or deleted. For example, the steps described in the present invention can be executed in parallel, sequentially or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is imposed herein.

[0144] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A wafer identification and positioning method, characterized in that: include: Acquire a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image; Using a set target detection algorithm to identify the size information of the target wafer according to the target image, and if the identification is successful, using the set target detection algorithm to extract the notch shape characteristics of the target wafer; If the size information recognition fails and / or the notch shape feature recognition fails, an alarm is issued to enter the manual recognition step, and the recognition failure is entered into the database for model training; wherein the notch shape feature includes Flat feature and Notch feature; Determine the target position of the target wafer, and determine the target posture of the target wafer according to the notch shape feature; wherein the target position is the position corresponding to the origin of the target coordinate system, and the target coordinate system is established in the field of view of photographing the target wafer, and takes the center of the field of view as the origin.

2. The method according to claim 1, characterized in that Identifying size information of the target wafer according to the target image includes: Identify the size characteristics of the target wafer according to the target image; Acquire preset size data, compare the size feature with the preset size data, and determine the size information of the target wafer according to the comparison result.

3. The method according to claim 1, characterized in that Extracting the notch shape feature of the target wafer includes: Identify the notch shape features of the target wafer according to the target image; The notch shape feature is matched in a preset feature database, and if the match is successful, it is determined that the notch shape feature recognition is completed.

4. The method according to claim 1, characterized in that: Determining a target position of the target wafer includes: Using a set target detection algorithm, feature points in the target image are extracted, and initial position information of the target wafer in the target coordinate system is generated; Determine the wafer center of the target wafer according to the initial position information, and determine the offset between the wafer center and the origin of the target coordinate system; A target position of the target wafer is determined according to the offset.

5. The method according to claim 1, characterized in that Determining a target posture of the target wafer according to the notch shape feature includes: Determining a wafer angle of the target wafer according to the notch shape feature; The target posture of the target wafer is determined according to an angle deviation between the wafer angle and a preset standard angle.

6. The method according to claim 1, characterized in that The method further comprises: After the target wafer moves to the target position and the target posture, the target position and the target posture are corrected.

7. The method according to claim 6, characterized in that Correcting the target position and the target posture includes: Acquire a current image of the target wafer at the target position and the target posture; Using a set target detection algorithm, the wafer features of the current image are extracted to determine the current position and current angle of the target wafer; The target position is corrected according to the offset between the current position and the origin of the target coordinate system, and the target posture is corrected according to the angle deviation between the current angle and a preset standard angle.

8. A wafer identification and positioning device, characterized in that: include: A target coordinate system establishing module, used to acquire a target image obtained by photographing a target wafer, and establish a target coordinate system according to the target image; A feature extraction module, used to identify the size information of the target wafer according to the target image by using a set target detection algorithm, and if the identification is successful, extract the notch shape feature of the target wafer by using the set target detection algorithm; If the size information recognition fails and / or the notch shape feature recognition fails, an alarm is issued to enter the manual recognition step, and the recognition failure is entered into the database for model training; wherein the notch shape feature includes Flat feature and Notch feature; The target position and target attitude determination module is used to determine the target position of the target wafer and determine the target attitude of the target wafer according to the notch shape characteristics; wherein the target position is the position corresponding to the origin of the target coordinate system, and the target coordinate system is established in the field of view of photographing the target wafer, and takes the center of the field of view as the origin.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the wafer identification and positioning method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the wafer identification and positioning method according to any one of claims 1 to 7 when executed.

Images