Wafer measurement method and apparatus based on metrology mark points

Abstract

Embodiments of the present application disclose a wafer measurement method and device based on measurement mark points, comprising: obtaining wafer alignment coordinates of a plurality of measurement mark points of a target wafer; performing target capture on a plurality of first measurement mark points in the plurality of measurement mark points to obtain a coordinate offset of each first measurement mark point, and obtaining a first target capture coordinate of each first measurement mark point based on the wafer alignment coordinate and the coordinate offset of each first measurement mark point; inputting wafer alignment coordinates of a plurality of second measurement mark points, which are different from the plurality of first measurement mark points, into a target capture coordinate prediction model to output a second target capture coordinate of each second measurement mark point; measuring the plurality of first measurement mark points based on each first target capture coordinate, and measuring the plurality of second measurement mark points based on each second target capture coordinate, so as to realize wafer measurement of the target wafer, and the mark positioning time is short and the measurement speed of the mark points is fast.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of semiconductor, and in particular, to a wafer measurement method and device based on measurement mark points. BACKGROUND

[0002] Semiconductor detection technology plays an important role in the processes of semiconductor production, packaging and testing, etc. The measurement of alignment error is an important part of the key process in the semiconductor production process. The alignment error is one of the most important errors that need to be controlled in the key process, which refers to the pattern alignment error between the previous layer and the current layer in the key process operation process, and there is a certain distribution rule on the wafer and the exposure field. In order to ensure that the alignment error is within the threshold range, after each batch of wafer exposure, a lot of alignment error measurements of measurement mark points need to be performed on the overlay measurement machine, and the measurement values are processed by mathematics to obtain the distribution model (overlay model terms) of the alignment error, which is fed back to the semiconductor production equipment for alignment error control of the next batch of wafer exposure.

[0003] The measurement mark points of the alignment error measurement are uniformly distributed on the whole wafer. The optical measurement of the alignment error needs to accurately move the wafer to the position of the measurement light path before measurement, so that the camera obtains a wafer measurement image containing information of the previous layer and the current layer (i.e. a wafer scanning image containing the alignment error measurement mark points), so as to obtain the alignment error through the wafer measurement image. If the positioning of the measurement mark points is not accurate, the wafer measurement image may be shifted and measurement error may be introduced. Therefore, in order to improve the measurement accuracy of the alignment error, the positioning accuracy of the mark points is very high, and therefore how to obtain accurate measurement mark point coordinates is an important part of the wafer measurement process.

[0004] In the process of improving the positioning accuracy of the measurement mark points, the measurement mark points are usually precisely positioned by target capture. The prior art realizes target capture by performing wafer image acquisition, wafer image transmission, algorithm calculation, feedback of calculation results, and wafer motion control of the motion platform on each measurement mark point in the wafer respectively. It takes about 90ms to position one measurement mark point by target capture, and the measurement time of one measurement mark point is generally 200-300ms. Therefore, target capture occupies a large part of the measurement time of the measurement mark points, and the positioning time of the measurement mark points is long, and the measurement speed of the measurement mark points is slow. SUMMARY

[0005] The present application provides a wafer measurement method and device based on measurement mark points, which can shorten the positioning time of the measurement mark points and improve the measurement speed of the measurement mark points.

[0006] In a first aspect, the present application provides a wafer measurement method based on measurement mark points, comprising: obtaining wafer alignment coordinates of a plurality of measurement mark points of a target wafer; performing target capture on a plurality of first measurement mark points in the plurality of measurement mark points to obtain coordinate offsets of each of the first measurement mark points, and obtaining first target capture coordinates of each of the first measurement mark points based on the wafer alignment coordinates and the coordinate offsets of each of the first measurement mark points; inputting the wafer alignment coordinates of a plurality of second measurement mark points other than the plurality of first measurement mark points in the plurality of measurement mark points into a target capture coordinate prediction model, and outputting second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model; and performing measurement on the plurality of first measurement mark points based on the first target capture coordinates of each of the first measurement mark points, and performing measurement on the plurality of second measurement mark points based on the second target capture coordinates of each of the second measurement mark points, so as to realize wafer measurement of the target wafer. By the present application, the first target capture coordinates can be obtained by target capture on the first measurement mark points, and the second target capture coordinates of the second measurement mark points can be quickly obtained through the target capture coordinate prediction model, so that the wafer measurement of the target wafer can be realized without target capture on the plurality of second measurement mark points, the measurement mark point positioning time can be shortened, and the measurement speed of the measurement mark points can be improved.

[0007] In a possible implementation of the first aspect, the first measurement mark points are randomly selected measurement mark points in the plurality of measurement mark points, or measurement mark points located on a target motion trajectory. By the present application, the first measurement mark points can be determined in different ways, and the applicability is strong.

[0008] In a possible implementation of the first aspect, the outputting of the second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model comprises: obtaining coordinate offsets of each of the second measurement mark points through the target capture coordinate prediction model based on the wafer alignment coordinates of each of the second measurement mark points, and outputting the second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model based on the coordinate offsets and the wafer alignment coordinates of each of the second measurement mark points. By the present application, the wafer alignment coordinates can be compensated by obtaining the coordinate offsets, so as to obtain the second target capture coordinates with higher positioning accuracy, the processing speed of the target capture coordinate prediction model is fast, and the positioning speed of the measurement mark points can be further improved while ensuring the accuracy of the second target capture coordinates.

[0009] In a possible implementation of the first aspect, the target capture coordinate prediction model is trained by the following method: obtaining a first training sample set, the first training sample set including sample target capture coordinates and sample wafer alignment coordinates of a plurality of sample measurement mark points, wherein the plurality of sample measurement mark points include the plurality of first measurement mark points and / or a plurality of measurement mark points included in a plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates include the first target capture coordinates of the plurality of first measurement mark points and the wafer alignment coordinates, and / or wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers; obtaining a plurality of position error terms of each of the sample measurement mark points in the field and the inter-field of the target wafer based on the sample wafer alignment coordinates and the sample target capture coordinates of each of the sample measurement mark points, performing high-order polynomial fitting on the plurality of position error terms to obtain a coordinate offset of each of the sample measurement mark points; and establishing the target capture coordinate prediction model based on the sample wafer alignment coordinates and the coordinate offset of each of the sample measurement mark points. According to the present application, in addition to the target capture coordinates and the wafer alignment coordinates of the sample wafer, the first target capture coordinates and the wafer alignment coordinates corresponding to the plurality of first measurement mark points obtained in the measurement process can be used to train the target capture coordinate prediction model, the first training sample set of the target capture coordinate prediction model can be more abundant, the target capture coordinate prediction model can be established by high-order polynomial fitting on the plurality of position error terms, the accuracy of the target capture coordinate prediction model can be improved, and therefore the positioning accuracy of the measurement mark point can be improved.

[0010] In a possible implementation of the first aspect, the target capture coordinate prediction model is trained by the following method: obtaining a first training sample set, the first training sample set including sample target capture coordinates, sample wafer alignment coordinates and measurement quality evaluation indexes of a plurality of sample measurement mark points, wherein the plurality of sample measurement mark points include the plurality of first measurement mark points and / or a plurality of measurement mark points included in a plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates include the first target capture coordinates of the plurality of first measurement mark points and the wafer alignment coordinates, and / or wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers; and establishing the target capture coordinate prediction model based on the sample target capture coordinates, the sample wafer alignment coordinates and the measurement quality evaluation indexes of each of the sample measurement mark points by using a target algorithm, wherein the target algorithm includes a gradient descent algorithm, a principal component analysis algorithm or a deep learning algorithm. According to the present application, the measurement quality evaluation indexes can be included in the first training sample set, the target capture coordinate prediction model can be established based on the measurement quality evaluation indexes by using a plurality of algorithms, and the applicability is strong.

[0011] In a possible implementation of the first aspect, in the first training sample set, the sample wafer alignment coordinates of the sample metrology mark points included in the plurality of sample wafers and the sample target capture coordinates, after the first target capture coordinates of each of the first metrology mark points are obtained based on the wafer alignment coordinates of each of the first metrology mark points and the coordinate offset, the method further includes: adding the wafer alignment coordinates of each of the first metrology mark points and the first target capture coordinates to the first training sample set, and performing correction training on the target capture coordinate prediction model by using the target capture coordinate prediction model as the correction training data. By using the method, the target capture coordinate prediction model can be corrected based on the first target capture coordinates after the first target capture coordinates are obtained, the accuracy of the target capture coordinate prediction model is further improved, and the accuracy of the mark point positioning is further improved.

[0012] In a possible implementation of the first aspect, the wafer alignment coordinates of the plurality of metrology mark points of the target wafer are obtained by: obtaining the wafer alignment coordinates of alignment mark points for wafer alignment in the target wafer; and performing wafer alignment on the target wafer based on the wafer alignment coordinates of the alignment mark points, to obtain the wafer alignment coordinates of the plurality of metrology mark points. By using the method, the wafer alignment coordinates of the plurality of metrology mark points can be obtained by wafer alignment, and the method is suitable for most scenarios of obtaining wafer alignment coordinates.

[0013] In a possible implementation of the first aspect, the wafer alignment coordinates of the plurality of metrology mark points of the target wafer are obtained by: obtaining the wafer alignment coordinates of alignment mark points for wafer alignment in the target wafer; performing wafer alignment on the target wafer based on the wafer alignment coordinates of the alignment mark points, to obtain initial wafer alignment coordinates of the plurality of metrology mark points; and inputting the initial wafer alignment coordinates of each of the metrology mark points into a wafer alignment coordinate correction model, and outputting the wafer alignment coordinates of each of the metrology mark points by using the wafer alignment coordinate correction model. By using the method, the initial wafer alignment coordinates can be obtained by wafer alignment, and the initial wafer alignment coordinates are corrected by using the wafer alignment coordinate correction model to obtain the wafer alignment coordinates, and the accuracy of the wafer alignment coordinates can be further improved.

[0014] In a possible implementation of the first aspect, the wafer alignment coordinate correction model is trained by the following method: obtaining a second training sample set, the second training sample set including sample target capture coordinates of a plurality of sample metrology mark points included in a plurality of sample wafers and sample wafer alignment coordinates corresponding to the sample metrology mark points; calculating coordinate difference values between the sample wafer alignment coordinates and the sample target capture coordinates of each sample metrology mark point; and establishing the wafer alignment coordinate correction model based on the sample wafer alignment coordinates of each sample metrology mark point and the coordinate difference values. According to the present application, the wafer alignment coordinate correction model can be trained by the second training sample set, and the second training sample set is simple to obtain and has strong applicability.

[0015] In a possible implementation of the first aspect, after the first target capture coordinates of each first metrology mark point are obtained based on the wafer alignment coordinates of each first metrology mark point and the coordinate offset, the method further includes: obtaining wafer alignment coordinate errors of each first metrology mark point based on the first target capture coordinates of each first metrology mark point and the wafer alignment coordinates of each first metrology mark point; adding the wafer alignment coordinates of each first metrology mark point and the wafer alignment coordinate errors to the second training sample set as correction training data of the wafer alignment coordinate correction model; and performing correction training on the wafer alignment coordinate correction model. According to the present application, the wafer alignment coordinate correction model can be corrected and trained by the first target capture coordinates obtained in the wafer metrology process, and the accuracy of the wafer alignment coordinate correction model can be further improved, thereby improving the positioning accuracy of the metrology mark points.

[0016] In a possible implementation of the first aspect, the target wafer includes a plurality of fields, the plurality of measurement mark points are a plurality of measurement mark points included in a target field of the plurality of fields, and the distribution states of the measurement mark points in each of the plurality of fields are the same; after the wafer measurement of the target wafer is implemented, the method further includes: constructing a field coordinate prediction model based on the wafer alignment coordinates of the plurality of first measurement mark points and the first target capture coordinates of the target field and the wafer alignment coordinates of the plurality of second measurement mark points and the second target capture coordinates of the target field; when the wafer alignment coordinates of the plurality of measurement mark points included in any field of the plurality of fields except the target field are obtained, the wafer alignment coordinates of each measurement mark point included in the any field are input into the field coordinate prediction model, and the target capture coordinates of the each measurement mark point in the any field are output by the field coordinate prediction model, so as to complete the measurement of the each measurement mark point included in the any field. By using the present application, the target capture coordinates of each measurement mark point in any field can be output by the field coordinate prediction model, the target capture coordinates of each measurement mark point can be obtained without target capture operation, the positioning time of the measurement mark point is further shortened, and the measurement speed of the mark point is improved.

[0017] In a second aspect, the present application provides a wafer measurement device based on measurement mark points, which includes: an acquisition module configured to acquire wafer alignment coordinates of a plurality of measurement mark points of a target wafer; a target capture module configured to perform target capture on a plurality of first measurement mark points of the plurality of measurement mark points to obtain coordinate offsets of each of the first measurement mark points, and configured to obtain first target capture coordinates of each of the first measurement mark points based on the wafer alignment coordinates of each of the first measurement mark points and the coordinate offsets; a prediction module configured to input wafer alignment coordinates of a plurality of second measurement mark points of the plurality of measurement mark points except the plurality of first measurement mark points into a target capture coordinate prediction model, and configured to output second target capture coordinates of each of the second measurement mark points by the target capture coordinate prediction model; and a measurement module configured to perform measurement on the plurality of first measurement mark points based on the first target capture coordinates of each of the first measurement mark points, and configured to perform measurement on the plurality of second measurement mark points based on the second target capture coordinates of each of the second measurement mark points, so as to implement wafer measurement of the target wafer.

[0018] In a third aspect, the present application provides a terminal device, which includes: an image acquisition device, a processor and a memory; the processor is connected with the memory, the memory is configured to store program code, and the image acquisition device and the processor are configured to call the program code to execute the method provided in the first aspect and any possible implementation of the first aspect.

[0019] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program is suitable for being loaded and executed by a processor to perform the method provided in the first aspect and any possible implementation manner of the first aspect. BRIEF DESCRIPTION OF DRAWINGS

[0020] Figure 1 is a structural schematic diagram of a wafer measurement system based on measurement mark points provided by the present application;

[0021] Figure 2 is a distribution schematic diagram of measurement mark points and alignment mark points of a target wafer provided by the present application;

[0022] Figure 3 is a flowchart of a wafer measurement method based on measurement mark points provided by the present application;

[0023] Figure 4 is another flowchart of a wafer measurement method based on measurement mark points provided by the present application;

[0024] Figure 5 is another flowchart of a wafer measurement method based on measurement mark points provided by the present application;

[0025] Figure 6 is another flowchart of a wafer measurement method based on measurement mark points provided by the present application;

[0026] Figure 7 is a structural schematic diagram of a wafer measurement device based on measurement mark points provided by the present application;

[0027] Figure 8 is a structural schematic diagram of a terminal device provided by the present application. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described below with reference to the drawings in the embodiments of the present application.

[0029] For the convenience of understanding, first, some nouns are simply explained as follows:

[0030] 1. Field, a part of area in a target wafer, a target wafer includes multiple fields, the size of each field is the same, and the distribution state of mark points in the field is the same. Usually, one field includes one alignment mark point and multiple measurement mark points.

[0031] 2. Alignment mark point, refers to a feature point on a target wafer for wafer alignment, usually located at the geometric center position of a field.

[0032] 3、measurement mark, refers to a feature point on a target wafer used for measuring wafer alignment error of the wafer, which is usually uniformly distributed in each field.

[0033] 4、target acquisition, refers to the process of moving the measurement mark in the field of view to the center position of the field of view when the image acquisition device of the wafer scans the target wafer to obtain the target wafer image, wherein the distance between the measurement mark and the center position of the field of view of the target wafer image is called the alignment error.

[0034] Embodiment I

[0035] The wafer measurement method based on the measurement mark provided in the present application can be applied to alignment error measurement of wafer mark positioning, and can also be extended to application scenarios such as size measurement between marks, focus position measurement, and other application scenarios that require positioning and measurement of specific marks. For ease of description, the present application is described by taking the application scenario of alignment error measurement based on wafer mark positioning as an example, and taking a terminal device as an example. Figure 1 , Figure 1 is a structural schematic diagram of the wafer measurement system based on the measurement mark provided in the present application. As shown in Figure 1 , the wafer measurement system based on the measurement mark can include a terminal device 1a, a motion stage 1b, and a motion controller 1c.

[0036] In some possible embodiments, the motion stage 1b described above can be used to carry the target wafer and carry the target wafer based on the target motion trajectory. The motion stage 1b described above can be an X / Z / Theta axis motion stage, or can be other motion stages that can carry the target wafer, and the present application does not limit this. The X / Z / Theta axis motion stage is taken as an example for description. It can be understood that the motion stage 1b described above can move on the X axis, the Z axis, and the Theta axis, corresponding to horizontal movement, vertical movement, and rotation movement, respectively. The motion stage 1b described above can be used to carry the target wafer and adjust the position of the target wafer through movement. Optionally, the motion stage 1b described above can also include a Y axis motion stage, which can carry the target wafer to make the target wafer move longitudinally. The motion stage 1b described above can move according to the target motion trajectory, and the target motion trajectory described above can be one of a spiral trajectory, a concentric circle trajectory, a square trajectory, a polygon trajectory, and a horizontal and vertical trajectory.

[0037] In some possible embodiments, the motion controller 1c described above can be a microcontroller, a central controller, or other controller, which can be used to obtain or generate the target motion trajectory of the target wafer and control the motion stage 1b to move based on the target motion trajectory. Optionally, the motion controller 1c can also be integrated into the motion control module in the terminal device 1a, and the present application does not limit this.

[0038] In some possible embodiments, the target wafer carried on the motion stage 1b includes a plurality of fields, each of which includes a plurality of measurement mark points and at least one alignment mark point. For ease of description, the present application takes an example of each field including one alignment mark point for description. The distribution state of the measurement mark points and the alignment mark points in each field is the same, and the size of each field is also the same. The alignment mark point is used for alignment of the target wafer, and the measurement mark point is used for measurement of the alignment error of the target wafer. For ease of understanding the distribution of the measurement mark points and the alignment mark points of the target wafer, please refer to Figure 2 , Figure 2 FIG. 1 is a schematic diagram of the distribution of the measurement mark points and the alignment mark points of the target wafer provided by the present application. As shown in Figure 2 , the target wafer includes a plurality of fields (not all shown in the figure, only part of the fields are shown) of the same size, such as field 1, field 2, field 3, field 4 and field 5, each of which includes one alignment mark point and a plurality of measurement mark points (not all shown in Figure 2 , only part of the measurement mark points of the field 1 are shown). Taking the field 1 as an example, the field 1 includes an alignment mark point, a measurement mark point 1, a measurement mark point 2, a measurement mark point 3 and a measurement mark point 4. The alignment mark point can be located at the geometric center of the field, and the measurement mark points are as uniformly distributed as possible in each field.

[0039] In some possible embodiments, the terminal device 1a can include a memory, and the memory can store a computer program of a target capture coordinate prediction model, a wafer alignment coordinate correction model, a field-in coordinate prediction model and the like. The terminal device 1a can be used to obtain wafer alignment coordinates of a plurality of measurement mark points of a target wafer, wherein one measurement mark point is marked by one wafer alignment coordinate, and the plurality of measurement mark points include a plurality of first measurement mark points and a plurality of second measurement mark points. It should be noted that the first measurement mark points can be determined according to the training requirements of the target capture coordinate prediction model, the wafer alignment coordinate correction model and / or the field-in coordinate prediction model and the like, for example, the target motion trajectory can be planned based on the training requirements, and the measurement mark points passed by the target motion trajectory are determined as the first measurement mark points.

[0040] In some possible embodiments, the terminal device 1a can include an image acquisition device, for example Figure 1The image acquisition device 1d shown can be a camera or the like that can acquire a target wafer image of a target wafer. The image acquisition device 1d can be used to scan the target wafer to obtain a target wafer image of the target wafer, so as to perform target capture, wafer alignment, and the like of the target wafer. Optionally, the image acquisition device can be located outside the terminal device 1a. If the image acquisition device 1d is located outside the terminal device 1a, the terminal device 1a can be transmitted to the terminal device 1a after scanning the target wafer to obtain a target wafer image, so as to perform target capture, wafer alignment, and the like of the target wafer based on the target wafer image. For ease of description, the terminal device 1a includes the image acquisition device 1d in this application, which will not be described again.

[0041] In some possible implementations, the terminal device 1a can perform target capture on the first measurement mark point based on the wafer alignment coordinates of the first measurement mark point. The terminal device 1a can determine a coordinate offset of the wafer alignment coordinates of the first measurement mark point through the target capture operation, compensate the wafer alignment coordinates based on the coordinate offset, and obtain first target capture coordinates of the first measurement mark point. For example, if the wafer alignment coordinates of the first measurement mark point are (1, 2), and the coordinate offset determined through the target capture is (0, -0.5), the first target capture coordinates can be (1, 1.5). It should be noted that the coordinate offset is used to indicate the difference between the wafer alignment coordinates of the first measurement mark point and the center of the field of view of the target wafer image. By compensating the difference, the first measurement mark point can be moved to the center of the field of view of the target wafer image.

[0042] In some possible implementations, the terminal device 1a can store a target capture coordinate prediction model. The terminal device 1a can input the wafer alignment coordinates of a plurality of second measurement mark points other than the plurality of first measurement mark points in the plurality of measurement mark points into the target capture coordinate prediction model, so as to skip the operation of directly performing target capture on the second measurement mark points, predict and output the second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model, and reduce the time required for mark positioning of the second measurement mark points. For example, the wafer alignment coordinates of a second measurement mark point in the plurality of second measurement mark points can be (0, 1), and the terminal device 1a can input (0, 1) into the target capture coordinate prediction model. The target capture coordinate prediction model can output the coordinates (1, 1) as the second target capture coordinates of the second measurement mark point with the wafer alignment coordinates (0, 1).

[0043] In some possible implementation manners, the terminal device 1a can further measure the plurality of first measurement mark points based on the first target capture coordinates corresponding to the first measurement mark points, and measure the plurality of second measurement mark points based on the second target capture coordinates corresponding to the second measurement mark points, so as to implement wafer measurement of the target wafer. For example, the terminal device 1a can control the motion stage 1b to carry the target wafer to the first target capture coordinates or the second target capture coordinates by using the motion controller 1c or a motion control module in the terminal device 1a, so as to implement wafer measurement of the target wafer, and avoid poor detection accuracy of wafer alignment error caused by positioning error of the first measurement mark points or the second measurement mark points. The first measurement mark points can be randomly selected from the plurality of measurement mark points. Alternatively, the first measurement mark points can be determined based on a target motion trajectory planned according to a training requirement of the target capture coordinate prediction model, or the first measurement mark points can be determined according to other rules, which is not limited in this application.

[0044] In some possible implementation manners, the terminal device 1a can predict, by using the target capture coordinate prediction model, a coordinate offset of each second measurement mark point based on a wafer alignment coordinate of the second measurement mark point, and compensate, by using the target capture coordinate prediction model, the wafer alignment coordinate of each second measurement mark point based on the coordinate offset of the second measurement mark point, to output a second target capture coordinate of each second measurement mark point. For example, if the target capture coordinate prediction model detects that a coordinate offset of a second measurement mark point is (1, 0) and a wafer alignment coordinate of the second measurement mark point is (0, 1), the target capture coordinate prediction model can obtain a second target capture coordinate of the second measurement mark point as (1, 1).

[0045] In some possible implementation manners, the terminal device 1a can obtain a first training sample set of the target capture coordinate prediction model, and train the target capture coordinate prediction model based on training sample data included in the first training sample set. The first training sample set can include sample target capture coordinates and sample wafer alignment coordinates of a plurality of sample measurement mark points. The plurality of sample measurement mark points include a plurality of first measurement mark points and / or a plurality of measurement mark points included in a plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates include first target capture coordinates and wafer alignment coordinates of the plurality of first measurement mark points and / or wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers. In other words, if the terminal device 1a does not obtain the first target capture coordinates of the first measurement mark points, the wafer alignment coordinates and the target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers can be obtained as the sample wafer alignment coordinates and the sample target capture coordinates to train the target capture coordinate prediction model. The sample wafers can be wafers that have completed wafer measurement before wafer measurement is performed on the target wafer. The target capture coordinate prediction model is trained by using the first training sample set, the data of the first training sample set is convenient to obtain, the data of the first training sample set is rich, and therefore the prediction accuracy of the target capture coordinate prediction model trained by using the first training sample set can be enhanced, and the adaptability is high. If the terminal device 1a has obtained a plurality of first target capture coordinates obtained by target capture on the plurality of first measurement mark points, the first target capture coordinates and the wafer alignment coordinates corresponding to the plurality of first measurement mark points can be used as the sample target capture coordinates and the sample wafer alignment coordinates in the first training sample set to train the target capture coordinate prediction model. Optionally, the first training sample set can also include the first target capture coordinates, the wafer alignment coordinates of the measurement mark points of the target wafer, and the target capture coordinates and the wafer alignment coordinates of the measurement mark points of the sample wafer. The first target capture coordinates and the wafer alignment coordinates obtained in the wafer measurement process of the target wafer are added to the first training sample set to train the target capture coordinate prediction model, so that the sample data of the first training sample set is more rich, and the prediction accuracy of the target capture coordinate prediction model trained by using the first training sample set can be enhanced.

[0046] In some possible implementation manners, the target capture coordinate prediction model can be a high-order fitting model. The terminal device 1a can obtain, by scaling, translation, distortion, or the like, a plurality of position error terms of each sample measurement mark point in the field and the interfield of the target wafer based on the sample wafer alignment coordinates and the sample target capture coordinates of the sample measurement mark point in the first training sample set. The plurality of position error terms of the same sample measurement mark point can be obtained by performing a plurality of different operations on the sample wafer alignment coordinates and the sample target capture coordinates of the same sample measurement mark point. Then, the plurality of position error terms obtained based on the same sample measurement mark point can be fitted by a high-order polynomial, so as to obtain the coordinate offset of the sample measurement mark point. The terminal device 1a can fit the plurality of position error terms obtained based on each sample measurement mark point by a high-order polynomial, so as to obtain the coordinate offset (which can also be referred to as a bias value) of each sample measurement mark point. Then, the target capture coordinate prediction model can be established based on the sample wafer alignment coordinates and the coordinate offset of each sample measurement mark point.

[0047] Optionally, in some possible implementation manners, the target capture coordinate prediction model can also be an artificial intelligence algorithm model. The first training sample set can further include a measurement quality evaluation index. The sample target capture coordinates of one sample measurement mark point correspond to one measurement quality evaluation index. The measurement quality evaluation index is used to evaluate the reliability of the sample target capture coordinates. When the reliability reaches a threshold value, it is indicated that the sample target capture coordinates can be regarded as the actual target capture coordinates. The threshold value can be a pre-set threshold value such as 80% or 90%, which should be determined according to the specific form of the product, and the present application does not make any limitation. It should be noted that the first target capture coordinates obtained by the terminal device 1a through target capture are the measurement quality evaluation index that reaches the threshold value. The terminal device 1a can establish the target capture coordinate prediction model by using a target algorithm based on the sample target capture coordinates, the sample wafer alignment coordinates, and the measurement quality evaluation index of each sample measurement mark point. The target algorithm includes but is not limited to a gradient descent algorithm, a principal component analysis algorithm, or a deep learning algorithm, and the present application does not make any limitation.

[0048] Optionally, in some possible implementations, if the training sample data used by the terminal device 1a when training the target capture coordinate prediction model is the wafer alignment coordinates and the target capture coordinates of the plurality of sample metrology mark points corresponding to the sample wafer, after the terminal device 1a performs target capture on the plurality of first metrology mark points and generates the first target capture coordinates, the terminal device 1a adds the wafer alignment coordinates and the first target capture coordinates of each first metrology mark point to the first training sample set as the correction training data of the target capture coordinate prediction model, inputs the correction training data into the target capture coordinate prediction model, and further performs correction training on the target capture coordinate prediction model. For example, the terminal device 1a can obtain the predicted target capture coordinates of the first metrology mark point by inputting the wafer alignment coordinates of the first metrology mark point into the target capture coordinate prediction model, and further obtain the correction training data (i.e., the correction training data for the first metrology mark point) of the target capture coordinate prediction model by comparing the predicted target capture coordinates and the first target capture coordinates of the first metrology mark point. In this way, the terminal device 1a can obtain the correction training data of the plurality of metrology mark points and perform correction training on the target capture coordinate prediction model based on the correction training data.

[0049] In some possible implementations, the terminal device 1a can obtain the wafer alignment coordinates of the plurality of metrology mark points through a wafer alignment operation. The terminal device 1a can obtain the wafer alignment coordinates of the alignment mark points used for wafer alignment in the target wafer, and perform wafer alignment on the target wafer based on the wafer alignment coordinates of the alignment mark points to obtain the wafer alignment coordinates of the plurality of metrology mark points. For example, the terminal device 1a can align the reference mark points in the reference layer of the target wafer with the alignment mark points to align the reference layer with the target wafer, and thus obtain the wafer alignment coordinates of the plurality of metrology mark points after alignment.

[0050] Optionally, in some possible embodiments, the terminal device la can also correct the wafer alignment coordinates obtained through wafer alignment by using a wafer alignment coordinate correction model, so as to obtain the corrected wafer alignment coordinates of the plurality of measurement mark points. For ease of understanding, if the terminal device la corrects by using the wafer alignment coordinate correction model, the wafer alignment coordinates obtained through wafer alignment and not corrected can be determined as initial wafer alignment coordinates. The terminal device la can obtain the initial wafer alignment coordinates of the plurality of measurement mark points and input the plurality of initial wafer alignment coordinates into the wafer alignment coordinate correction model, so that the wafer alignment coordinate correction model can output the wafer alignment coordinates obtained by correcting each initial wafer alignment coordinate. For example, if the wafer alignment coordinates of one of the plurality of measurement mark points are (1, 2), the terminal device la can input (1, 2) into the wafer alignment coordinate correction model, and the wafer alignment coordinate correction model can output the coordinates (2, 2) as the wafer alignment coordinates of the measurement mark point with the initial wafer alignment coordinates (1, 2), for obtaining the target capture coordinates of the wafer.

[0051] In some possible embodiments, the terminal device la can train the wafer alignment coordinate correction model. The terminal device la can obtain a second training sample set of the wafer alignment coordinate correction model, and the second training sample set can include the sample target capture coordinates and the sample wafer alignment coordinates of a plurality of sample measurement mark points included in a plurality of sample wafers, wherein one sample measurement mark point corresponds to one sample target capture coordinate and one sample wafer alignment coordinate. The terminal device la can calculate the coordinate difference between the sample target capture coordinates and the sample wafer alignment coordinates of each sample measurement mark point, so as to establish the wafer alignment coordinate correction model based on the coordinate difference, so that the wafer alignment coordinate correction model can obtain the ability of outputting the wafer alignment coordinates corresponding to any initial wafer alignment coordinate based on the input of any initial wafer alignment coordinate.

[0052] In some possible embodiments, after obtaining the first target capture coordinates of each first measurement mark point, the terminal device 1a can obtain wafer alignment coordinate errors of each first measurement mark point based on the first target capture coordinates and the wafer alignment coordinates corresponding to each first measurement mark point. For example, if the first target capture coordinates are (1, 1.5) and the wafer alignment coordinates are (1, 2), the wafer alignment coordinate error can be (0, -0.5). The terminal device 1a can input the wafer alignment coordinates and the wafer alignment coordinate errors of each first measurement mark point into the wafer alignment coordinate correction model, and use the wafer alignment coordinates and the wafer alignment coordinate errors as correction training data of the wafer alignment coordinate correction model to perform correction training on the wafer alignment coordinate correction model. For example, the terminal device 1a can input the wafer alignment coordinate error (0, -0.5) and the wafer alignment coordinates (1, 2) into the wafer alignment coordinate correction model, and perform correction training on the wafer alignment coordinate correction model based on the correction training data.

[0053] In some possible embodiments, the plurality of measurement mark points can be a plurality of measurement mark points included in a target field of a plurality of fields in the target wafer. After performing wafer measurement on the target wafer, the terminal device 1a can construct an intra-field coordinate prediction model based on the wafer alignment coordinates and the first target capture coordinates of the plurality of first measurement mark points and the wafer alignment coordinates and the second target capture coordinates of the plurality of second measurement mark points included in the target field, and then predict the target capture coordinates of the plurality of measurement mark points in any field other than the target field through the intra-field coordinate prediction model. For example, the terminal device 1a can use the wafer alignment coordinates and the first target capture coordinates of the plurality of first measurement mark points and the wafer alignment coordinates and the second target capture coordinates of the plurality of second measurement mark points in the target field as construction samples of the intra-field coordinate prediction model, perform iterative training on the intra-field coordinate prediction model based on the construction samples, and construct the intra-field coordinate prediction model. The intra-field coordinate prediction model has the ability to output the target capture coordinates corresponding to the wafer alignment coordinates of a measurement mark point included in any field other than the target field. When the terminal device 1a obtains the wafer alignment coordinates of the plurality of measurement mark points included in any field other than the target field, the terminal device 1a can input the wafer alignment coordinates of each measurement mark point included in any field into the intra-field coordinate prediction model, and output the target capture coordinates of each measurement mark point in any field through the intra-field coordinate prediction model to complete measurement of each measurement mark point included in any field. For example, if the wafer alignment coordinates of one of the plurality of measurement mark points included in any field are (3, 3), the terminal device 1a can input (3, 3) into the intra-field coordinate prediction model, and the intra-field coordinate prediction model can output (4, 4) as the target capture coordinates of the measurement mark point with the wafer alignment coordinates (3, 3).

[0054] It should be noted that the above target capture coordinate prediction model, wafer alignment coordinate correction model and in-field coordinate prediction model can be a high-order fitting model, an artificial intelligence algorithm model, a neural network model, etc. The type of the above model is not limited in the present application.

[0055] By using the present application, the wafer measurement system based on the measurement mark points can obtain the first target capture coordinate by target capture of the first measurement mark point, and quickly and accurately obtain the second target capture coordinate of the second measurement mark point through the target capture coordinate prediction model, so as to realize the wafer measurement of the target wafer, shorten the measurement mark point positioning time, improve the measurement speed of the measurement mark point, and have simple operation and strong adaptability. In addition, the wafer measurement system can also obtain the wafer alignment coordinates of each measurement mark point through the wafer alignment coordinate correction model, and obtain the target capture coordinates of the measurement mark points of multiple fields through the in-field coordinate prediction model, so as to improve the acquisition efficiency of the wafer alignment coordinates and / or the target capture coordinates of the measurement mark points, thereby improving the efficiency of the wafer measurement, and having simple operation and strong applicability.

[0056] Embodiment Two

[0057] Referring to Figure 3 , Figure 3 is a flowchart of a wafer measurement method based on measurement mark points provided by the present application. Figure 3 The wafer measurement method based on measurement mark points shown in Figure 1 The wafer measurement system based on measurement mark points shown in FIG. 1 is described by taking a terminal device as an execution subject for the convenience of description. As Figure 3 The wafer measurement method based on measurement mark points shown in FIG. 1 can include the following steps:

[0058] In step S101, the wafer alignment coordinates of the plurality of measurement mark points of the target wafer are obtained.

[0059] In some possible embodiments, the terminal device can acquire wafer alignment coordinates of the plurality of measurement mark points in the target wafer. Optionally, the terminal device can directly acquire the wafer alignment coordinates of the plurality of measurement mark points through wafer alignment. The terminal device can acquire a wafer alignment coordinate of an alignment mark point for wafer alignment in the target wafer, for example, the terminal device can acquire the wafer alignment coordinate of the alignment mark point as (5, 5). The terminal device can perform wafer alignment on the target wafer based on the wafer alignment coordinate of the alignment mark point, for example, move a reference mark point in a reference layer to the wafer alignment coordinate (5, 5) so that the reference mark point is aligned with the alignment mark point. Further, based on the alignment of the reference mark point and the alignment mark point, the terminal device can detect the wafer alignment coordinates of the plurality of measurement mark points through image recognition on a target wafer image of the target wafer, where the target wafer image can be obtained by an image acquisition device in the terminal device scanning the target wafer; the image acquisition device can also be located outside the terminal device, and the terminal device can acquire the target wafer image from the image acquisition device. Further optionally, the terminal device can correct the wafer alignment coordinates through a wafer alignment coordinate correction model. The terminal device can acquire initial wafer alignment coordinates of the plurality of measurement mark points in the target wafer through wafer alignment, and then input the plurality of initial wafer alignment coordinates into the wafer alignment coordinate correction model, so as to output each wafer alignment coordinate through the wafer alignment coordinate correction model. For example, if the initial wafer alignment coordinate of one of the plurality of measurement mark points is (1, 2), the terminal device can input (1, 2) to the wafer alignment coordinate correction model, and the wafer alignment coordinate correction model can output the coordinate (2, 2) as the wafer alignment coordinate of the measurement mark point with the initial wafer alignment coordinate (1, 2).

[0060] In step S102, target capture is performed on the plurality of first measurement mark points to obtain a coordinate offset of each of the first measurement mark points, and a first target capture coordinate of each of the first measurement mark points is obtained based on the wafer alignment coordinate of each of the first measurement mark points and the coordinate offset.

[0061] In some possible implementation manners, the terminal device can perform target capture based on wafer alignment coordinates of the plurality of first measurement mark points, to obtain coordinate offset of each first measurement mark point, and correct the wafer alignment coordinates based on the coordinate offset of each first measurement mark point to obtain each first target capture coordinate. For example, if the wafer alignment coordinate of the above one first measurement mark point is (2, 2), the coordinate offset of the first measurement mark point determined through target capture is (0, -0.5), and the first target capture coordinate of the first measurement mark point can be obtained as (2, 1.5). The plurality of first measurement mark points can be randomly selected from the plurality of measurement mark points included in the target wafer, can be the plurality of measurement mark points included in the target motion trajectory, or can be determined according to other manners. The actual product form should be determined, which is not limited here. It can be understood that, since the target motion trajectory can be planned according to the training requirement of the target capture coordinate prediction model, the plurality of first measurement mark points determined based on the planned target motion trajectory can better meet the training requirement of the target capture coordinate prediction model, and additional target wafer motion time caused by no planning of the motion path can be avoided. Therefore, the positioning time of the measurement mark point can be further shortened, and the measurement speed of the measurement mark point can be improved.

[0062] In some possible implementation manners, the terminal device can train the target capture coordinate prediction model. The terminal device can obtain a first training sample set of the target capture coordinate prediction model, and the first training sample set can include sample target capture coordinates of a plurality of sample measurement mark points and sample wafer alignment coordinates. The plurality of sample measurement mark points can include a plurality of first measurement mark points and / or a plurality of measurement mark points included in a plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates can include first target capture coordinates and wafer alignment coordinates of the plurality of first measurement mark points and / or wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers. In other words, the first training sample set can include the first target capture coordinates and the wafer alignment coordinates corresponding to the plurality of first measurement mark points, or can include the wafer alignment coordinates and the target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers, or can include the wafer alignment coordinates and the target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers and the first target capture coordinates and the wafer alignment coordinates corresponding to the plurality of first measurement mark points. The sample wafers can be wafers on which wafer measurement has been completed before target wafer measurement. The implementation manner of training the target capture coordinate prediction model by using the sample wafers can enhance the prediction accuracy of the target capture coordinate prediction model trained by using the first training sample set by using the convenience of obtaining data of the first training sample set and the richness of data of the first training sample set, and the source of obtaining the first training sample set is rich and adaptable.

[0063] In some possible implementation manners, the target capture coordinate prediction model can be a high-order fitting model, and the terminal device can obtain a plurality of position error terms of each sample measurement mark point in a field and between fields of the target wafer by scaling, translation, distortion, or the like based on the sample wafer alignment coordinates and the sample target capture coordinates of each sample measurement mark point in the first training sample set. The plurality of position error terms of the same sample measurement mark point can be obtained by performing different operations on the sample wafer alignment coordinates and the sample target capture coordinates of the same sample measurement mark point, and then a high-order polynomial fitting can be performed on the plurality of position error terms obtained based on the same sample measurement mark point, so as to obtain a coordinate offset of the sample measurement mark point. The terminal device can perform high-order polynomial fitting on the plurality of position error terms obtained based on each sample measurement mark point, so as to obtain a coordinate offset (the coordinate offset can also be referred to as a bias value) of each sample measurement mark point, and then establish the target capture coordinate prediction model based on the sample wafer alignment coordinates and the coordinate offset of each sample measurement mark point.

[0064] Optionally, in some possible embodiments, the target capture coordinate prediction model can also be an artificial intelligence algorithm model, and the first training sample set can further include a metrology quality evaluation index, a sample target capture coordinate of a sample metrology mark point corresponds to a metrology quality evaluation index, and the metrology quality evaluation index is used to evaluate the reliability of the sample target capture coordinate. When the reliability reaches a threshold value, it is indicated that the sample target capture coordinate can be regarded as an actual target capture coordinate, and the threshold value can be 80%, 90%, or a pre-set threshold value, which should be determined according to the specific form of the product and is not limited in the present application. It should be noted that the first target capture coordinate obtained by the terminal device through target capture is a metrology quality evaluation index that reaches the threshold value. The terminal device can establish a target capture coordinate prediction model based on the sample target capture coordinates, sample wafer alignment coordinates, and metrology quality evaluation indexes of the sample metrology mark points in the plurality of sample wafers, wherein the target algorithm includes but is not limited to a gradient descent algorithm, a principal component analysis algorithm, or a deep learning algorithm, and the present application is not limited. It can be understood that if the terminal device does not obtain the first target capture coordinate and the wafer alignment coordinate corresponding to the first metrology mark point, the wafer alignment coordinates and the target capture coordinates of the plurality of metrology mark points in the plurality of sample wafers are included in the first training sample set. If the terminal device has obtained the first target capture coordinate and the wafer alignment coordinate corresponding to the plurality of first metrology mark points of the target wafer, the historical data of the first target capture coordinates and the wafer alignment coordinates of the plurality of first metrology mark points can be added to the first training sample set. By adding the plurality of first target capture coordinates obtained during the wafer metrology process of the target wafer to the first training sample set, the diversity of the data acquisition path of the first training sample set can be improved, the richness of the sample data of the first training sample set can be improved, the operation is simple, and the applicability is strong.

[0065] In some possible embodiments, if the training sample data used by the terminal device to train the target capture coordinate prediction model is the sample wafer alignment coordinates and the sample target capture coordinates of the plurality of sample metrology mark points corresponding to the sample wafer, when the terminal device obtains the first target capture coordinates of each first metrology mark point, the wafer alignment coordinates and the first target capture coordinates corresponding to each first metrology mark point can also be added to the first training sample set as correction training data of the target capture coordinate prediction model to correct the training of the target capture coordinate prediction model. That is, the terminal device can correct the target capture coordinate prediction model after target capture of the plurality of first metrology mark points, so that the second target capture coordinates output by the target capture coordinate prediction model gradually approach the actual value in the process of target capture of the plurality of first metrology mark points, and the prediction accuracy of the target capture coordinate prediction model can be further improved.

[0066] In some possible implementation manners, the terminal device can further determine, based on the training requirement of the target capture coordinate prediction model, a measurement mark point that needs to be captured, and determine a plurality of first measurement mark points from the plurality of measurement mark points for target capture. The terminal device can plan a target motion trajectory of the target wafer according to the training requirement of the target capture coordinate prediction model. Since the training requirement of the target capture coordinate prediction model is considered when the target motion trajectory is generated, the efficiency of measurement on the plurality of measurement mark points can be improved by planning the target motion trajectory, and the wafer measurement time of the target wafer can be further shortened. The terminal device can determine, based on the target motion trajectory, a plurality of measurement mark points passed through by the target motion trajectory as the plurality of first measurement mark points to capture the first measurement mark points.

[0067] In step S103, the wafer alignment coordinates of a plurality of second measurement mark points other than the plurality of first measurement mark points are input into the target capture coordinate prediction model, and second target capture coordinates of each of the second measurement mark points are output by the target capture coordinate prediction model.

[0068] In some possible implementation manners, the terminal device can obtain, by using the target capture coordinate prediction model, second target capture coordinates corresponding to each of the second measurement mark points other than the first measurement mark points. For example, if the wafer alignment coordinates of one of the second measurement mark points are (0, 1), the terminal device can input (0, 1) into the target capture coordinate prediction model, and the target capture coordinate prediction model can predict and output coordinates (1, 1) as the second target capture coordinates of the second measurement mark point with the wafer alignment coordinates of (0, 1). By using the target capture coordinate prediction model, the process of directly capturing the second measurement mark point can be skipped, the target capture coordinates of the second measurement mark point can be quickly output, the measurement mark positioning time can be further shortened, and the measurement speed of the measurement mark point can be improved.

[0069] In some possible implementation manners, the terminal device can obtain, by using the target capture prediction model, a coordinate offset of each of the second measurement mark points based on the wafer alignment coordinates of the second measurement mark point, and compensate, by using the target capture coordinate prediction model, the wafer alignment coordinates of each of the second measurement mark points based on the coordinate offset of the second measurement mark point, to output the second target capture coordinates of each of the second measurement mark points.

[0070] In step S104, the plurality of first measurement mark points are measured based on the first target capture coordinates corresponding to each of the first measurement mark points, and the plurality of second measurement mark points are measured based on the second target capture coordinates corresponding to each of the second measurement mark points, to implement wafer measurement on the target wafer.

[0071] In some possible implementation manners, the terminal device can measure the plurality of first measurement mark points based on the plurality of first target capture coordinates, and measure the plurality of second measurement mark points based on the plurality of second target capture coordinates. The terminal device can trigger the target wafer to move to the first target capture coordinates or the second target capture coordinates, so as to measure the target wafer. When all the first measurement mark points and all the second measurement mark points on the target wafer are measured, wafer measurement of the target wafer can be achieved.

[0072] By using the present application, the first target capture coordinates of the first measurement mark points can be obtained through target capture, and the second target capture coordinates of the second measurement mark points can be quickly and accurately obtained through the target capture coordinate prediction model, so as to achieve wafer measurement of the target wafer. The measurement mark positioning time can be shortened, the measurement speed of the measurement mark points can be improved, the operation is simple, and the adaptability is strong. In addition, the plurality of measurement mark points can be quickly positioned through the target capture coordinate prediction model and the wafer alignment coordinate correction model, and the plurality of models can be applied to subsequent wafer measurement, without the need to reestablish the model, so that the wafer measurement time can be further shortened. The plurality of models can be corrected during wafer measurement, so that the prediction accuracy of the plurality of models is high.

[0073] In order to facilitate understanding of the above wafer measurement method based on measurement mark points, refer to Figure 4 , Figure 4 is another flowchart of the wafer measurement method based on measurement mark points provided by the present application. As shown in Figure 4 , the wafer measurement method based on measurement mark points can include the following steps:

[0074] Step S201, obtaining wafer alignment coordinates of a plurality of measurement mark points of a target wafer.

[0075] In some possible implementation manners, the terminal device can obtain the wafer alignment coordinates of the plurality of measurement mark points. For the convenience of understanding, the implementation manner of the above step S201 can be jointly referred to the description of the above step S101, and will not be repeated here.

[0076] Step S202, triggering the target wafer to move so as to sequentially move each measurement mark point to the corresponding wafer alignment coordinates.

[0077] In some possible implementation manners, the terminal device triggers the motion of the motion stage to carry the target wafer to move so as to sequentially move each measurement mark point to the wafer alignment coordinate corresponding to each measurement mark point, from the alignment target wafer. For example, if the wafer alignment coordinate of the measurement mark point indicated by the target motion trajectory is (4, 4) and measurement needs to be performed, the terminal device can trigger the motion of the motion stage to carry the target wafer to move, so as to move the measurement mark point to the wafer alignment coordinate (4, 4), thereby performing wafer alignment based on the measurement mark point with the wafer alignment coordinate (4, 4).

[0078] In step S203, it is determined whether the measurement mark point currently reached by the target wafer is the first measurement mark point.

[0079] In some possible implementation manners, the terminal device can identify the measurement mark point indicated by the wafer alignment coordinate corresponding to the wafer alignment coordinate currently reached by the target wafer, and determine whether the wafer alignment coordinate point is the first measurement mark point. If the terminal device identifies that the measurement mark point is the first measurement mark point, step S204 is performed; if the terminal device identifies that the measurement mark point is the second measurement mark point, step S205 is performed.

[0080] In step S204, target capture is performed on the first measurement mark point, to obtain the first target capture coordinate corresponding to the first measurement mark point.

[0081] In some possible implementation manners, if the terminal device identifies that the measurement mark point is the first measurement mark point, target capture can be performed on the first measurement mark point, to generate the first target capture coordinate. Optionally, the terminal device can also add the first target capture coordinate corresponding to the first measurement mark point and the wafer alignment coordinate to the first training sample set of the target capture coordinate prediction model, so as to train the target capture coordinate prediction model based on the updated first training sample set. For ease of understanding, the implementation manner of step S204 can be jointly referred to the description of step S102, and will not be described herein again.

[0082] In step S205, the wafer alignment coordinates of each second measurement mark point are input into the target capture coordinate prediction model, and the second target capture coordinate corresponding to each second measurement mark point is output by the target capture coordinate prediction model.

[0083] In some possible implementation manners, if the terminal device identifies the measurement mark point as the second measurement mark point, i.e., the terminal device identifies that the measurement mark point reached by the current motion is not the first measurement mark point, the wafer alignment coordinates of the second measurement mark point can be input into the target capture coordinate prediction model, and the second target capture coordinates corresponding to the second measurement mark point can be output by the target capture coordinate prediction model. It can be understood that the terminal device can identify each measurement mark point in sequence to determine each second measurement mark point, and then input the wafer alignment coordinates of each second measurement mark point into the target capture coordinate prediction model to make the target capture coordinate prediction model output the second target capture coordinates of each second measurement mark point. For ease of understanding, the implementation manners of the step S206 can be jointly referred to the description of the step S103, and details are not described herein.

[0084] In some possible implementation manners, before the terminal device calls the target capture coordinate prediction model to predict the second target capture coordinates, the terminal device can perform the step S2051 and the step S2052 to train the target capture coordinate prediction model.

[0085] In the step S2051, a first training sample set of the target capture coordinate prediction model is obtained.

[0086] In some possible implementation manners, the terminal device can obtain the first training sample set of the target capture coordinate prediction model, and the first set includes a plurality of sample target capture coordinates and a plurality of sample wafer alignment coordinates. The sample target capture coordinates can include the first target capture coordinates of the first measurement mark point of the target wafer and / or the sum target capture coordinates of the measurement mark points of the sample wafer, and the sample wafer alignment coordinates can include the wafer alignment coordinates of the first measurement mark point of the target wafer and / or the sum wafer alignment coordinates of the measurement mark points of the sample wafer.

[0087] Optionally, if the target capture coordinate prediction model is an artificial intelligence algorithm model, the first training sample set further includes a measurement quality evaluation index. The implementation manners of the step S2051 can be jointly referred to the description of the first training sample set in the step S102, and details are not described herein.

[0088] In the step S2052, the target capture coordinate prediction model is trained based on the first training sample set.

[0089] In some possible implementation manners, the terminal device can train the target capture coordinate prediction model based on the first training sample set. For example, if the target capture coordinate prediction model is a high-order polynomial model, the terminal device can perform high-order polynomial fitting training on the target capture coordinate prediction model based on the first training sample set. Alternatively, if the target capture coordinate prediction model is an artificial intelligence algorithm model, the terminal device can train the target capture coordinate prediction model through a gradient descent algorithm, a principal component analysis algorithm, or a deep learning algorithm based on the first training sample set. Through the above training of the target capture coordinate prediction model based on the first training sample set, the target capture coordinate prediction model can obtain the capability of outputting the target capture coordinates of the measurement mark points corresponding to any wafer alignment coordinates based on any input wafer alignment coordinates.

[0090] In some possible implementation manners, the terminal device can plan a target motion trajectory according to the training requirement of the target capture coordinate prediction model, so as to determine the plurality of first measurement mark points based on the target motion trajectory. Alternatively, the terminal device can also not plan the target motion trajectory, which is not limited in the present application. The implementation manners of the step S2052 can be jointly referred to the description of the target capture coordinate prediction model in the step S102, and details are not repeated.

[0091] In step S206, each first measurement mark point is measured based on the first target capture coordinate corresponding to the first measurement mark point, and each second measurement mark point is measured based on the second target capture coordinate corresponding to the second measurement mark point.

[0092] In some possible implementation manners, if the terminal device obtains the first target capture coordinates of the first measurement mark points, the target wafer motion can be triggered to move the first measurement mark points to the positions of the first target capture coordinates, so as to measure the first measurement mark points. If the terminal device obtains the second target capture coordinates of the second measurement mark points, the target wafer motion can be triggered to move the second measurement mark points to the positions of the second target capture coordinates, so as to measure the second measurement mark points. For ease of understanding, the implementation manners of the step S206 can be jointly referred to the description of the step S104, and details are not repeated.

[0093] In step S207, it is determined whether the measurement of all measurement mark points is completed.

[0094] In some possible implementation manners, the terminal device can determine whether all the measurement mark points indicated by the target motion trajectory are measured according to the target motion trajectory, and if yes, execute step S208 to end the flow; or if not, execute step S202 to measure the next measurement mark point indicated by the target motion trajectory. For example, if the wafer alignment coordinates of the next measurement mark point are (5, 5), the terminal device can trigger the target wafer to move to the position of the coordinates (5, 5).

[0095] Step S208, completing the wafer measurement on the target wafer.

[0096] When the terminal device completes the measurement of all the measurement mark points, the terminal device can output a signal or the like indicating that the wafer measurement on the target wafer is completed, so as to complete the wafer measurement on the target wafer.

[0097] By using the present application, the second target capture coordinates of the second measurement mark point can be quickly output by using the target capture coordinate prediction model, the sample data of the target capture coordinate prediction model is rich and easy to obtain, in addition, the terminal device can correct and train the target capture coordinate prediction model according to the target capture result (i.e., the first target capture coordinates) of the first measurement mark point, so as to further improve the prediction accuracy of the target capture coordinate prediction model, and therefore, the present application can shorten the positioning time of the measurement mark point and improve the measurement speed of the measurement mark point.

[0098] Embodiment Three

[0099] In some possible implementation manners, the terminal device can obtain the wafer alignment coordinates of each measurement mark point in the target wafer by using the wafer alignment coordinate correction model. For the purpose of facilitating the understanding of the application of the wafer alignment coordinate correction model, please refer to Figure 5 , Figure 5 is another flowchart of the wafer measurement method based on the measurement mark point provided by the present application. As shown in Figure 5 , the wafer measurement method based on the measurement mark point can include the following steps:

[0100] Step S301, obtaining a second training sample set of the wafer alignment coordinate correction model.

[0101] In some possible implementation manners, the terminal device can obtain a second training sample set of the wafer alignment coordinate correction model, wherein the second training sample set includes the sample target capture coordinates and the sample wafer alignment coordinates of a plurality of sample measurement mark points included in a plurality of sample wafers, one sample measurement mark point corresponds to one sample target capture coordinate and one sample wafer alignment coordinate. Here, the implementation manner of obtaining the second training sample set requested to be protected in step S301 can be jointly referred to the description of step S101 above, and will not be repeated here.

[0102] Step S302, training the wafer alignment coordinate correction model based on the second training sample set.

[0103] In some possible implementation manners, the terminal device can train the wafer alignment coordinate correction model based on the sample target capture coordinates and the sample wafer alignment coordinates of the plurality of sample measurement mark points, for example, by calculating the coordinate difference between the sample wafer alignment coordinates and the sample target capture coordinates of each sample measurement mark point, and establishing the wafer alignment coordinate correction model based on the sample wafer alignment coordinates and the coordinate difference of each plurality of sample measurement mark points, so that the wafer alignment coordinate correction model has the capability of outputting the wafer alignment coordinates corresponding to any wafer alignment coordinate based on any input initial wafer alignment coordinate.

[0104] Step S303, obtaining the wafer alignment coordinates of each measurement mark point of the target wafer by the wafer alignment coordinate correction model.

[0105] In some possible implementation manners, the wafer alignment coordinate correction model trained can be stored in the terminal device. The terminal device can perform wafer alignment on the target wafer to obtain the initial wafer alignment coordinates of each measurement mark point of the target wafer, input the initial wafer alignment coordinates into the wafer alignment coordinate correction model, and correct the initial wafer alignment coordinates by the wafer alignment coordinate correction model to output the wafer alignment coordinates corresponding to each measurement mark point. Here, the implementation manner of obtaining the wafer alignment coordinates of each measurement mark point of the target wafer requested to be protected in step S303 can be referred to the description of step S101 above, and will not be described herein again.

[0106] Step S304, triggering the target wafer to move to sequentially move each measurement mark point to the corresponding wafer alignment coordinate.

[0107] In some possible implementation manners, after the terminal device obtains the wafer alignment coordinates of each measurement mark point, the terminal device can trigger the motion stage to carry the target wafer to move each measurement mark point to the wafer alignment coordinate (for example, (2, 2)) corresponding to each measurement mark point. For the convenience of understanding, the implementation manner of step S304 above can be referred to the description of steps S102 and S204 above, and will not be described herein again.

[0108] Step S305, determining whether the measurement mark point corresponding to the position currently reached by the target wafer is the first measurement mark point.

[0109] In some possible implementation manners, the terminal device can identify whether the position to which the target wafer currently moves is the wafer alignment coordinate of the first measurement mark point, for example, if the target wafer moves according to the target movement trajectory planned based on the training requirement of the target capture coordinate prediction model, whether the position to which the target wafer currently moves is the movement mark of the measurement mark point on the target movement trajectory can be identified, if yes, the measurement mark point corresponding to the position to which the target wafer currently moves can be determined as the first measurement mark point, if no, the measurement mark point corresponding to the position to which the target wafer currently moves can be determined as not the first measurement mark point. If the terminal device determines that the measurement mark point corresponding to the position to which the target wafer currently moves is the first measurement mark point, step S306 is performed, if not, step S304 is performed.

[0110] In step S306, target capture is performed on the first measurement mark point, and a first target capture coordinate is obtained.

[0111] In some possible implementation manners, the terminal device can perform target capture on the first measurement mark point based on the target wafer image of the target wafer, and obtain the first target capture coordinate of the first measurement mark point through image recognition or the like. For ease of understanding, the implementation manners of step S306 can be jointly referred to the description of step S102, and details are not described herein.

[0112] In step S307, the wafer alignment coordinate correction model is corrected and trained based on the first target capture coordinate and the wafer alignment coordinate.

[0113] In some possible implementation manners, the terminal device can calculate the wafer alignment coordinate error of the first measurement mark point based on the first target capture coordinate corresponding to the first measurement mark point and the wafer alignment coordinate. For example, if the first target capture coordinate is (2, 1.5) and the wafer alignment coordinate is (2, 2), the wafer alignment coordinate error is (0, -0.5). The terminal device can also add the wafer alignment coordinate of the first measurement mark point and the wafer alignment coordinate error to the second training sample set, to serve as the correction training data of the wafer alignment coordinate correction model, and correct and train the wafer alignment coordinate correction model.

[0114] In step S308, it is determined whether the measurement of all the first measurement mark points is completed.

[0115] In some possible implementations, the terminal device can determine whether the measurement of all the first measurement mark points is completed based on the target motion trajectory or the wafer alignment coordinates of the first measurement mark points. For example, if the target wafer has moved to the end point of the target motion trajectory, it indicates that the measurement of all the first measurement mark points is completed. Alternatively, if the terminal device detects that the initial wafer alignment coordinates input to the wafer alignment coordinate correction model are the initial wafer alignment coordinates of the last first measurement mark point, it indicates that the measurement of all the first measurement mark points is completed. Similarly, if the target wafer has not moved to the end point of the target motion trajectory, it indicates that the measurement of all the first measurement mark points is not completed. Alternatively, if the terminal device detects that the initial wafer alignment coordinates input to the wafer alignment coordinate correction model are not the wafer alignment coordinates of the last first measurement mark point, it indicates that the measurement of all the first measurement mark points is not completed. When the terminal device determines that the measurement of all the first measurement mark points is completed, step S309 can be performed; when the terminal device determines that the measurement of all the first measurement mark points is not completed, step S304 is performed.

[0116] In step S309, the wafer alignment coordinate correction model is stored.

[0117] When the measurement of all the first measurement mark points is completed, the terminal device can store the wafer alignment coordinate correction model so that the wafer alignment coordinate correction model can be applied to subsequent wafer measurement.

[0118] According to the present application, the wafer alignment coordinates corresponding to each measurement mark point can be quickly obtained through the wafer alignment coordinate correction model, the positioning time of the measurement mark point can be further shortened, and the measurement speed of the measurement mark point can be improved. In addition, the first target capture coordinates obtained through target capture during wafer measurement can be compared with the wafer alignment coordinates predicted by the wafer alignment coordinate correction model, the wafer alignment coordinate correction model can be corrected through the difference between the two, and the prediction accuracy of the wafer alignment coordinate correction model can be improved.

[0119] Embodiment Four

[0120] In some possible implementations, the target wafer includes a plurality of fields, the plurality of measurement mark points described in the above-described embodiments two and three can be a plurality of measurement mark points included in a target field included in the target wafer, and the distribution states of the measurement mark points in each of the plurality of fields are the same. The terminal device can construct a field-in coordinate prediction model after implementing wafer measurement on the target field included in the target wafer. The above-described field-in coordinate prediction model can also be constructed by using the data of the wafer that has been measured, and can be stored in the terminal device after being constructed, so as to be directly called in the wafer measurement on the target wafer, so as to complete the measurement of each measurement mark point included in any field other than the target field in the target wafer. For ease of understanding, see Figure 6 , Figure 6is another flowchart of the wafer measurement method based on the metrology mark points provided in the present application. As shown in Figure 6 The wafer measurement method based on the metrology mark points can include the following steps:

[0121] Step S401, constructing an intra-field coordinate prediction model.

[0122] In some possible implementation manners, the terminal device can construct the intra-field coordinate prediction model based on the wafer alignment coordinates and the first target capture coordinates of the plurality of first metrology mark points included in the target field, and the wafer alignment coordinates and the second target capture coordinates corresponding to the plurality of second metrology mark points. For example, the wafer alignment coordinates and the first target capture coordinates of the plurality of first metrology mark points included in the target field, and the wafer alignment coordinates and the second target capture coordinates corresponding to the plurality of second metrology mark points can be taken as training samples of the intra-field coordinate prediction model, and the intra-field coordinate prediction model is iteratively trained based on the training samples, so that the intra-field coordinate prediction model has the function of outputting the target capture coordinates of any metrology mark point included in any field other than the target field according to the wafer alignment coordinates of the any metrology mark point.

[0123] Step S402, sequentially outputting the target capture coordinates of each metrology mark point in any field by the intra-field coordinate prediction model.

[0124] In some possible implementation manners, when the terminal device obtains the wafer alignment coordinates of the plurality of metrology mark points included in any field other than the target field, the terminal device can input the wafer alignment coordinates of each metrology mark point included in any field into the intra-field coordinate prediction model, and output the target capture coordinates of each metrology mark point in any field by the intra-field coordinate prediction model, so as to complete the measurement of each metrology mark point included in any field. For example, if the plurality of wafer alignment coordinates of the plurality of metrology mark points in a field are (7, 7), (8, 8), and (9, 9), the terminal device can input (7, 7), (8, 8), and (9, 9) into the intra-field coordinate prediction model, and the intra-field coordinate prediction model can output (7.5, 7), (8.5, 8), and (9.5, 9) as the target capture coordinates of the metrology mark points with the wafer alignment coordinates of (7, 7), (8, 8), and (9, 9), respectively. It can be understood that when the terminal device obtains the target capture coordinates of the plurality of metrology mark points included in any field other than the target field in the target wafer, the measurement of the next field can be performed, for example, the terminal device can input the wafer alignment coordinates of the plurality of metrology mark points included in the next field into the intra-field coordinate prediction model, so as to sequentially output the target capture coordinates of each metrology mark point in any field.

[0125] Step S403, performing correction training on the intra-field coordinate prediction model based on the wafer alignment coordinates and the target capture coordinates of each metrology mark point in any field.

[0126] In some possible implementation, after the terminal device obtains the target capture coordinates of each measurement mark point in any field through the field coordinate prediction model, the terminal device can input the target capture coordinates of each measurement mark point in any field into the field coordinate prediction model to perform correction training on the field coordinate prediction model. For example, the terminal device can determine a loss value of a loss function of the field coordinate prediction model through the plurality of target capture coordinates, and update the field coordinate prediction model by compensating the loss value, so as to improve the accuracy of the target capture coordinates output by the field coordinate prediction model. That is, the field coordinate prediction model can perform correction on the field coordinate prediction model based on the plurality of output target capture coordinates after outputting the plurality of target capture coordinates of any field, so as to enrich the training data of the field coordinate prediction model and improve the prediction accuracy of the field coordinate prediction model.

[0127] In step S404, each measurement mark point is measured based on the target capture coordinates of each measurement mark point in any field.

[0128] In some possible implementation, the terminal device can trigger the target wafer motion carried by the motion table based on the target capture coordinates of each measurement mark point in any field, so as to move each measurement mark point to the target capture coordinates corresponding to the measurement mark point in sequence, and measure each measurement mark point.

[0129] In step S405, it is determined whether the measurement of all fields is completed.

[0130] In some possible implementation, the terminal device can determine whether the measurement of all fields is completed by determining whether the wafer alignment coordinates of the measurement mark point are the wafer alignment coordinates corresponding to the last measurement mark point. For example, the terminal device can determine whether the measurement of all fields is completed according to the wafer alignment coordinates of the last measurement mark point indicated by the target motion trajectory. If the wafer alignment coordinates of the last measurement mark point are (9, 9), when the terminal device detects that the wafer alignment coordinates of the current measurement mark point are (9, 9), it can be determined that the measurement of all fields is completed, and step S406 is performed. Otherwise, it is determined that the measurement of all fields is not completed, and step S402 is performed.

[0131] In step S406, the field coordinate prediction model is stored.

[0132] In some possible implementation, if the terminal device determines that the measurement of all fields is completed, the terminal device can store the field coordinate prediction model obtained after the measurement of all fields is completed, so that the field coordinate prediction model can be applied to wafer measurement of other target wafers in the future.

[0133] By adopting the application, target capture coordinates of multiple measurement mark points in any field except a target field in a target wafer can be quickly output through an in-field coordinate prediction model, and measurement of each measurement mark point can be performed based on the target capture coordinates output by the in-field coordinate prediction model without target capture and other operations on the multiple measurement mark points in any field, so that the positioning time of the measurement mark points is short and the measurement speed of the measurement mark points is fast.

[0134] Embodiment five

[0135] Referring to Figure 7 , Figure 7 is a structural schematic diagram of a wafer measurement device based on measurement mark points provided by the application. As Figure 7 indicated, the wafer measurement device based on measurement mark points 10 can be a computer device having a computer program (including program code) for implementing the wafer image scanning method. The wafer measurement device based on measurement mark points 10 can also be a computer program, for example, an application software. The device can be used to perform corresponding steps in the wafer measurement method based on measurement mark points provided by the application, such as Figure 1 indicated, a terminal device. As Figure 7 indicated, the wafer measurement device based on measurement mark points 10 can include a first acquisition module 101, a target capture module 102, a first prediction module 103, and a measurement module 104:

[0136] The first acquisition module 101 is configured to acquire wafer alignment coordinates of multiple measurement mark points of a target wafer.

[0137] The target capture module 102 is configured to perform target capture on multiple first measurement mark points of the multiple measurement mark points to obtain coordinate offsets of each of the first measurement mark points, and obtain first target capture coordinates of each of the first measurement mark points based on the wafer alignment coordinates of each of the first measurement mark points and the coordinate offsets.

[0138] The first prediction module 103 is configured to input the wafer alignment coordinates of multiple second measurement mark points except the multiple first measurement mark points among the multiple measurement mark points into a target capture coordinate prediction model, and output second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model.

[0139] The measurement module 104 is configured to perform measurement on the multiple first measurement mark points based on the first target capture coordinates of each of the first measurement mark points, and perform measurement on the multiple second measurement mark points based on the second target capture coordinates of each of the second measurement mark points, so as to achieve wafer measurement on the target wafer.

[0140] In some possible implementation manners, the first measurement mark point in the wafer measurement device based on measurement mark points is a randomly selected measurement mark point in the plurality of measurement mark points, or a measurement mark point located on the target motion trajectory in the plurality of measurement mark points.

[0141] In some possible implementation manners, the first prediction module 103 further includes an output unit 1031.

[0142] The output unit 1031 is configured to obtain, by the target capture coordinate prediction model, a coordinate offset of each second measurement mark point based on the wafer alignment coordinate of each second measurement mark point, and output, by the target capture coordinate prediction model, a second target capture coordinate of each second measurement mark point based on the coordinate offset of each second measurement mark point and the wafer alignment coordinate of each second measurement mark point.

[0143] In some possible implementation manners, the wafer measurement device based on measurement mark points further includes a second acquisition module 105, a fitting module 106, and a first establishment module 107.

[0144] The second acquisition module 105 is configured to acquire a first training sample set, the first training sample set including sample target capture coordinates and sample wafer alignment coordinates of a plurality of sample measurement mark points, wherein the plurality of sample measurement mark points include the plurality of first measurement mark points and / or a plurality of measurement mark points included in a plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates include the first target capture coordinates and the wafer alignment coordinates of the plurality of first measurement mark points, and / or wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers.

[0145] The fitting module 106 is configured to obtain a plurality of position error terms of each sample measurement mark point in a field and between fields of the target wafer based on the sample wafer alignment coordinates and the sample target capture coordinates of each sample measurement mark point, and perform high-order polynomial fitting on the plurality of position error terms to obtain a coordinate offset of each sample measurement mark point.

[0146] The first establishment module 107 is configured to establish the target capture coordinate prediction model based on the sample wafer alignment coordinates and the coordinate offset of each sample measurement mark point.

[0147] In some possible implementation manners, the wafer measurement device based on measurement mark points further includes a third acquisition module 108.

[0148] The third obtaining module 108 is configured to obtain a first training sample set, wherein the first training sample set comprises sample target capture coordinates of a plurality of sample metrology mark points, sample wafer alignment coordinates, and a metrology quality evaluation index, the plurality of sample metrology mark points comprise the plurality of first metrology mark points and / or a plurality of metrology mark points comprised by a plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates comprise the first target capture coordinates of the plurality of first metrology mark points and the wafer alignment coordinates, and / or wafer alignment coordinates and target capture coordinates of the plurality of metrology mark points comprised by the plurality of sample wafers.

[0149] In some possible implementation manners, the wafer metrology device based on metrology mark points further comprises a second establishing module 109:

[0150] The second establishing module 109 is configured to establish the target capture coordinate prediction model by using a target algorithm based on the sample target capture coordinates, the sample wafer alignment coordinates, and the metrology quality evaluation index of each sample metrology mark point, wherein the target algorithm comprises a gradient descent algorithm, a principal component analysis algorithm, or a deep learning algorithm.

[0151] In some possible implementation manners, the wafer metrology device based on metrology mark points further comprises a first correcting module 110:

[0152] The first correcting module 110 is configured to add the wafer alignment coordinates and the first target capture coordinates of each first metrology mark point to the first training sample set as correction training data of the target capture coordinate prediction model, and perform correction training on the target capture coordinate prediction model.

[0153] In some possible implementation manners, the first obtaining module 101 comprises a first obtaining unit 1011 and an alignment unit 1012:

[0154] The first obtaining unit 1011 is configured to obtain wafer alignment coordinates of alignment mark points for wafer alignment in the target wafer.

[0155] The alignment unit 1012 is configured to perform wafer alignment on the target wafer based on the wafer alignment coordinates of the alignment mark points, to obtain wafer alignment coordinates of the plurality of metrology mark points.

[0156] In some possible implementation manners, the first obtaining module 101 further comprises a second obtaining unit 1013 and a prediction unit 1014:

[0157] The second acquisition unit 1013 is configured to acquire wafer alignment coordinates of alignment mark points in the target wafer for wafer alignment, and perform wafer alignment on the target wafer based on the wafer alignment coordinates of the alignment mark points to obtain initial wafer alignment coordinates of the plurality of measurement mark points.

[0158] The prediction unit 1014 is configured to input the initial wafer alignment coordinates of each measurement mark point into a wafer alignment coordinate correction model, and output wafer alignment coordinates of each measurement mark point through the wafer alignment coordinate correction model.

[0159] In some possible implementation manners, the first acquisition module 101 further includes a third acquisition unit 1015 and a training unit 1016.

[0160] The third acquisition unit 1015 is configured to acquire a second training sample set, and the second training sample set includes sample target capture coordinates and sample wafer alignment coordinates of a plurality of sample measurement mark points included in a plurality of sample wafers, one sample wafer alignment coordinate corresponding to one sample measurement mark point and one sample target capture coordinate.

[0161] The training unit 1016 is configured to calculate a coordinate difference between the sample wafer alignment coordinates and the sample target capture coordinates of each sample measurement mark point, and establish the wafer alignment coordinate correction model based on the sample wafer alignment coordinates of each sample measurement mark point and the coordinate difference.

[0162] In some possible implementation manners, the wafer measurement device based on the measurement mark point further includes a third acquisition module 111 and a second correction module 112.

[0163] The third acquisition module 111 is configured to obtain wafer alignment coordinate errors of each first measurement mark point based on the first target capture coordinates of each first measurement mark point and wafer alignment coordinates of each first measurement mark point.

[0164] The second correction module 112 is configured to add the wafer alignment coordinates and the wafer alignment coordinate errors of each first measurement mark point to the second training sample set as correction training data of the wafer alignment coordinate correction model, and perform correction training on the wafer alignment coordinate correction model.

[0165] In some possible implementation manners, the wafer measurement device based on the measurement mark point further includes a construction module 113 and a second prediction module 114.

[0166] The constructing module 113 is configured to construct an intra-field coordinate prediction model based on the wafer alignment coordinates of the plurality of first measurement mark points and the first target capture coordinates of the target field, and the wafer alignment coordinates of the plurality of second measurement mark points and the second target capture coordinates of the target field.

[0167] The second prediction module 114 is configured to, when the wafer alignment coordinates of the plurality of measurement mark points in any field other than the target field are obtained, input the wafer alignment coordinates of each measurement mark point in the any field into the intra-field coordinate prediction model, and output the target capture coordinates of each measurement mark point in the any field by the intra-field coordinate prediction model, so as to complete the measurement of each measurement mark point in the any field.

[0168] In some possible implementation manners, the implementation manners of each module and / or unit included in the wafer measurement device can refer to the implementation manners provided by each step in the wafer measurement method based on measurement mark points shown in the foregoing description, and will not be described herein. Figures 3 to 6 The wafer measurement method based on measurement mark points shown in the foregoing description, and will not be described herein.

[0169] In the present application, the wafer measurement device based on measurement mark points can obtain the first target capture coordinates by target capture of the first measurement mark point, and quickly and accurately obtain the second target capture coordinates of the second measurement mark point by the target capture coordinate prediction model, so as to realize the wafer measurement of the target wafer, shorten the measurement mark positioning time, improve the measurement speed of the measurement mark, and have simple operation and strong adaptability. In addition, the wafer measurement device based on measurement mark points can quickly position the plurality of measurement mark points by the target capture coordinate prediction model and the wafer alignment coordinate correction model, and the plurality of models can be applied to subsequent wafer measurement, without the need to reestablish the model, so that the wafer measurement time can be further shortened, and the plurality of models can be corrected in the wafer measurement process, so that the prediction accuracy of the plurality of models is high.

[0170] Embodiment Six

[0171] Please refer to Figure 8 , Figure 8 is a structural schematic diagram of a terminal device provided in the present application. As shown in Figure 8As shown, the terminal device 100 can include a processor 1001, a network interface 1004, a memory 1005, a controller 1006 and an image acquisition device 1007. In addition, the terminal device 100 can further include a user interface 1003 and at least one communication bus 1002. The communication bus 1002 is used to realize the connection communication between the components. The user interface 1003 can include a display, a keyboard, and optionally a standard wired interface, a wireless interface. The network interface 1004 can optionally include a standard wired interface, a wireless interface (such as a WI-FI interface). The memory 1005 includes a random access memory (RAM) and a non-volatile memory (NVM), such as an erasable programmable read-only memory (EPROM). The memory 1005 can also be at least one storage device located away from the aforementioned processor 1001. The aforementioned controller 1006 can be used to receive data sent by the processor and generate control instructions to control devices such as a motion platform, and to execute the functions of the controller described in the foregoing Figures 1 to 6 The functions implemented by the controller involved in the embodiment. The image acquisition device 1007 can be a line array camera or the like, which can be used to scan a target wafer to obtain a target wafer image. As shown Figure 8 The memory 1005 as a computer readable storage medium can include an operating system, a network communication module, a user interface module and a device control application. The memory 1005 in the embodiment can execute the functions of the memory described in the foregoing Figure 1 The processor 1001 described in the embodiment can execute the functions of the processor described in the foregoing Figure 1 The functions executed by the processor provided in the embodiment.

[0172] In the terminal device 100 as shown Figure 8 The network interface 1004 can provide network communication functions in the terminal device 100. The user interface 1003 is mainly used to provide an input interface for the user. The processor 1001 and the image acquisition device 1007 can be used to call the device control application stored in the memory 1005 to realize the functions of the terminal device 100 described in the foregoing Figures 3 to 6 The wafer measurement method based on the measurement mark point in the embodiment.

[0173] It should be understood that the terminal device 100 described in the embodiment of the present application can execute the functions of the terminal device 100 described in the foregoing Figures 3 to 6The wafer measurement method based on the measurement mark points of the embodiment is not described again. In addition, the beneficial effects of using the same method are not described again.

[0174] In addition, it is pointed out here that the embodiment of the present application also provides a computer readable storage medium, and the computer readable storage medium stores the computer program executed by the wafer measurement method based on the measurement mark points mentioned above, and the computer program includes program instructions, and when the processor executes the program instructions, the wafer measurement method based on the measurement mark points mentioned above can be executed. Figures 3 to 6 The wafer measurement method based on the measurement mark points provided by the embodiment is not described again. In addition, the beneficial effects of using the same method are not described again. For the technical details not disclosed in the computer readable storage medium embodiment of the present application, please refer to the description of the method embodiment of the present application.

[0175] The computer readable storage medium can be an internal storage unit of the terminal device provided by any of the preceding embodiments, for example, a hard disk or a memory of the terminal device. The computer readable storage medium can also be an external storage device of the terminal device, for example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the terminal device. Further, the computer readable storage medium can include both the internal storage unit and the external storage device of the terminal device. The computer readable storage medium is used to store the computer program and other programs and data required by the terminal device. The computer readable storage medium can also be used to temporarily store data that has been output or will be output.

[0176] In addition, it is pointed out here that the embodiment of the present application also provides a computer program product or a computer program, which includes computer instructions stored in a computer readable storage medium. The processor of the terminal device loads and executes the computer instructions, so that the terminal device can execute the wafer measurement method based on the measurement mark points mentioned above. Figures 3 to 6 The method provided by the embodiment.

[0177] Those of ordinary skill in the art can realize that the system and algorithm steps of the examples described in conjunction with the embodiments disclosed herein can be realized in electronic hardware, computer software or a combination of both. In order to clearly illustrate the interchangeability of hardware and software, the components and steps of the examples have been described in the above description in general terms. The skilled person can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

Claims

1. A wafer measurement method based on measurement mark points, characterized in that: include: Obtaining wafer alignment coordinates of a plurality of measurement mark points of a target wafer; performing target capture on a plurality of first measurement mark points among the plurality of measurement mark points to obtain a coordinate offset of each of the first measurement mark points, and obtaining a first target capture coordinate of each of the first measurement mark points based on the wafer alignment coordinates and the coordinate offset of each of the first measurement mark points; Inputting the wafer alignment coordinates of a plurality of second measurement mark points among the plurality of measurement mark points except the plurality of first measurement mark points into a target capture coordinate prediction model, and outputting second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model; The multiple first measurement mark points are measured based on the first target capture coordinates of each first measurement mark point, and the multiple second measurement mark points are measured based on the second target capture coordinates of each second measurement mark point to achieve wafer measurement of the target wafer.

2. The method according to claim 1, characterized in that The first measurement mark point is a measurement mark point randomly selected from the multiple measurement mark points, or a measurement mark point located on the target motion trajectory from the multiple measurement mark points.

3. The method according to claim 1, characterized in that Outputting the second target capture coordinates of each second measurement marker point through the target capture coordinate prediction model includes: The coordinate offset of each second measurement mark point is obtained based on the wafer alignment coordinates of each second measurement mark point through the target capture coordinate prediction model, and the second target capture coordinates of each second measurement mark point are output based on the coordinate offset of each second measurement mark point and the wafer alignment coordinates of each second measurement mark point through the target capture coordinate prediction model.

4. The method according to claim 1, wherein The target capture coordinate prediction model is trained by the following method: Acquire a first training sample set, wherein the first training sample set includes sample target capture coordinates and sample wafer alignment coordinates of a plurality of sample measurement mark points, wherein the plurality of sample measurement mark points include the plurality of first measurement mark points and / or the plurality of measurement mark points included in the plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates include the first target capture coordinates and the wafer alignment coordinates of the plurality of first measurement mark points, and / or the wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers; Obtaining a plurality of position error terms of each of the sample measurement mark points within and between fields of the target wafer based on the sample wafer alignment coordinates and the sample target capture coordinates of each of the sample measurement mark points, and performing high-order polynomial fitting on the plurality of position error terms to obtain a coordinate offset of each of the sample measurement mark points; The target capture coordinate prediction model is established based on the sample wafer alignment coordinates and the coordinate offsets of each of the sample measurement mark points.

5. The method according to claim 1, wherein The target capture coordinate prediction model is trained by the following method: Acquire a first training sample set, wherein the first training sample set includes sample target capture coordinates, sample wafer alignment coordinates, and measurement quality evaluation indicators of a plurality of sample measurement mark points, wherein the plurality of sample measurement mark points include the plurality of first measurement mark points and / or the plurality of measurement mark points included in the plurality of sample wafers, and the sample target capture coordinates and the sample wafer alignment coordinates include the first target capture coordinates and the wafer alignment coordinates of the plurality of first measurement mark points, and / or the wafer alignment coordinates and target capture coordinates of the plurality of measurement mark points included in the plurality of sample wafers; Based on the sample target capture coordinates, the sample wafer alignment coordinates and the measurement quality evaluation index of each of the sample measurement mark points, a target capture coordinate prediction model is established using a target algorithm, wherein the target algorithm includes a gradient descent algorithm, a principal component analysis algorithm or a deep learning algorithm.

6. The method according to claim 4 or 5, characterized in that The first training sample set includes sample wafer alignment coordinates and sample target capture coordinates of a plurality of sample measurement mark points included in a plurality of sample wafers. After obtaining the first target capture coordinates of each of the first measurement mark points based on the wafer alignment coordinates and the coordinate offset of each of the first measurement mark points, the method further includes: The wafer alignment coordinates and the first target capture coordinates of each of the first measurement mark points are added to the first training sample set as correction training data of the target capture coordinate prediction model to perform correction training on the target capture coordinate prediction model.

7. The method according to any one of claims 1 to 5, characterized in that The step of obtaining wafer alignment coordinates of a plurality of measurement mark points of a target wafer includes: Obtaining wafer alignment coordinates of alignment mark points in the target wafer for wafer alignment; Wafer alignment is performed on the target wafer based on the wafer alignment coordinates of the alignment mark points to obtain the wafer alignment coordinates of the multiple measurement mark points.

8. The method according to any one of claims 1 to 5, characterized in that The step of obtaining wafer alignment coordinates of a plurality of measurement mark points of a target wafer includes: Acquiring wafer alignment coordinates of alignment mark points used for wafer alignment in the target wafer, and performing wafer alignment on the target wafer based on the wafer alignment coordinates of the alignment mark points to obtain initial wafer alignment coordinates of the plurality of measurement mark points; The initial wafer alignment coordinates of each of the measurement mark points are input into a wafer alignment coordinate correction model, and the wafer alignment coordinates of each of the measurement mark points are output through the wafer alignment coordinate correction model.

9. The method according to claim 8, characterized in that The wafer alignment coordinate correction model is trained by the following method: Acquire a second training sample set, wherein the second training sample set includes sample target capture coordinates and sample wafer alignment coordinates of a plurality of sample measurement mark points included in a plurality of sample wafers, wherein one sample measurement mark point corresponds to one sample wafer alignment coordinate and one sample wafer alignment coordinate; The coordinate difference between the sample wafer alignment coordinates of each of the sample measurement mark points and the sample target capture coordinates is calculated, and the wafer alignment coordinate correction model is established based on the sample wafer alignment coordinates of each of the plurality of sample measurement mark points and the coordinate difference.

10. The method according to claim 9, characterized in that After obtaining the first target capture coordinates of each of the first measurement mark points based on the wafer alignment coordinates and the coordinate offsets of each of the first measurement mark points, the method further includes: Obtaining a wafer alignment coordinate error of each first measurement mark point based on the first target capture coordinate of each first measurement mark point and the wafer alignment coordinate of each first measurement mark point; The wafer alignment coordinates and the wafer alignment coordinate errors of each of the first measurement mark points are added to the second training sample set as correction training data of the wafer alignment coordinate correction model to perform correction training on the wafer alignment coordinate correction model.

11. The method according to any one of claims 1 to 5, characterized in that The target wafer includes a plurality of fields, the plurality of measurement marking points are a plurality of measurement marking points included in a target field in the plurality of fields, and the distribution state of the measurement marking points in each of the plurality of fields is the same; After the wafer measurement of the target wafer is achieved, the method further includes: Building an intra-field coordinate prediction model based on the wafer alignment coordinates and the first target capture coordinates of the plurality of first measurement mark points included in the target site, and the wafer alignment coordinates and the second target capture coordinates of the plurality of second measurement mark points; When the wafer alignment coordinates of multiple measurement mark points included in any one of the multiple fields except the target field are obtained, the wafer alignment coordinates of each measurement mark point included in any one of the multiple fields are input into the in-field coordinate prediction model, and the target capture coordinates of each measurement mark point in any one of the fields are output through the in-field coordinate prediction model to complete the measurement of each measurement mark point included in any one of the fields.

12. A wafer measurement device based on measurement mark points, characterized in that: include: An acquisition module, which acquires wafer alignment coordinates of multiple measurement mark points of a target wafer; a target capture module, performing target capture on a plurality of first measurement mark points among the plurality of measurement mark points to obtain a coordinate offset of each of the first measurement mark points, and obtaining a first target capture coordinate of each of the first measurement mark points based on the wafer alignment coordinates and the coordinate offset of each of the first measurement mark points; a prediction module, inputting the wafer alignment coordinates of a plurality of second measurement mark points among the plurality of measurement mark points excluding the plurality of first measurement mark points into a target capture coordinate prediction model, and outputting second target capture coordinates of each of the second measurement mark points through the target capture coordinate prediction model; A measurement module is used to measure the multiple first measurement mark points based on the first target capture coordinates of each of the first measurement mark points, and to measure the multiple second measurement mark points based on the second target capture coordinates of each of the second measurement mark points, so as to achieve wafer measurement of the target wafer.

13. A terminal device, characterized in that: include: image acquisition device, processor, and memory; The processor is connected to the memory, wherein the memory is used to store program code, and the image acquisition device and the processor are used to call the program code to execute the method according to any one of claims 1-11.

14. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is suitable for being loaded by a processor and executing the method according to any one of claims 1 to 11.

Images