Through-hole contact resistance prediction method, electronic device and readable storage medium

Abstract

The present invention provides a method, electronic device, and readable storage medium for predicting through-hole contact resistance. The method comprises: constructing a training sample set based on historical through-hole contact resistance measurement data and historical back-end process online measurement data obtained from multiple wafers; using the training sample set to train a deep neural network model including a feature enhancement layer to obtain a corresponding through-hole contact resistance prediction model. The feature enhancement layer is used to learn the interactive features between different back-end process parameters and the cross-layer correlation between back-end process parameters and through-hole contact resistance based on a multi-head attention mechanism; and inputting the current back-end process online measurement data of the wafer to be tested into the through-hole contact resistance prediction model to obtain through-hole contact resistance prediction data for the wafer to be tested. By combining deep learning with an attention mechanism, the present invention can achieve real-time and accurate prediction of through-hole contact resistance.

Description

Technical Field

[0001] The present invention relates to the technical field of semiconductor processing and manufacturing, and in particular to a through-hole contact resistance prediction method, electronic equipment and a readable storage medium. Background Art

[0002] The through-hole (VIA) contact resistance (Rc) directly affects the electrical performance of the device. Testing and monitoring the through-hole contact resistance is one of the important means to adjust chip performance and reflect the device process.

[0003] However, through-hole contact resistance exhibits a significantly low correlation with BEOL (back-end-of-the-line) inline measurement data, and lacks an explainable sensitivity relationship. This not only makes it difficult to effectively predict through-hole contact resistance, but also makes it impossible to establish an effective process adjustment strategy when abnormal fluctuations in through-hole contact resistance occur. Summary of the Invention

[0004] The purpose of the present invention is to provide a through-hole contact resistance prediction method, electronic device and readable storage medium. By combining deep learning with an attention mechanism, it is possible to not only learn the interaction characteristics between different back-end process parameters but also learn the correlation between cross-layer processes and through-hole contact resistance, thereby achieving real-time and accurate prediction of through-hole contact resistance.

[0005] To achieve the above-mentioned objectives, the present invention provides a through-hole contact resistance prediction method, comprising: obtaining historical through-hole contact resistance measurement data and historical back-end process online measurement data of multiple wafers; constructing a training sample set based on the historical through-hole contact resistance measurement data and historical back-end process online measurement data of the multiple wafers, wherein each training sample in the training sample set includes back-end process online measurement data and corresponding through-hole contact resistance measurement data, and the through-hole contact resistance measurement data is the label of the training sample; using the training sample set to train a pre-constructed deep neural network model to obtain a corresponding through-hole contact resistance prediction model, wherein the deep neural network model includes a feature enhancement layer, and the feature enhancement layer is used to learn the interaction features between different back-end process parameters based on a multi-head attention mechanism and learn the cross-layer correlation between the back-end process parameters and the through-hole contact resistance; inputting the current back-end process online measurement data of the wafer to be inspected into the through-hole contact resistance prediction model to obtain the through-hole contact resistance prediction data of the wafer to be inspected.

[0006] Optionally, constructing a training sample set based on the historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers includes: preprocessing the historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers; and constructing the training sample set based on the preprocessed historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers.

[0007] Optionally, the preprocessing of the historical through-hole contact resistance measurement data of the multiple wafers and the historical back-end process online measurement data includes: sequentially performing data cleaning, normalization and labeling on the historical through-hole contact resistance measurement data of the multiple wafers and the historical back-end process online measurement data.

[0008] Optionally, the back-end process parameters include through-hole depth, through-hole diameter, through-hole bottom metal layer thickness, through-hole bottom metal layer width, through-hole top metal layer thickness and through-hole top metal layer width.

[0009] Optionally, the through-hole contact resistance prediction method provided by the present invention further includes: obtaining influence weight information of each back-end process parameter on the through-hole contact resistance based on attention weight information of the through-hole contact resistance prediction model.

[0010] Optionally, the through-hole contact resistance prediction method provided by the present invention also includes: when the error between the through-hole contact resistance prediction data of the wafer to be tested and the through-hole contact resistance target data of the wafer to be tested exceeds a preset range, a process tuning strategy is formulated based on the back-end process parameters with the greatest impact on the through-hole contact resistance.

[0011] Optionally, the through-hole contact resistance prediction method provided by the present invention also includes: obtaining a cross-layer correlation analysis heat map between the back-end process parameters and the through-hole contact resistance based on the attention weight information of the through-hole contact resistance prediction model; and analyzing the cross-layer causality between the through-hole contact resistance and the back-end process parameters based on the cross-layer correlation analysis heat map.

[0012] Optionally, the through-hole contact resistance prediction method provided by the present invention also includes: updating the through-hole contact resistance prediction model when the absolute value of the average error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance measurement data of the wafer to be inspected is greater than a preset threshold.

[0013] To achieve the above object, the present invention further provides an electronic device, comprising a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the through-hole contact resistance prediction method described above is implemented.

[0014] To achieve the above-mentioned object, the present invention further provides a readable storage medium, wherein the readable storage medium stores a computer program, and when the computer program is executed by a processor, the through-hole contact resistance prediction method described above is implemented.

[0015] Compared with the prior art, the through-hole contact resistance prediction method, electronic device and readable storage medium provided by the present invention have the following unexpected technical effects: the through-hole contact resistance prediction method provided by the present invention first obtains the historical through-hole contact resistance measurement data and historical back-end process online measurement data of multiple wafers, and then constructs a training sample set based on the historical through-hole contact resistance measurement data and historical back-end process online measurement data of the multiple wafers, and then uses the training sample set to train the pre-constructed deep neural network model to obtain a corresponding through-hole contact resistance prediction model, wherein the deep neural network model includes a feature enhancement layer, and the feature enhancement layer is used to learn the interaction features between different back-end process parameters based on a multi-head attention mechanism and learn the cross-layer correlation between the back-end process parameters and the through-hole contact resistance. Finally, the current back-end process online measurement data of the wafer to be inspected is input into the through-hole contact resistance prediction model to obtain the through-hole contact resistance prediction data of the wafer to be inspected. Therefore, the present invention, based on deep learning and combined with the attention mechanism, can not only learn the interaction characteristics between different back-end process parameters, but also learn the correlation between cross-layer processes and through-hole contact resistance, thereby realizing real-time and accurate prediction of through-hole contact resistance, effectively saving testing time and cost, and also laying a certain foundation for subsequent process tuning.

[0016] Since the electronic device and readable storage medium provided by the present invention belong to the same inventive concept as the through-hole contact resistance prediction method provided by the present invention, the electronic device and readable storage medium provided by the present invention at least have all the technical effects of the through-hole contact resistance prediction method provided by the present invention. Therefore, the relevant content about the technical effects of the electronic device and readable storage medium provided by the present invention can refer to the relevant description of the technical effects of the through-hole contact resistance prediction method provided by the present invention above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flowchart of a through-hole contact resistance prediction method provided in one embodiment of the present invention.

[0018] Figure 2 A structural block diagram of a deep neural network model provided by one embodiment of the present invention.

[0019] Figure 3 A weighted diagram showing the impact of various back-end process parameters on through-hole contact resistance provided in one embodiment of the present invention.

[0020] Figure 4 A heat map showing the cross-layer correlation analysis between back-end-of-the-line process parameters and through-hole contact resistance according to one embodiment of the present invention.

[0021] Figure 5 The figure is a comparison diagram of the through-hole contact resistance value predicted by the through-hole contact resistance prediction method provided by the present invention and the through-hole contact resistance value actually measured.

[0022] Figure 6 A schematic block diagram of an electronic device according to an embodiment of the present invention.

[0023] The reference numerals are as follows: input layer 110 ; feature enhancement layer 120 ; hidden layer 130 ; output layer 140 ; processor 210 ; communication interface 220 ; memory 230 ; and communication bus 240 . DETAILED DESCRIPTION

[0024] The following is a further detailed description of the through-hole contact resistance prediction method, electronic device, and readable storage medium proposed in the present invention in conjunction with the accompanying drawings and specific embodiments. The advantages and features of the present invention will become clearer based on the following description. It should be noted that the structures, proportions, sizes, etc. illustrated in the drawings of this specification are only used to match the contents disclosed in the specification for people familiar with this technology to understand and read, and are not intended to limit the conditions for the implementation of the present invention. Any structural modification, change in proportional relationship, or adjustment of size, as long as the effects and purposes that can be achieved by the present invention are the same or similar, should still fall within the scope of the technical content disclosed by the present invention.

[0025] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprise", "include" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device comprising a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the statement "comprises a ..." does not exclude the presence of other identical elements in the process, method, article or device comprising the element. The singular forms "a", "an" and "the" include plural objects, the term "or" is generally used in a sense including "and / or", the term "several" is generally used in a sense including "at least one", and the term "at least two" is generally used in a sense including "two or more". In addition, the terms "first", "second" and "third" are used for descriptive purposes only and cannot be understood as indicating or suggesting relative importance or implicitly indicating the number of the indicated technical features.

[0026] In addition, in the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples without contradiction.

[0027] The core idea of the present invention is to provide a through-hole contact resistance prediction method, electronic device and readable storage medium. By combining deep learning with attention mechanism, the correlation between cross-layer process and through-hole contact resistance can be learned, thereby realizing real-time prediction of through-hole contact resistance.

[0028] It should be noted that the through-hole contact resistance prediction method provided by the present invention can be applied to the electronic device provided by the present invention, wherein the electronic device can be a personal computer, a mobile terminal, etc., and the mobile terminal can be a mobile phone, a tablet computer, and other hardware devices with various operating systems.

[0029] To realize the above idea, the present invention provides a through-hole contact resistance prediction method, please refer to Figure 1 , which is a flow chart of a through-hole contact resistance prediction method provided by one embodiment of the present invention. Figure 1 As shown, the through-hole contact resistance prediction method provided by the present invention includes the following steps: step S100, obtaining historical through-hole contact resistance measurement data and historical back-end process online measurement data of multiple wafers; step S200, constructing a training sample set based on the historical through-hole contact resistance measurement data and historical back-end process online measurement data of the multiple wafers, wherein each training sample in the training sample set includes back-end process online measurement data and corresponding through-hole contact resistance measurement data, and the through-hole contact resistance measurement data is the label of the training sample; step S300, using the training sample set to train a pre-constructed deep neural network model to obtain a corresponding through-hole contact resistance prediction model; step S400, inputting the current back-end process online measurement data of the wafer to be detected into the through-hole contact resistance prediction model to obtain the through-hole contact resistance prediction data of the wafer to be detected.

[0030] Please continue to refer to Figure 2 , which is a structural block diagram of a deep neural network model provided by one embodiment of the present invention. Figure 2 As shown, the deep neural network model includes a feature enhancement layer 120, which is used to learn the interaction features between different back-end process parameters and the cross-layer correlation between the back-end process parameters and the through-hole contact resistance based on a multi-head attention mechanism. Therefore, the present invention, based on deep learning and combined with the attention mechanism, can not only learn the interaction features between different back-end process parameters but also learn the correlation between the cross-layer process and the through-hole contact resistance, thereby achieving real-time and accurate prediction of the through-hole contact resistance, effectively saving testing time and cost, and also laying a certain foundation for subsequent process tuning.

[0031] Please continue to refer to Figure 2 ,like Figure 2As shown, the deep neural network model also includes an input layer 110, a hidden layer 130, and an output layer 140. The feature enhancement layer 120 is located between the input layer 110 and the hidden layer 130. The input layer 110 is used to receive input data (online measurement data of the back-end process), the hidden layer 130 is used to use a sigmoid activation function to realize neuron transmission of parameters, and the output layer 140 is used to output through-hole contact resistance prediction data using a linear activation function. It should be noted that, as can be understood by those skilled in the art, the present invention does not limit the number of hidden layers 130 included in the deep neural network model and the number of neurons included in the hidden layer 130. The number of hidden layers 130 and the neurons can be adjusted according to the amount and complexity of the data.

[0032] Furthermore, the back-end process online measurement data in each training sample includes online measurement data of multiple back-end process parameters corresponding to each layer of through holes, and the through hole contact resistance measurement data in each training sample includes the contact resistance corresponding to each layer of through holes.

[0033] Specifically, the online measurement data of N back-end process parameters corresponding to each of the M layers of through-holes can be converted into a data matrix X after preprocessing:

[0034]

[0035] Among them, X 11 、……、X 1N Indicates the online measurement data of N back-end process parameters corresponding to the first layer through hole; X M1 、……、X MN Indicates the online measurement data of N back-end process parameters corresponding to the M-th layer through-hole.

[0036] Taking the two-head attention mechanism as an example, the dimension of each head is N / 2, focusing on the back-end process parameters of the current layer and the cross-layer back-end process parameters respectively.

[0037] The weight matrix W of the query vector of the first head 1-Q , the weight matrix W of the key vector 1-K , the weight matrix W of the value vector 1-V As shown below:

[0038]

[0039]

[0040]

[0041] Then the query vector of the first head Q1=X×W 1-Q, the key vector of the first head K1=X×W 1-K , the value vector of the first head V1=X×W 1-V .

[0042] The calculation formula of the first head's attention head1 is as follows:

[0043]

[0044] Similarly, the attention of the second head, head2, can be calculated based on the following formula:

[0045]

[0046] Among them, the query vector of the second head Q2=X×W 2-Q , W 2-Q is the weight matrix of the query vector of the second head; the key vector of the second head K2=X×W 2-K , W 2-K is the weight matrix of the key vector of the second head; the value vector of the second head V2=X×W 2-V , W 2-V is the weight matrix of the value vector of the second head.

[0047] The final output of the feature enhancement layer 120 is FO = Concat(head1, head2). It should be noted that the dimension of the concatenation of the attention of the first head head1 and the attention of the second head head2 is still N.

[0048] The hidden layer 130 performs a nonlinear transformation on the output result FO of the feature enhancement layer 120 according to the following formula:

[0049]

[0050] Where Y is the output of the hidden layer 130, W M*N is the weight matrix learned by the hidden layer 130, and b is the bias term.

[0051] Thus, after the cyclic calculation of the multi-layer hidden layer 130 and the linear calculation of the output layer 140, the through-hole contact resistance prediction data can be output.

[0052] In some exemplary embodiments, the back-end process parameters include via depth, via diameter, via bottom metal layer thickness, via bottom metal layer width, via top metal layer thickness, and via top metal layer width.

[0053] It should be noted that, as can be understood by those skilled in the art, the back-end process parameters include not only the through-hole depth, through-hole diameter, through-hole bottom metal layer thickness, through-hole bottom metal layer width, through-hole top metal layer thickness and through-hole top metal layer width, but also other parameters, such as yellow light parameters, etching parameters, deposition parameters, material characteristic parameters, etc.

[0054] In some exemplary embodiments, constructing a training sample set based on the historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers includes: preprocessing the historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers; and constructing the training sample set based on the preprocessed historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers.

[0055] Therefore, by first preprocessing the historical through-hole contact resistance measurement data of the multiple wafers and the historical back-end process online measurement data, and then constructing the training sample set based on the preprocessed historical through-hole contact resistance measurement data of the multiple wafers and the historical back-end process online measurement data, a high-quality training sample set can be provided for subsequent model training, thereby improving the prediction accuracy of the trained through-hole contact resistance prediction model.

[0056] In some exemplary embodiments, the preprocessing of the historical through-hole contact resistance measurement data of the multiple wafers and the historical back-end process online measurement data includes: sequentially performing data cleaning, normalization and labeling on the historical through-hole contact resistance measurement data of the multiple wafers and the historical back-end process online measurement data.

[0057] Therefore, data cleaning can remove noise and outliers introduced by equipment fluctuations, measurement errors or human operational errors, avoid the model being misled by erroneous data during subsequent training, and thus reduce the prediction deviation of the model. By normalizing the data, different types of data can be mapped to the same numerical range (for example, [0,1]), thereby accelerating the convergence of the model during subsequent training. By labeling the data, the online measurement data of the back-end process can be accurately matched with the corresponding through-hole contact resistance, ensuring that the input features of each training sample correspond to the label one-to-one. It should be noted that, as can be understood by those skilled in the art, the data needs to be aligned according to the process timing when labeling (for example, yellow light in front, etching in the back) to ensure that the model can capture the dynamic impact of the process steps.

[0058] Furthermore, before inputting the current back-end process online measurement data of the wafer to be inspected into the through-hole contact resistance prediction model, the through-hole contact resistance prediction method further includes: normalizing the current back-end process online measurement data of the wafer to be inspected.

[0059] Correspondingly, inputting the current back-end process online measurement data of the wafer to be inspected into the through-hole contact resistance prediction model includes: inputting the normalized current back-end process online measurement data of the wafer to be inspected into the through-hole contact resistance prediction model.

[0060] In some exemplary embodiments, the through-hole contact resistance prediction method provided by the present invention further includes: obtaining the influence weight information of each back-end process parameter on the through-hole contact resistance based on the attention weight information of the through-hole contact resistance prediction model.

[0061] Therefore, by obtaining the influence weight information of each back-end process parameter on the through-hole contact resistance based on the attention weight information of the through-hole contact resistance prediction model, engineers can intuitively determine which back-end process parameters have a greater impact on the through-hole contact resistance, thereby providing a theoretical basis for subsequent process tuning.

[0062] Specifically, please refer to Figure 3 , which is a weighted diagram of the influence of various back-end process parameters on the through-hole contact resistance provided by one embodiment of the present invention. Figure 3 As shown, the influence weight of back-end process parameter A on through-hole contact resistance is the largest, followed by the influence weight of back-end process parameter B on through-hole contact resistance, and the influence weights of back-end process parameter C, back-end process parameter D, back-end process parameter E and back-end process parameter F on through-hole contact resistance decrease in sequence. Therefore, according to the influence weight of each back-end process parameter on through-hole contact resistance, the back-end process parameter with the largest influence weight on through-hole contact resistance can be selected to determine the process tuning strategy. It should be noted that Figure 3 The weight values of the influence of various back-end process parameters on the through-hole contact resistance are merely exemplary and do not constitute a limitation to the present invention.

[0063] In some exemplary embodiments, the through-hole contact resistance prediction method provided by the present invention also includes: when the error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance target data of the wafer to be inspected exceeds a preset range, a process tuning strategy is formulated based on the back-end process parameters with the greatest influence on the through-hole contact resistance.

[0064] Therefore, when the error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance target data of the wafer to be inspected exceeds a preset range, a process tuning strategy is formulated based on the back-end process parameters that have the greatest impact on the through-hole contact resistance. This can not only effectively save process tuning time, but also effectively ensure the effectiveness of process tuning.

[0065] In some exemplary embodiments, the through-hole contact resistance prediction method provided by the present invention also includes: obtaining a cross-layer correlation analysis heat map between the back-end process parameters and the through-hole contact resistance based on the attention weight information of the through-hole contact resistance prediction model; and analyzing the cross-layer causality between the through-hole contact resistance and the back-end process parameters based on the cross-layer correlation analysis heat map.

[0066] Therefore, by analyzing the cross-layer causality between the through-hole contact resistance and the back-end process parameters, direct causality and indirect correlation can be distinguished, thereby guiding engineers to prioritize monitoring the back-end process parameters that have a direct causal relationship with the through-hole contact resistance, thereby providing a clear direction for process optimization.

[0067] Please continue to refer to Figure 4 , which is a cross-layer correlation analysis heat map between back-end process parameters and through-hole contact resistance provided by one embodiment of the present invention. Figure 4 As shown, through correlation analysis, it was found that Via3_thk (the thickness of the third-layer via) and Rc_V2 (the contact resistance of the second-layer via) are correlated (0.48), and Via3_thk (the thickness of the third-layer via) and Via2_thk (the thickness of the second-layer via) are strongly correlated (0.72). Further evaluation found that there is no causal relationship between Via3_thk (the thickness of the third-layer via) and Rc_V2 (the contact resistance of the second-layer via). The correlation between Via3_thk (the thickness of the third-layer via) and Rc_V2 (the contact resistance of the second-layer via) is due to the similar process types of Via3_thk (the thickness of the third-layer via) and Via2_thk (the thickness of the second-layer via). It should be noted that, as can be understood by those skilled in the art, Figure 4 The numerical values shown are merely exemplary and do not constitute a limitation to the present invention.

[0068] In some exemplary embodiments, the through-hole contact resistance prediction method provided by the present invention also includes: updating the through-hole contact resistance prediction model when the absolute value of the average error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance measurement data of the wafer to be inspected is greater than a preset threshold.

[0069] Therefore, when the absolute value of the average error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance measurement data of the wafer to be inspected is greater than a preset threshold (for example, 5%), the through-hole contact resistance prediction model is updated to improve the robustness of the through-hole contact resistance prediction model, so that the through-hole contact resistance prediction model can maintain high prediction accuracy and avoid prediction deviation.

[0070] Specifically, the through-hole contact resistance prediction model can be updated through strategies such as hyperparameter tuning, model architecture optimization (such as attention mechanism adjustment, hidden layer 130 structure adjustment), data enhancement and regularization, and training strategy optimization (such as optimizer selection, learning rate adjustment, and batch adjustment).

[0071] Please continue to refer to Table 1, which shows the comparison results of the through-hole contact resistance values predicted by the through-hole contact resistance prediction method provided by the present invention (referred to as predicted values in Table 1) and the through-hole contact resistance values obtained by actual measurement (referred to as actual measured values in Table 1). As shown in Table 1, the accuracy of the through-hole contact resistance data predicted by the through-hole contact resistance prediction method provided by the present invention is greater than 93%, which meets the controllability and can improve the fluctuation rate of the through-hole contact resistance.

[0072] Table 1 Comparison of predicted and measured through-hole contact resistance values

[0073]

[0074] Please continue to refer to Figure 5 , which is a comparison chart of the through-hole contact resistance value predicted by the through-hole contact resistance prediction method provided by the present invention and the through-hole contact resistance value actually measured. Figure 5 As shown, the through-hole contact resistance data predicted by the through-hole contact resistance prediction method provided by the present invention is highly consistent with the through-hole contact resistance data obtained by actual measurement.

[0075] Based on the same inventive concept, the present invention also provides an electronic device, please refer to Figure 6 , which is a block diagram of an electronic device provided by one embodiment of the present invention. Figure 6As shown, the electronic device includes a processor 210 and a memory 230. The memory 230 stores a computer program. When the computer program is executed by the processor 210, the through-hole contact resistance prediction method described above is implemented. Since the electronic device provided by the present invention and the through-hole contact resistance prediction method provided by the present invention are based on the same inventive concept, the electronic device provided by the present invention has at least all the beneficial effects of the through-hole contact resistance prediction method provided by the present invention. Therefore, for the beneficial effects of the electronic device provided by the present invention, reference can be made to the relevant description of the beneficial effects of the through-hole contact resistance prediction method provided by the present invention above, and no further description will be given here.

[0076] Please continue to refer to Figure 6 ,like Figure 6 As shown, the electronic device further includes a communication interface 220 and a communication bus 240. The processor 210, the communication interface 220, and the memory 230 communicate with each other via the communication bus 240. The communication bus 240 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, for example. The communication bus 240 can be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus. The communication interface 220 is used for communication between the electronic device and other devices.

[0077] It should be noted that the processor 210 referred to in the present invention may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor 210 is the control center of the electronic device, connecting various parts of the entire electronic device using various interfaces and lines.

[0078] It should also be noted that the memory 230 can be used to store the computer program, and the processor 210 implements various functions of the electronic device by running or executing the computer program stored in the memory 230 and calling the data stored in the memory 230. The memory 230 may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable memory (PROM), electrically programmable memory (EPROM), electrically erasable programmable memory (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, random access memory is available in many forms, such as static random access memory (SRAM), dynamic random access memory (DRAM), synchronous random access memory (SDRAM), double data rate synchronous random access memory (DDRSDRAM), enhanced synchronous random access memory (ESDRAM), synchronous link (Synchlink) dynamic random access memory (SLDRAM), memory bus (Rambus) direct random access memory (RDRAM), direct memory bus dynamic random access memory (DRDRAM), and memory bus dynamic random access memory (RDRAM), etc.

[0079] The present invention also provides a readable storage medium having a computer program stored therein. When executed by a processor, the computer program can implement the through-hole contact resistance prediction method described above. Since the readable storage medium provided by the present invention and the through-hole contact resistance prediction method provided by the present invention are based on the same inventive concept, the readable storage medium provided by the present invention has at least all the beneficial effects of the through-hole contact resistance prediction method provided by the present invention. Therefore, for the beneficial effects of the readable storage medium provided by the present invention, reference can be made to the relevant description of the beneficial effects of the through-hole contact resistance prediction method provided by the present invention above, and no further elaboration is given here.

[0080] The readable storage medium provided by the present invention may adopt any combination of one or more computer-readable media. The readable medium may be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples (non-exhaustive) of computer-readable storage media include: an electrical connection having one or more wires, a portable computer hard drive, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. As used herein, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, device, or component.

[0081] A computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, which carries computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium, which may transmit, propagate, or transfer a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wired, optical cable, etc., or any suitable combination thereof.

[0082] In summary, compared with the existing technology, the through-hole contact resistance prediction method, electronic device and readable storage medium provided by the present invention have the following unexpected technical effects: based on deep learning and combined with the attention mechanism, the present invention can not only learn the interaction characteristics between different back-end process parameters but also learn the correlation between cross-layer processes and through-hole contact resistance, thereby realizing real-time and accurate prediction of through-hole contact resistance, effectively saving testing time and cost, and also laying a certain foundation for subsequent process optimization.

[0083] It should be noted that the computer program code for performing the operations of the present invention can be written in one or more programming languages, or a combination thereof, including object-oriented programming languages such as Java, Smalltalk, and C++, as well as conventional procedural programming languages such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0084] It should be noted that the above description is merely a description of preferred embodiments of the present invention and does not limit the scope of the present invention. Any changes or modifications made by persons skilled in the art based on the above disclosure are within the scope of protection of the present invention. Obviously, various modifications and variations may be made by persons skilled in the art without departing from the spirit and scope of the present invention. Thus, provided such modifications and variations fall within the scope of the present invention and its equivalents, the present invention is intended to include such modifications and variations.

Claims

1. A method for predicting through-hole contact resistance, characterized in that: include: Obtain historical through-hole contact resistance measurement data and historical back-end process online measurement data for multiple wafers; Based on the historical through-hole contact resistance measurement data and the historical back-end process online measurement data of the multiple wafers, a training sample set is constructed, wherein each training sample in the training sample set includes the back-end process online measurement data and the corresponding through-hole contact resistance measurement data, and the through-hole contact resistance measurement data is the label of the training sample, the back-end process online measurement data in each training sample includes the online measurement data of multiple back-end process parameters corresponding to each layer of through-holes, and the through-hole contact resistance measurement data in each training sample includes the contact resistance corresponding to each layer of through-holes; Using the training sample set to train a pre-built deep neural network model to obtain a corresponding through-hole contact resistance prediction model, wherein the deep neural network model includes a feature enhancement layer, and the feature enhancement layer is used to learn the interaction features between different back-end process parameters based on a multi-head attention mechanism and learn the cross-layer correlation between the back-end process parameters and the through-hole contact resistance; Inputting the current back-end process online measurement data of the wafer to be inspected into the through-hole contact resistance prediction model to obtain the through-hole contact resistance prediction data of the wafer to be inspected; The back-end process parameters include through-hole depth, through-hole diameter, through-hole bottom metal layer thickness, through-hole bottom metal layer width, through-hole top metal layer thickness and through-hole top metal layer width.

2. The through-hole contact resistance prediction method according to claim 1, characterized in that: The method of constructing a training sample set based on historical through-hole contact resistance measurement data of the plurality of wafers and historical back-end process online measurement data includes: Preprocessing historical through-hole contact resistance measurement data and historical back-end process online measurement data of the plurality of wafers; The training sample set is constructed based on the pre-processed historical through-hole contact resistance measurement data of the plurality of wafers and the historical back-end process online measurement data.

3. The through-hole contact resistance prediction method according to claim 2, characterized in that: The pre-processing of the historical through-hole contact resistance measurement data of the plurality of wafers and the historical back-end process online measurement data includes: The historical through-hole contact resistance measurement data of the plurality of wafers and the historical back-end process online measurement data are sequentially cleaned, normalized and labeled.

4. The through-hole contact resistance prediction method according to claim 1, wherein: The method further comprises: According to the attention weight information of the through-hole contact resistance prediction model, the influence weight information of each back-end process parameter on the through-hole contact resistance is obtained.

5. The through-hole contact resistance prediction method according to claim 4, characterized in that: The method further comprises: When the error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance target data of the wafer to be inspected exceeds a preset range, a process tuning strategy is formulated based on the back-end process parameter with the greatest influence on the through-hole contact resistance.

6. The through-hole contact resistance prediction method according to claim 4, characterized in that: The method further comprises: Obtaining a cross-layer correlation analysis heat map between back-end process parameters and through-hole contact resistance based on the attention weight information of the through-hole contact resistance prediction model; The cross-layer causality between the through-hole contact resistance and the back-end process parameters is analyzed based on the cross-layer correlation analysis heat map.

7. The through-hole contact resistance prediction method according to claim 1, characterized in that: The method further comprises: When the absolute value of the average error between the through-hole contact resistance prediction data of the wafer to be inspected and the through-hole contact resistance measurement data of the wafer to be inspected is greater than a preset threshold, the through-hole contact resistance prediction model is updated.

8. An electronic device, characterized in that: The method comprises a processor and a memory, wherein a computer program is stored in the memory, and when the computer program is executed by the processor, the through-hole contact resistance prediction method according to any one of claims 1 to 7 is implemented.

9. A readable storage medium, characterized in that The readable storage medium stores a computer program, and when the computer program is executed by a processor, the through-hole contact resistance prediction method according to any one of claims 1 to 7 is implemented.

Images