Film thickness measurement model training method, film thickness measurement method, device, equipment, medium, product

By training the film thickness measurement model, the refractive index and interference image signal intensity curve of the film sample are used to solve the problem of peak identification and offset in the measurement of extreme film thickness in white light interference scanning technology, and high-precision film thickness measurement is achieved.

CN118570591BActive Publication Date: 2024-11-19JIANGSU JIANGLING SEMICON CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202411059937.6
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-08-02
Publication Date
2024-11-19
Estimated Expiration
2044-08-02

AI Technical Summary

Technical Problem

When measuring extremely thin films using white light interference scanning technology, the central peak identification of the two columns of interference curves is difficult and positional offset problems, resulting in inaccurate thickness measurement.

Method used

By training the film thickness measurement model, the central peak is determined and the film thickness prediction value is calculated by using the refractive index, reflectance and interference image signal intensity curves of multiple film samples, and the calibration value is combined to improve measurement accuracy.

Benefits of technology

Accurate measurement of extremely thin film thickness is achieved, reducing the difficulty of peak identification and offset problems, and improving measurement accuracy and accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118570591B_ABST
    Figure CN118570591B_ABST
Patent Text Reader

Abstract

The present application proposes a method, device, equipment, medium and product for measuring film thickness, the method comprising: obtaining the refractive index and reflectivity of the film to be measured, and obtaining the predicted film thickness value and calibration value of the film to be measured based on the scanning interferometer method; inputting the refractive index, reflectivity, predicted film thickness value and calibration value of the film to be measured into the film thickness measurement model to obtain the thickness value of the film to be measured. The present application also proposes a method for training a film thickness measurement model, the method comprising: providing a plurality of different film samples, obtaining the standard film thickness value, refractive index and reflectivity of each film sample; obtaining the predicted film thickness value and calibration value of each film sample based on the scanning interferometer method; using the refractive index, reflectivity, predicted film thickness value and calibration value of the film sample as the sample input value, and the standard film thickness value of the film sample as the sample output value, to train the film thickness measurement model. The above method can accurately measure the thickness of films, especially extremely thin films.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of thickness measurement, and in particular to a method, device, equipment, medium, product for measuring the thickness of a thin film, and a method for training a film thickness measurement model. Background Art

[0002] When using white light interference scanning technology to measure the thickness of a film, the collected interference curve is formed by the superposition of the first interference curve formed by the reflected light and reference light at the bottom interface of the film and the second interference curve formed by the reflected light and reference light at the top interface of the film, which is called the third interference curve. It is necessary to correctly identify the central peak of the first interference curve and the central peak of the second interference curve from the third interference curve; the distance between the two central peaks divided by the refractive index of the film is the thickness of the film. When the central peaks of the first interference curve and the second interference curve are far apart, generally greater than 3 times the central wavelength of white light (about 1.8 microns), the two waves are independent of each other, and the position of the film interface can be obtained using general interference scanning technology. When the distance between the two interfaces is close, the two waves interfere with each other, which will cause the problem of difficulty in identifying the two central peaks and the problem of the displacement of the central peak position. Summary of the invention

[0003] In order to solve the above problems and avoid or eliminate interference when measuring extremely thin films using white light interferometric scanning technology, the present application embodiment proposes a method for training a film thickness measurement model, including: providing a plurality of different thin film samples, obtaining a standard film thickness value, a refractive index and a reflectivity of each of the thin film samples; obtaining a predicted film thickness value and a calibration value of each of the thin film samples based on a scanning interferometer method; using the refractive index, reflectivity, predicted film thickness value and calibration value of the thin film sample as sample input values ​​and the standard film thickness value of the thin film sample as a sample output value to train the film thickness measurement model.

[0004] Optionally, obtaining the predicted film thickness value of each of the thin film samples based on the scanning interferometry method includes: collecting a set of interference images at different heights for each of the thin film samples, and obtaining a signal intensity curve of the interference image; determining that the peak with the largest signal intensity in the signal intensity curve is the first central peak; obtaining the second central peak based on the first film thickness estimate and refractive index of the thin film sample; calculating a first distance between the first central peak and the second central peak, and dividing the first distance by the refractive index to obtain the predicted film thickness value of each of the thin film samples.

[0005] Optionally, the first film thickness estimation value is obtained based on the film thickness standard value of the film sample, and the difference between the first film thickness estimation value and the corresponding film thickness standard value does not exceed ,in, is the central wavelength of the white light used in the scanning interferometry method, is the refractive index of the film sample.

[0006] Optionally, obtaining the second central peak based on the first film thickness estimate and refractive index of the thin film sample includes: calculating the second distance from all peaks in the signal intensity curve to the first central peak; calculating the deviation between the result of dividing the second distance by the refractive index and the first film thickness estimate; and determining the peak corresponding to the smallest deviation as the second central peak.

[0007] Optionally, the calibration value of the film sample includes a third distance between the second central peak and a left adjacent peak and / or a fourth distance between the second central peak and a right adjacent peak.

[0008] Optionally, the film thickness measurement model is a decision regression tree model.

[0009] Optionally, the multiple different thin film samples are a group of film thickness standard sheets, the film thickness standard values ​​of the film thickness standard sheets are in the range of 0.1 microns to 1.5 microns, the refractive index is in the range of 1.0 to 2.0, and the reflectivity ratio of the top and bottom of the film is in the range of 0.1 to 1.0.

[0010] The present application also proposes a method for measuring film thickness, including: obtaining the refractive index and reflectivity of the film to be measured, and obtaining the predicted film thickness value and calibration value of the film to be measured based on the scanning interferometry method; inputting the refractive index, reflectivity, predicted film thickness value and calibration value of the film to be measured into a film thickness measurement model to obtain the thickness value of the film to be measured, wherein the film thickness measurement model is trained based on the aforementioned training method.

[0011] Optionally, obtaining the predicted film thickness value and calibration value of the film to be measured based on the scanning interferometry method includes: collecting a set of interference images at different heights for the film to be measured, and obtaining a signal intensity curve of the interference image; obtaining the predicted film thickness value and calibration value of the film to be measured based on the signal intensity curve, the second film thickness estimation value and the refractive index of the film to be measured.

[0012] Optionally, the measuring method comprises: obtaining the second film thickness estimation value based on the possible range of the actual film thickness of the film to be measured, and the difference between the second film thickness estimation value and the optional value in the possible range of the actual film thickness is not more than ,in, is the central wavelength of the white light used in the scanning interferometry method, is the refractive index of the film to be tested.

[0013] The embodiment of the present application also proposes a device for measuring the thickness of a thin film, comprising: a parameter acquisition unit, used to acquire the refractive index and reflectivity of the thin film to be measured, and to acquire a predicted value and a calibration value of the film thickness of the thin film to be measured based on a scanning interferometer method; and a film thickness calculation unit, used to input the refractive index, reflectivity, predicted value and calibration value of the film thickness of the thin film to be measured into a film thickness measurement model to obtain the thickness value of the thin film to be measured, wherein the film thickness measurement model is trained based on the aforementioned training method.

[0014] The embodiment of the present application also proposes an electronic device, which includes a memory storing computer-executable instructions and a processor; when the instructions are executed by the processor, the device implements the above-mentioned method.

[0015] The embodiment of the present application further proposes a computer-readable medium, which stores one or more programs. The one or more programs can be executed by one or more processors to implement the aforementioned method.

[0016] The embodiment of the present application further proposes a computer program product, including a computer program, and the computer program implements the aforementioned method when executed by a processor.

[0017] The training method of the film thickness measurement model proposed in the present application is combined with the scanning interferometry method, and the refractive index, reflectivity, predicted film thickness value and calibration value of the film sample with the standard value of the film thickness are introduced to train a film thickness measurement model with high measurement accuracy, especially solving the problem of difficulty in identifying the peak when the extremely thin film uses the scanning interferometry method. When measuring the thickness of the film to be measured, similar to the training method of the film thickness measurement model, it is only necessary to combine the scanning interferometry method and input the parameters of the film to be measured, such as the refractive index, reflectivity, predicted film thickness value and calibration value of the film to be measured, to obtain the thickness of each point of the film to be measured, and then form a morphology map of the film to be measured, so as to obtain a more accurate thickness value. In addition, when the present application obtains the predicted film thickness value, the film thickness estimation value used also has a larger range, so that the accurate actual thickness value can still be obtained when the film thickness estimation value deviates greatly from the actual thickness value. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a schematic diagram of interference curves when thicker films are measured using scanning interferometry;

[0019] Figure 2 It is a schematic diagram of interference curves when measuring thin films using scanning interferometry;

[0020] Figure 3 is a flow chart of a training method of a film thickness measurement model using an embodiment of the present application;

[0021] Figure 4 is a further flow chart of a training method using a film thickness measurement model according to an embodiment of the present application;

[0022] Figure 5 is a graph using a film thickness prediction value and a film thickness standard value according to an embodiment of the present application;

[0023] Figure 6 is a graph of mean absolute error versus film thickness using an embodiment of the present application;

[0024] Figure 7 is a graph of mean absolute error and refractive index using an embodiment of the present application;

[0025] Figure 8 is a graph of the mean absolute error versus the ratio of the reflectivity of the top of the film and the bottom of the film using an embodiment of the present application;

[0026] Fig. 9 is a flow chart of a method for measuring the thickness of a thin film according to an embodiment of the present application;

[0027] Fig.10 is a schematic diagram of a device for measuring the thickness of a thin film according to an embodiment of the present application;

[0028] Fig.11 is a schematic diagram of using an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0029] The thickness of the film can be measured using white light scanning interferometry. The main steps include: collecting a set of interference images of the film at different heights by scanning interferometry, and obtaining a signal intensity curve for each pixel on the interference image. It can be understood by those skilled in the art that the signal intensity curve is a composite of the first interference curve of the bottom interface of the film and the second interference curve of the top interface of the film, which is called the third interference curve; then, the first central peak of the first interference curve and the second central peak of the second interference curve are determined from the obtained signal intensity curve (third interference curve); finally, the distance between the first central peak and the second central peak is divided by the refractive index of the film to obtain the thickness value of the film. For example, refer to Figure 1 For a film with a large thickness, due to its large film thickness, the first central wave peak and the second central wave peak will not interfere with each other in its third interference curve (i.e., the interference curve actually measured), and the first central wave peak and the second central wave peak can be accurately obtained. Since the positions of the first central wave peak and the second central wave peak correspond to the positions of the upper and lower surfaces of the film, the distance between the two central wave peaks is divided by the refractive index of the film to obtain the true thickness of the film.

[0030] However, reference Figure 2 The inventors found that when measuring an extremely thin film, the distance between the upper and lower surfaces is very close, which causes the first central peak and the second central peak to be very close, so that the first central peak and the second central peak in the obtained third interference curve are too close and difficult to identify, and may also cause the peak position to shift (for example, the second central peak in the third interference curve is shifted to the left relative to the second central peak in the second interference curve), further making the measurement result inaccurate.

[0031] Furthermore, in the above method, the peak obtained by interferometric scanning of the bottom interface of the film is the first central peak, and the peak obtained by interferometric scanning of the top interface is the second central peak. The amplitude of the first central peak is greater than the amplitude of the second central peak. However, those skilled in the art can understand that this is due to Figure 1 The material of the thin film provided in the embodiment shown is caused (the reflectivity of the bottom interface of the transparent film used is greater). In other embodiments, the peak obtained by the interference scan of the top interface of the thin film may be the first central peak, and the peak obtained by the interference scan of the bottom interface may be the second central peak, that is, the reflectivity of the bottom interface of the thin film is less than the reflectivity of the top of the film. In the synthesized third interference curve, the two interference curves will affect each other, and the interference curve with a larger signal intensity will have a greater impact on the interference curve with a smaller signal intensity, causing the peak position of the interference curve with a smaller signal intensity to shift, and it is difficult to identify its peak position. When implementing the method proposed in the present application, it is only necessary to select the corresponding first central peak and second central peak according to the corresponding thin film material.

[0032] In an embodiment of the present application, a film thickness measurement method is proposed to accurately measure the thickness of an extremely thin film. The measurement method is to obtain the true thickness value of the film to be measured by inputting multiple parameter values ​​of the film to be measured into a trained film thickness measurement model, and some parameter values ​​of the film to be measured are obtained by scanning interferometry.

[0033] First, this embodiment provides an implementation method of a film thickness measurement model training method. Figure 3 The training method of the film thickness measurement model is described by the flowchart of FIG. 1 , which includes:

[0034] Step 301, provide a plurality of different thin film samples, and obtain the standard value of film thickness, refractive index and reflectivity of each thin film sample. It will be appreciated by those skilled in the art that the standard value of film thickness, refractive index and reflectivity of these thin film samples can be known values, and these values ​​are regarded as absolutely accurate values ​​in this method. In the embodiment of the present application, these thin film samples are a set of film thickness standard sheets (i.e., thin films with standard film thickness), and their film thickness standard values ​​are in the range of 0.1 micron to 1.5 micron, the refractive index is in the range of 1.0 to 2.0, and the ratio of the reflectivity of the top of the film to the bottom of the film is in the range of 0.1 to 1.0. The above ranges are empirical values ​​obtained in actual measurements, and other ranges of the above parameters can also be selected in other embodiments.

[0035] Step 302: Obtain the predicted film thickness value and calibration value of each thin film sample based on scanning interferometry.

[0036] Specifically, this embodiment also provides an implementation method for obtaining a predicted film thickness value of each thin film sample based on a scanning interferometer method. Figure 4 , which is a flow chart for obtaining the predicted value and calibration value of the film thickness, step 302, includes steps 401 to 404 for calculating the predicted value of the film thickness, and step 405 for calculating the calibration value. Specifically, it includes:

[0037] Step 401, collect a set of interference images at different heights for each film sample, and obtain a signal intensity curve of the interference image. It can be understood by those skilled in the art that the signal intensity curve of the interference image obtained here refers to the signal intensity curve of all pixel points on the interference image, and the signal intensity curve is a curve synthesized by two signal curves, that is, the third interference curve described above. In addition, these signal intensity curves can be smoothed to improve the accuracy of the measurement results.

[0038] Step 402: Determine the peak with the largest signal strength in the signal strength curve as the first central peak. Since the peak with the largest signal strength is less affected, the first central peak is selected as a reference to perform the following steps.

[0039] Step 403: obtaining a second central peak based on the first film thickness estimation value and the refractive index of the thin film sample.

[0040] The first estimated value of film thickness is an estimated value obtained by the measurement personnel according to the standard value of film thickness of the film sample, the production process of the film, and measurement experience.

[0041] Preferably, the difference between the first film thickness estimation value and the corresponding film thickness standard value does not exceed ,in, is the central wavelength of the white light used in scanning interferometry, is the refractive index of the thin film sample. In fact, this is a very wide range of differences, that is, the first film thickness estimation value has a large error tolerance.

[0042] One advantage of this embodiment is that even if there is a large deviation from the standard value of the film thickness, the parameter can still be used for training to obtain a film thickness measurement model with higher accuracy.

[0043] Furthermore, in step 403, after obtaining the first film thickness estimation value, the method further includes:

[0044] Step f1: respectively calculating the second distances from all the peaks in the signal strength curve to the first central peak;

[0045] Step f2: dividing all the second distances by the refractive index of the corresponding film sample and calculating the deviation from the first film thickness estimation value;

[0046] Step f3: Determine the peak corresponding to the smallest deviation as the second central peak.

[0047] Specifically, refer to the following formula to calculate the deviation:

[0048]

[0049] in, Er is the deviation value, P Represents all the peaks in the signal strength curve, p 1 is the first central peak, Es is the first estimated film thickness.

[0050] After the deviations corresponding to all the peaks are obtained, the peak corresponding to the minimum deviation is selected as the second central peak. Those skilled in the art can understand that the principle of this operation is to obtain the first central peak and the first film thickness estimation value, and then use the above Figure 1 The method in the reverse calculation obtains an estimated second central wave peak, that is, the estimated position of the other surface of the film (i.e., the second central wave peak) is calculated in reverse based on the estimated film thickness (i.e., the first film thickness estimation value) and the position of one surface of the film (i.e., the first central wave peak). It can be understood that in the embodiment of the present application, the second central wave peak obtained in this step is not the actual second central wave peak, and a calibration value still needs to be introduced to calibrate it, so as to calibrate the second central wave peak during the training process or application process of the film thickness measurement model, thereby obtaining a film thickness measurement model with higher accuracy, and being able to measure and obtain an accurate film thickness value.

[0051] Step 404, calculate the first distance between the first central wave peak and the second central wave peak, and divide the first distance by the refractive index to obtain the predicted film thickness value of each thin film sample. Figure 1The predicted film thickness value is obtained using the method principle described in .

[0052] In addition, step 405 is included to calculate the calibration value of the film sample, including: calculating the third distance between the second central peak and the left adjacent peak and / or the fourth distance between the second central peak and the right adjacent peak as the calibration value of the film sample.

[0053] Specifically, the calibration value is obtained from actual production experience. In this embodiment, the left and right adjacent peaks of the second central peak are used for calibration, which is a preferred calibration value, but it is only used as an example for determining the calibration value and is not limited thereto. In other embodiments, other parameters or methods may also be used for calibration. For example, according to the distance from the second central peak, more peaks are selected for weighted calibration; according to the distance from the second central peak and the signal strength of the first interference curve and the second interference curve, the corresponding peaks are selected for calibration; the corresponding fixed parameters may also be selected as calibration values ​​for calibration based on prior knowledge such as previous measurement experience, etc.

[0054] The predicted film thickness value and calibration value of each thin film sample can be obtained through steps 401 to 405. However, those skilled in the art will appreciate that the above steps are only examples, and obtaining the predicted film thickness value and calibration value through other implementations is also applicable.

[0055] Additionally, refer to Figure 5 As shown, Figure 5 The graph is a graph of the predicted film thickness value and the standard film thickness value according to the embodiment of the present application; wherein, the predicted film thickness value and the standard film thickness value obtained when the film sample with the ratio of the reflectivity of the top and bottom of the film being 1.0 and the refractive index being 1.0, 1.5, and 2.0 respectively are shown. It can be seen that the predicted film thickness value obtained by this method is already close to the standard film thickness value, so the thickness value of the film to be measured can be measured more accurately. In addition, it can be understood by those skilled in the art that although the standard film thickness value is 0.1 micron to 1.5 microns, the model will still produce a curve below 0.1 micron during the training process, but this part is not used to evaluate the model.

[0056] Then, returning to the training process, in step 303, the refractive index, reflectivity, film thickness prediction value and calibration value of the thin film sample are used as sample input values, and the film thickness standard value of the thin film sample is used as a sample output value to train the film thickness measurement model. In the embodiment of the present application, the film thickness measurement model is a decision regression tree model, but it can be understood by those skilled in the art that other suitable models can also be used to implement the present method.

[0057] Finally, reference Figures 6-8 The mean absolute error (MAE) (i.e., the deviation between the value output by the model and the standard value of the film thickness) curve is used to illustrate the accuracy of the film thickness measurement model. Figure 6 It is a curve chart of MAE and standard value of film thickness. It can be understood by those skilled in the art that although the standard value of film thickness is 0.1 micron to 1.5 micron, the model will still produce a curve below 0.1 micron during the training process, but this part is not used to evaluate the model. It can be seen that as the thickness of the film increases, the MAE decreases as a whole and quickly decreases to close to 0. Figure 7 It is a graph of MAE and the refractive index of the thin film sample. It can be seen that MAE decreases rapidly with the increase of the refractive index. The higher the refractive index, the more accurate the model prediction value. Figure 8 It is a curve graph of MAE and the ratio of the reflectivity of the top and bottom of the thin film sample. It can be seen that MAE decreases rapidly with the increase of the ratio of the reflectivity of the top and bottom of the film. The closer the reflectivity of the top and bottom of the film is, the more accurate the model prediction value is.

[0058] The above steps are the training process of the film thickness measurement model used in the film thickness measurement method in the embodiment of the present application. Fig. 9 , Fig. 9 The flowchart of the method for measuring the film thickness provided in this embodiment is shown. Specifically, the measuring method includes:

[0059] In step 901, the refractive index and reflectivity of the film to be measured are obtained, and the predicted value and calibration value of the film thickness of the film to be measured are obtained based on the scanning interferometry method.

[0060] It will be understood by those skilled in the art that the refractive index and reflectivity are intrinsic properties of the film, which may be known or simply measured by professional equipment, and the specific implementation method of obtaining the predicted measurement value and calibration value of the film thickness of the film to be measured based on the scanning interferometry method may be similar to the aforementioned method of obtaining the predicted measurement value and calibration value of the film thickness of the thin film sample based on the scanning interferometry method, which will not be repeated here.

[0061] It should be noted that, since there is no standard value for the thickness of the film to be measured, the second estimated film thickness value used when obtaining the predicted film thickness value and calibration value of the film to be measured is obtained based on the possible range of the actual film thickness of the film to be measured. The possible range of the actual film thickness of the film to be measured can be estimated by the measurement personnel based on the design requirements of the production process in which the film to be measured is located, the general thickness range of such films caused by relevant process parameters, and other prior knowledge. For example, the possible range of the actual film thickness of the film to be measured can be the thickness range of the film to be measured that can be estimated based on the prior knowledge of the product design requirements, the specific process steps that have been experienced, the relevant process parameters, and other influencing factors after a certain processing process that increases or decreases the thickness of the film to be measured, such as deposition, etching, oxidation, or chemical mechanical polishing in the integrated circuit production process.

[0062] Further, based on prior knowledge, the thickness value that is most likely to be close to the actual thickness is selected from the possible range of the actual film thickness as the second estimated film thickness value of the film to be measured. Similarly, the difference between the second estimated film thickness value and the optional value in the possible range of the actual film thickness is no more than ,in, The refractive index of the film to be measured also has a large error tolerance, which can improve the accuracy of the measurement.

[0063] In step 902, the refractive index, reflectivity, film thickness prediction value and calibration value of the film to be measured are input into the film thickness measurement model to obtain the thickness value of the film to be measured, wherein the film thickness measurement model is obtained by training based on the above training method. It can be understood by those skilled in the art that since the signal intensity curve is the signal intensity curve of each pixel on the interference image obtained by the scanning interferometer method, the operations based on the signal intensity curve in the above process are all operations performed on the pixel points, and these operations can be performed on all the pixel points at the same time through the film thickness measurement model to obtain the thickness value of each location on the film to be measured, and then the morphology of the film to be measured can be constructed through all the thickness values, so as to obtain the true thickness of the film to be measured as a whole. Since a large number of pixels are used to measure the thickness, the accuracy of the measurement results is greatly improved. It can be understood that since the calibration value is introduced and the offset second central peak is calibrated in the machine learning model (i.e., the film thickness measurement model), the measurement method has a good effect on the thickness measurement of extremely thin films, but it can also be applied to films of ordinary thickness, and it also has a good effect.

[0064] Furthermore, in the detection / measurement application scenarios of the integrated circuit industry, the above method can be used to measure the thickness of transparent or translucent films on the surface of the wafer in various process steps, including semiconductor films formed by deposition, oxidation, etc., and adhesive films formed by processes such as coating.

[0065] refer to Fig.10 The present application also proposes a film thickness measuring device 1000, the measuring device 1000 comprising:

[0066] The parameter acquisition unit 1001 is used to acquire the refractive index and reflectivity of the film to be measured, and acquire the predicted value and calibration value of the film thickness of the film to be measured based on the scanning interferometry method;

[0067] The film thickness calculation unit 1002 is used to input the refractive index, reflectivity, film thickness prediction value and calibration value of the film to be measured into the film thickness measurement model to obtain the thickness value of the film to be measured, wherein the film thickness measurement model is trained based on the above-mentioned training method.

[0068] It can be understood that the measuring device 1000 can be run on various computers and servers, and can use the film thickness measurement method corresponding to the present application to measure the film thickness of the film.

[0069] Reference now Fig.11 , which is a block diagram of an electronic device 1100 according to an embodiment of the present application. The electronic device 1100 may include one or more processors 1102, a system control logic 1108 connected to at least one of the processors 1102, a system memory 1104 connected to the system control logic 1108, a non-volatile memory (NVM) 1106 connected to the system control logic 1108, and a network interface 1110 connected to the system control logic 1108.

[0070] The processor 1102 may include one or more single-core or multi-core processors. The processor 1102 may include any combination of a general-purpose processor and a dedicated processor (e.g., a graphics processor, an application processor, a baseband processor, etc.). In the embodiments of this document, the processor 1102 may be configured to execute one or more embodiments of the various embodiments proposed in this application.

[0071] In some embodiments, system control logic 1108 may include any suitable interface controller to provide any suitable interface to at least one of processors 1102 and / or any suitable device or component in communication with system control logic 1108 .

[0072] In some embodiments, the system control logic 1108 may include one or more memory controllers to provide an interface to the system memory 1104. The system memory 1104 may be used to load and store data and / or instructions. In some embodiments, the system memory 1104 of the electronic device 1100 may include any suitable volatile memory, such as a suitable dynamic random access memory (DRAM).

[0073] The non-volatile memory 1106 may include one or more tangible, non-transitory computer-readable media for storing data and / or instructions. In some embodiments, the non-volatile memory 1106 may include any suitable non-volatile memory such as flash memory and / or any suitable non-volatile storage device, such as at least one of a HDD (Hard Disk Drive), a CD (Compact Disc) drive, and a DVD (Digital Versatile Disc) drive.

[0074] The non-volatile memory 1106 may include a portion of storage resources installed on a device of the electronic device 1100, or it may be accessible by the device but not necessarily a portion of the device. For example, the non-volatile memory 1106 may be accessed over a network via the network interface 1110.

[0075] In particular, the system memory 1104 and the non-volatile memory 1106 may include: a temporary copy and a permanent copy of the instruction 1120, respectively. The instruction 1120 may include: an instruction that causes the electronic device 1100 to implement the method provided by the present application when executed by at least one of the processors 1102. In some embodiments, the instruction 1120, hardware, firmware and / or software components thereof may be additionally / alternatively placed in the system control logic 1108, the network interface 1110 and / or the processor 1102.

[0076] In some embodiments, the network interface 1110 may be integrated with other components of the electronic device 1100. For example, the network interface 1110 may be integrated with at least one of the processor 1102, the system memory 1104, the non-volatile memory 1106, and a firmware device (not shown) having instructions, and when at least one of the processors 1102 executes the instructions, the electronic device 1100 implements one or more of the various embodiments described herein. The network interface 1110 may further include any suitable hardware and / or firmware to provide a multiple-input multiple-output radio interface.

[0077] In one embodiment, at least one of the processors 1102 may be packaged together with logic for one or more controllers of the system control logic 1108 to form a system in package (SiP). In one embodiment, at least one of the processors 1102 may be integrated on the same die with logic for one or more controllers of the system control logic 1108 to form a system on chip (SoC).

[0078] The electronic device 1100 may further include an input / output (I / O) device 1112. The input / output (I / O) device 1112 may include a user interface to enable a user to interact with the device 1100; the design of a peripheral component interface enables peripheral components to interact with the electronic device 1100.

[0079] In some embodiments, the user interface may include, but is not limited to, a display (e.g., an LCD display, a touch screen display, etc.), a speaker, a microphone, one or more cameras (e.g., a still image camera and / or a video camera), a flashlight (e.g., an LED flash), and a keyboard.

[0080] In some embodiments, the peripheral component interface may include, but is not limited to, a non-volatile memory port, an audio jack, and a power interface.

[0081] It will be understood by those skilled in the art that the structure illustrated in the embodiment of the present invention does not constitute a specific limitation on the electronic device 1100. In other embodiments of the present application, the electronic device 1100 may include more or fewer components than shown in the figure, or combine some components, or split some components, or arrange the components differently. The components shown in the figure may be implemented in hardware, software, or a combination of software and hardware.

[0082] Program code can be applied to input instructions to perform each function described herein and generate output information. Output information can be applied to one or more output devices in a known manner. For purposes of this application, processing system includes any system with a processor such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC) or a microprocessor.

[0083] Program code can be implemented with high-level programming language or object-oriented programming language to communicate with the processing system. When necessary, program code can also be implemented with assembly language or machine language. In fact, the mechanism described herein is not limited to the scope of any specific programming language. In either case, the language can be a compiled language or an interpreted language.

[0084] One or more aspects of at least one embodiment may be implemented by representative instructions stored on a computer-readable storage medium, which represent various logic in a processor, and when the instructions are read by a machine, cause the machine to fabricate logic for performing the techniques described herein. These representations, known as "IP cores," may be stored on a tangible computer-readable storage medium and supplied to multiple customers or manufacturing facilities to load into a manufacturing machine that actually manufactures the logic or processor.

[0085] An embodiment of the present application discloses a computer-readable medium storing one or more programs executable by one or more processors to implement the method of the present application.

[0086] An embodiment of the present application discloses a computer program product, including a computer program, which implements the method of the present application when executed by a processor.

[0087] The above specific embodiments illustrate the implementation of the present application, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Although the description of the present application will be introduced in conjunction with the preferred embodiment, this does not mean that the features of this invention are limited to the implementation. In addition, in order to avoid confusion or blurring the focus of the present application, some specific details will be omitted in the description. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.

[0088] Furthermore, various operations will be described as multiple discrete operations in a manner that is most helpful for understanding the illustrative embodiments; however, the order of description should not be construed as implying that these operations are necessarily order dependent. In particular, these operations do not need to be performed in the order presented.

[0089] Unless the context dictates otherwise, the terms "comprising," "having," and "including" are synonymous. The phrase "A / B" means "A or B." The phrase "A and / or B" means "(A and B) or (A or B)."

[0090] As used herein, the term "module" or "unit" may refer to, be or include: an application specific integrated circuit (ASIC), an electronic circuit, a (shared, dedicated or group) processor and / or memory that executes one or more software or firmware programs, a combinational logic circuit and / or other suitable components that provide the described functionality.

[0091] In the accompanying drawings, some structural or method features are shown in a specific arrangement and / or order. However, it should be understood that such specific arrangement and / or ordering may not be required. In some embodiments, these features may be arranged in a manner and / or order different from that shown in the illustrative drawings. In addition, the inclusion of structural or method features in a specific figure does not mean that such features are required in all embodiments, and in some embodiments, these features may not be included or may be combined with other features.

[0092] It should be understood that although the terms "first", "second", etc. may be used here to describe various units or data, these units or data should not be limited by these terms. These terms are used only to distinguish one feature from another. For example, without departing from the scope of the exemplary embodiment, a first feature may be referred to as a second feature, and similarly, a second feature may be referred to as a first feature.

[0093] It should be noted that in this specification, similar reference numerals and letters denote similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.

[0094] While the present invention has been shown and described with reference to certain preferred embodiments thereof, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention.

Claims

1. A method for training a film thickness measurement model, characterized in that: include: Providing a plurality of different thin film samples, and obtaining a standard value of film thickness, refractive index and reflectivity of each of the thin film samples; Obtaining a film thickness prediction value and a calibration value of each of the thin film samples based on a scanning interferometer method, including: For each of the thin film samples, a set of interference images at different heights are collected, and a signal intensity curve of the interference image is obtained; Determine the peak with the largest signal strength in the signal strength curve as the first central peak; Obtaining a second central wave peak based on a first film thickness estimation value and a refractive index of the thin film sample, wherein the calibration value of the thin film sample is used to calibrate the second central wave peak; Calculating a first distance between the first central wave peak and the second central wave peak, and dividing the first distance by the refractive index to obtain the predicted film thickness value of each of the thin film samples; The film thickness measurement model is trained by taking the refractive index, reflectivity, predicted film thickness value and calibration value of the film sample as sample input values ​​and the standard film thickness value of the film sample as sample output values.

2. The training method according to claim 1, characterized in that: The first film thickness estimation value is obtained based on the film thickness standard value of the film sample, and the difference between the first film thickness estimation value and the corresponding film thickness standard value does not exceed ,in, is the central wavelength of the white light used in the scanning interferometry method, is the refractive index of the film sample.

3. The training method according to claim 1, characterized in that: Obtaining a second central peak based on the first film thickness estimation value and the refractive index of the thin film sample comprises: Calculating a second distance from all peaks in the signal strength curve to the first central peak; Calculate the deviation between the result of dividing the second distance by the refractive index and the first estimated film thickness; The peak corresponding to the smallest said deviation is determined as the second central peak.

4. The training method according to claim 3, characterized in that: The calibration value of the film sample includes a third distance between the second central peak and a left adjacent peak and / or a fourth distance between the second central peak and a right adjacent peak.

5. The training method according to claim 1, characterized in that: The film thickness measurement model is a decision regression tree model.

6. The training method according to claim 1, characterized in that: The multiple different thin film samples form a group of film thickness standard sheets, the film thickness standard values ​​of the film thickness standard sheets are in the range of 0.1 microns to 1.5 microns, the refractive index is in the range of 1.0 to 2.0, and the reflectivity ratio between the top and bottom of the film is in the range of 0.1 to 1.

0.

7. A method for measuring film thickness, characterized in that: include: Obtaining the refractive index and reflectivity of the film to be measured, and obtaining the predicted film thickness value and calibration value of the film to be measured based on the scanning interferometry method, including: Collecting a set of interference images at different heights for the film to be tested, and obtaining a signal intensity curve of the interference image; Determine the peak with the largest signal strength in the signal strength curve as the first central peak; Obtaining a second central wave peak based on a second film thickness estimation value and a refractive index of the film to be measured, wherein the calibration value of the film to be measured is used to calibrate the second central wave peak; Acquire a predicted film thickness value and a calibration value of the film to be measured based on the signal intensity curve, a second film thickness estimation value and a refractive index of the film to be measured; The refractive index, reflectivity, predicted film thickness value and calibration value of the film to be measured are input into a film thickness measurement model to obtain the thickness value of the film to be measured, wherein the film thickness measurement model is trained based on the training method described in any one of claims 1-6.

8. The measuring method according to claim 7, characterized in that: include: The second film thickness estimation value is obtained based on the possible range of the actual film thickness of the film to be measured, and the difference between the second film thickness estimation value and the optional value in the possible range of the actual film thickness is not more than ,in, is the central wavelength of the white light used in the scanning interferometry method, is the refractive index of the film to be tested.

9. A device for measuring film thickness, characterized in that: include: A parameter acquisition unit is used to acquire the refractive index and reflectivity of the film to be measured, and to acquire the predicted film thickness value and calibration value of the film to be measured based on the scanning interferometry method, including: Collecting a set of interference images at different heights for the film to be tested, and obtaining a signal intensity curve of the interference image; Determine the peak with the largest signal strength in the signal strength curve as the first central peak; Obtaining a second central wave peak based on a second film thickness estimation value and a refractive index of the film to be measured, wherein the calibration value of the film to be measured is used to calibrate the second central wave peak; Acquire a predicted film thickness value and a calibration value of the film to be measured based on the signal intensity curve, a second film thickness estimation value and a refractive index of the film to be measured; A film thickness calculation unit is used to input the refractive index, reflectivity, film thickness prediction value and calibration value of the film to be measured into a film thickness measurement model to obtain the thickness value of the film to be measured, wherein the film thickness measurement model is trained based on the training method described in any one of claims 1 to 6.

10. An electronic device, characterized in that: The device comprises a memory storing computer executable instructions and a processor; when the instructions are executed by the processor, the device implements the method according to any one of claims 1 to 8.

11. A computer readable medium, characterized in that The computer-readable medium stores one or more programs, and the one or more programs can be executed by one or more processors to implement the method according to any one of claims 1 to 8.

12. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.