Method and device for determining process parameters and semiconductor process equipment

Abstract

This application provides a method, apparatus, and semiconductor manufacturing equipment for determining process parameters. The method includes: responding to user-inputted target process information by inputting the target process information into a target network model; the target process information includes the process result achievable by the process formulation to be determined; predicting the process parameters required to achieve the process result using the target network model; the target network model includes a capsule network layer constructed based on capsule networking; and determining the prediction results output by the target network model as the process parameters for the process formulation to be determined. This application can quickly determine process parameters that meet process requirements, saving significant time, and the inclusion of a capsule network layer based on capsule networking in the target network model can improve the accuracy of the process parameters.

Description

[Technical Field]

[0001] The embodiments in this application relate to the field of production process technology, specifically to process formula processing technology in the field of production process technology, and more specifically, to a method, apparatus and semiconductor process equipment for determining process parameters. [Previous Technology]

[0002] A process formulation can be simply understood as a combination of various process parameters under the working state of a process equipment, and its accuracy directly affects the process result. In the process generation process, the process requirement, i.e., the desired process result, usually appears first. Then, based on this process requirement, the process parameters are continuously adjusted so that the adjusted process parameters can meet the process requirement.

[0003] However, the above process is not something that can be accomplished overnight. It requires continuous adjustment of process parameters so that the process results after adjustment are constantly closer to the desired process results, and finally process parameters that meet the process requirements are obtained. The whole process takes a long time. [Summary of the Invention]

[0004] This application provides a method, apparatus and semiconductor process equipment for determining process parameters in several embodiments, so as to achieve the purpose of quickly determining process parameters that can meet process requirements.

[0005] In a first aspect, one embodiment of this application provides a method for determining process parameters, the method comprising: responding to target process information input by a user, inputting the target process information into a target network model; wherein the target process information includes a process result achievable by a process formulation to be determined; predicting the process parameters required to achieve the process result using the target network model; wherein the target network model includes: a capsule network layer constructed based on a capsule network; and determining the prediction result output by the target network model as the process parameters of the process formulation to be determined.

[0006] In some embodiments, the capsule network layer includes: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, and an output layer; predicting the process parameters required to achieve the process result using the target network model includes: preprocessing the target process information using the input layer to generate input features; extracting features from the input features using the convolutional layer to generate an initial feature vector; extracting features from the initial feature vector using the main capsule layer to generate an initial capsule vector; processing the initial capsule vector using the digital capsule layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and a prediction probability of each predicted value; and the output layer outputs the predicted value with the highest prediction probability for each process parameter based on the result capsule vectors.

[0007] In some embodiments, the initial capsule vector is generated by extracting features from the initial feature vector through the main capsule layer, including: extracting features from the initial feature vector through the main capsule layer in a dynamic routing manner to generate the initial capsule vector.

[0008] In some embodiments, before performing feature processing on the initial capsule vector using the digital capsule layer to generate a target number of result capsule vectors, the method further includes: determining an execution chamber based on the target process information using the target network model, wherein the execution chamber is a chamber in the process equipment that executes the process recipe to be determined; and determining the number of process parameters corresponding to the execution chamber as the target number based on the correspondence between each chamber and the number of process parameters in the process equipment using the target network model.

[0009] In some embodiments, the target network model further includes: a long short-term memory network layer constructed based on a long short-term memory network, wherein the input of the long short-term memory network layer is the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

[0010] In some embodiments, predicting the process parameters required to achieve the process result using the target network model includes: processing the target process information using the capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and a predicted probability of each predicted value; processing the result capsule vectors using the forget gate, input gate, output gate, and output layer of the long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0011] In some embodiments, the target network model further includes: a long short-term memory network layer constructed based on a long short-term memory network, and an attention module constructed based on an attention mechanism; wherein, the input of the attention module is the target process information, the input of the long short-term memory network layer is the fusion result of the output of the attention module and the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

[0012] In some embodiments, predicting the process parameters required to achieve the process result using the target network model includes: processing the target process information using the capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and a predicted probability of each predicted value; processing the target process information using the attention module to generate a context vector corresponding to each result capsule vector; and processing the fusion result of the result capsule vector and the context vector using the forget gate, input gate, output gate, and output layer of the long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0013] In some embodiments, in response to user-inputted target process information, before inputting the target process information into the target network model, the method further includes: acquiring training data; wherein the training data includes: historical process recipes and the process results achievable by the historical process recipes; using the training data to train the network model constructed by the capsule network, and determining the trained network model as the target network model.

[0014] In some embodiments, during the model training process of the network model constructed by the capsule network using the training data, the sum of the interval loss and the reconstruction loss is used as the model loss.

[0015] In a second aspect, one embodiment of this application provides a process parameter determination apparatus, the process parameter determination apparatus comprising: a response module, configured to respond to target process information input by a user and input the target process information to a target network model; wherein the target process information includes a process result achievable by a process formulation to be determined; a model processing module, configured to predict the process parameters required to achieve the process result using the target network model; wherein the target network model includes: a capsule network layer constructed based on a capsule network; and a determination module, configured to determine the prediction result output by the target network model as the process parameters of the process formulation to be determined.

[0016] In some embodiments, the capsule network layer includes: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, and an output layer; the model processing module includes: a preprocessing unit, used to preprocess the target process information through the input layer to generate input features; a first feature extraction unit, used to extract features from the input features through the convolutional layer to generate an initial feature vector; a second feature extraction unit, used to extract features from the initial feature vector through the main capsule layer to generate an initial capsule vector; a model processing unit, used to perform feature processing on the initial capsule vector through the digital capsule layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and a prediction probability of each predicted value; a model output unit, used by the output layer to output the predicted value with the highest prediction probability for each process parameter based on the result capsule vectors.

[0017] In some embodiments, the second feature extraction unit is specifically used to extract features from the initial feature vector by means of the main capsule layer in a dynamic routing manner to generate an initial capsule vector.

[0018] In some embodiments, the apparatus further includes: a chamber determination module, configured to determine an execution chamber based on the target process information using the target network model, wherein the execution chamber is a chamber in the process equipment that executes the process recipe to be determined; and a quantity determination module, configured to determine the number of process parameters corresponding to the execution chamber as the target quantity based on the correspondence between each chamber and the number of process parameters in the process equipment using the target network model.

[0019] In some embodiments, the target network model further includes: a long short-term memory network layer constructed based on a long short-term memory network, wherein the input of the long short-term memory network layer is the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model. In some embodiments, the model processing module is specifically used to: process the target process information through the capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and a predicted probability of each predicted value; process the result capsule vectors through the forget gate, input gate, output gate, and output layer of the long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0020] In some embodiments, the target network model further includes: a long short-term memory network layer constructed based on a long short-term memory network, and an attention module constructed based on an attention mechanism; wherein, the input of the attention module is the target process information, the input of the long short-term memory network layer is the fusion result of the output of the attention module and the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model. In some embodiments, the model processing module is specifically used for: processing the target process information through the capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and a prediction probability of each predicted value; processing the target process information through the attention module to generate a context vector corresponding to each result capsule vector; and processing the fusion result of the result capsule vector and the context vector through the forget gate, input gate, output gate, and output layer of the long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0021] In some embodiments, the device further includes: a model training module, used to: acquire training data; wherein the training data includes: historical process recipes and the process results that the historical process recipes can achieve; use the training data to train the network model constructed by the capsule network, and determine the trained network model as the target network model.

[0022] In some embodiments, during the model training process of the network model constructed by the capsule network using the training data, the sum of the interval loss and the reconstruction loss is used as the model loss.

[0023] In a third aspect, one embodiment of this application provides a semiconductor manufacturing apparatus, comprising: a host computer and a slave computer connected to the host computer; the host computer is configured to execute a process parameter determination method as described in any of the first aspects to determine process parameters of a process recipe to be determined, and to send the process parameters of the process recipe to be determined to the slave computer; the slave computer is configured to receive the process parameters of the process recipe to be determined, and to perform process production according to the process parameters of the process recipe to be determined.

[0024] In a fourth aspect, one embodiment of this application provides an electronic device, including a processor and a memory; wherein the memory is connected to the processor and is used to store a computer program; the processor is used to implement the method for determining process parameters as described in any one of the first aspects by running the computer program stored in the memory.

[0025] In a fifth aspect, one embodiment of this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method for determining process parameters as described in any of the first aspects.

[0026] In a sixth aspect, one embodiment of this application provides a computer program product or computer program, the computer program product including a computer program stored in a computer-readable storage medium; the processor of the computer device reads the computer program from the computer-readable storage medium, and the processor executes the computer program to implement the steps of the method for determining process parameters as described in any of the first aspects.

[0027] The various embodiments provided in this application, for process parameters of a process formulation to be determined, first determine the process result that can be achieved or is expected to be achieved, i.e., the process requirement. Then, with the help of a target network model, predict the process parameters that can achieve this process result, and finally use the predicted process parameters as the process parameters of the process formulation to be determined. Compared with the method of using self-consistent iterative calculation to find the optimal process parameters, this application can quickly determine the process parameters that can meet the process requirements, saving a lot of time. At the same time, the target network model includes a capsule network layer based on capsule network construction, so that the target network model integrates the characteristics of capsule network, which can better consider the correlation between different features, thereby improving the accuracy of process parameters.

Implementation Method

[0029] Unless otherwise defined, the technical or scientific terms used in the embodiments of this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms "first," "second," and similar terms used in the embodiments of this application do not indicate any order, quantity, or importance, but are merely used to avoid confusion of the constituent elements.

[0030] Unless the context otherwise requires, throughout the specification, "a plurality of" means "at least two," and "including" is interpreted as open-ended or encompassing, that is, "including, but not limited to." In the description of the specification, terms such as "one embodiment," "some embodiments," "exemplary embodiment," "example," "specific example," or "some examples" are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this application. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example.

[0031] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of this application. Overview

[0032] As described in the background section, process formulation is crucial in the manufacturing process. Determining appropriate process parameters to meet process requirements is an unavoidable issue in process generation. As shown in Figure 1, after inputting process requirements, a set of process parameters is usually randomly assigned. The system then determines whether the current process parameters meet the requirements. If not, the process parameters need to be updated based on the deviation from the expected result until the requirements are met, at which point the manufacturing process will be executed according to the latest process parameters.

[0033] Although a neural network model is used to determine process parameters, the principle of this model is still to slowly find the optimal process parameters through self-consistent iterative calculations. In order to shorten the time for determining process parameters, the inventors discovered through research that the required process parameters can be directly predicted based on the desired process results. At the same time, combined with the characteristics of capsule networks, the process parameters that meet the process requirements can be quickly obtained by using the target network model.

[0034] Based on the above concept, the method for determining process parameters provided in the embodiments of this application will be described below by way of example. Exemplary Method

[0035] As shown in Figure 2, this application embodiment provides a method for determining process parameters. The method for determining process parameters includes: Step S201: In response to the target process information input by the user, the target process information is input into the target network model.

[0036] In this step, the target process information includes the process result achievable by the process formulation to be determined. The process formulation to be determined is the desired process formulation or a process formulation that meets the process requirements. The process result can be understood as the process requirement or the result of the process requirement. Specifically, during the process generation process, if it is necessary to determine a process formulation that can achieve a certain process result or meet a certain process requirement, then this process formulation can be considered as the process formulation to be determined, and the process result or process requirement can be considered as the target process information. For example, for semiconductor process equipment, suppose it is necessary to determine the specific parameter values ​​of process temperature, process pressure, and gas flow rate that enable a deposition rate of 10 nanometers per minute. This deposition rate of 10 nanometers per minute is the target process information, and the specific parameter values ​​of process temperature, process pressure, and gas flow rate are the process formulation to be determined or the process parameters in the process formulation. It is understandable that the target process information and process formulation are related to the process production process involved in the process equipment, which includes, but is not limited to, the process production process of semiconductor process equipment.

[0037] It should be noted that the method provided in this application can be directly applied to the process equipment to determine the process parameters. Therefore, after determining the process parameters, production can be directly carried out according to these process parameters. In this case, the user only needs to input the target process information into the process equipment. Of course, other electronic devices with more powerful computing capabilities can also be used to determine the process parameters using the method provided in this embodiment. Then, the process parameters are input into the process equipment so that the process equipment performs production according to the input process parameters.

[0038] Step S202: Predict the process parameters required to achieve the process result using the target network model.

[0039] Step S203: The prediction results output by the target network model are determined as the process parameters of the process formula to be determined.

[0040] It should be noted that the target network model is a pre-trained network model. Its input is the process requirement or process result, and its output is the predicted process parameters that can meet the process requirement or achieve the process result, i.e., the prediction result. Therefore, by using the target network model, the process parameters corresponding to the target process information can be obtained, that is, the process parameters that can achieve the process result in the target process information can be obtained. After determining the process parameters, the process formula to be determined can be determined. Then, the process equipment can use the determined process formula to be determined for process production.

[0041] The target network model includes: capsule network layers built based on capsule networks. Capsule networks, or Capsule Nets, offer significant advantages over convolutional neural networks in several aspects. For example, capsule networks can extract richer object features through hierarchical feature extraction. In contrast, convolutional neural networks primarily extract features through tiling and pooling operations, potentially losing some detailed information. Capsule networks represent objects using vectors; this distributed representation better captures the internal structure and relationships of objects. Convolutional neural networks generally use scalars to represent features, making it difficult to represent the complex structure of objects.

[0042] In this embodiment, for the process parameters of the process formulation to be determined, the achievable or expected process result, i.e., the process requirement, is first determined. Then, the process parameters that can achieve this process result are predicted by using the target network model, and finally, the predicted process parameters are used as the process parameters of the process formulation to be determined. Compared with the method of using self-consistent iterative calculation to find the optimal process parameters, this application can quickly determine the process parameters that can meet the process requirements, saving a lot of time. At the same time, the target network model includes a capsule network layer based on capsule network, which integrates the characteristics of capsule network into the target network model, and can better consider the correlation between different features, thereby improving the accuracy of the process parameters.

[0043] In some embodiments, the capsule network layer includes: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, and an output layer; Predicting the process parameters required to achieve the process result using the target network model includes: preprocessing the target process information using the input layer to generate input features; extracting features from the input features using the convolutional layer to generate an initial feature vector; extracting features from the initial feature vector using the main capsule layer to generate an initial capsule vector; processing the initial capsule vector using the digital capsule layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; and the output layer outputs the predicted value with the highest prediction probability for each process parameter based on the result capsule vectors.

[0044] It should be noted that the input of the input layer is the input of the target network model, which is used to preprocess the input data of the target network model, thereby processing it into features that can be directly recognized and processed. The input of the convolutional layer is the output of the input layer, which is used to perform convolution processing on the output of the input layer, thereby generating an initial feature vector. The convolution processing will not be described in detail here. In some embodiments, the convolutional layer in this embodiment can adopt a three-layer convolutional structure, thereby avoiding an overly complex network structure and making it suitable for parameter tuning on large devices. The input of the main capsule layer is the output of the convolutional layer, which is used to process the output of the convolutional layer, thereby generating an initial capsule vector. The main capsule layer is the PrimaryCaps layer in the capsule network, which can perform data processing of the PrimaryCaps layer, and will not be described in detail here. The input of the digital capsule layer is the output of the main capsule layer, which is used to process the output of the main capsule layer, thereby generating a result capsule vector. The digital capsule layer is the DigitCaps layer in the capsule network, which can perform data processing of the DigitCaps layer, and will not be described in detail here. The output layer takes the output of the digital capsule layer as its input and processes that output to obtain the final output of the target network model. The output of the output layer is the output of the target network model.

[0045] Specifically, the input layer preprocesses the target process information, including: standardizing the length of the target process information and performing IDX conversion. Standardizing the length includes adjusting the input data to the same length, which can be achieved by padding with null values ​​or truncation. IDX is a binary file format typically used to store multidimensional array data. It is converted from IDX to a tensor or matrix format suitable for the network model for input.

[0046] The processing of the convolutional layer includes: processing the input features using Formula 1. Formula 1: ; where represents the initial feature vector, represents the convolution kernel, represents the bias term, is a non-linear initiation function, such as the ReLU function, but not limited to it, and represents the input features.

[0047] It is understandable that the larger the convolution kernel, the greater the amount of information contained in the initial feature vector.

[0048] The processing of the main capsule layer includes: processing the initial feature vector using Formula 2.

[0049] Formula 2: ; where represents the initial capsule vector, represents the convolution kernel of the main capsule layer, represents the initial feature vector, represents the bias term, and is the squash function in the capsule network.

[0050] The main capsule layer can transform the multidimensional data output by the convolutional layer into several capsules or capsule vectors. Specifically, it performs in-depth feature extraction on the target process information.

[0051] The processing of the digital capsule layer includes: processing the initial capsule vector using Formula 3.

[0052] Formula 3: ; where represents the resulting capsule vector, represents the initial capsule vector, and and are the weights and biases, respectively. represents the transformation matrix.

[0053] It is understood that each capsule is associated with the previous capsule network by a transformation matrix. The input is predicted by using the transformation matrix. Through the calculation of the digital capsule layer, multiple capsule vectors containing feature information can be obtained, namely the result capsule vectors. The number of capsule vectors is equal to the number of process parameters in the process recipe to be determined.

[0054] In this embodiment, the capsule network layer is composed of an input layer, a convolutional layer, a main capsule layer, a digital capsule layer and an output layer. This can effectively integrate the characteristics of the capsule network in the target network model, while avoiding an overly complex network structure.

[0055] In some embodiments, the initial capsule vector is generated by extracting features from the initial feature vector through the main capsule layer, including: extracting features from the initial feature vector through the main capsule layer in a dynamic routing manner to generate the initial capsule vector.

[0056] It should be noted that in a capsule network, the main capsule layer can be considered as being composed of multiple capsules, with each capsule in each layer connected to each capsule in the next layer. Furthermore, each capsule performs the same dynamic routing process on the output of the previous layer capsule, and finally, the output of the last layer capsule is used as the initial capsule vector. During the process of lower-layer capsules passing the input vector to higher-layer capsules, the corresponding parameters are continuously adjusted to enable the higher-layer capsules to output more suitable data; this process can be called dynamic routing. Since the dynamic routing process is the same for each capsule, only one capsule is used as an example here. As shown in Figure 3, assume that the previous layer capsule includes two capsules, and the outputs of the two capsules are V1 and V2, with weights W1 and W2 respectively. Then, the coupling coefficients used in the first processing of this capsule are and , resulting in S1. After processing by the squeezing function, the coupling coefficients used in the processing are updated to obtain and . Then, the capsule undergoes a second processing, and the updated coupling coefficients are used to obtain a new result S2. After processing by the squeezing function again, the coupling coefficients used in the processing are updated to obtain and . Then, a third processing step is performed in the capsule, and the updated coupling coefficients are used to obtain a new result S3. Given that S3 is suitable data, the capsule's true output V is obtained through a squeezing function. It can be understood that when the capsule length represents the probability of process parameters, the capsule's modulus can represent the significance of the feature; the longer the modulus, the more significant the feature. Simultaneously, when the modulus is close to 0, it also has an amplification effect, eliminating the need for global compression using a squeezing function. The squeezing function is shown below: ; The squeezing function is mainly divided into two parts. The first part changes the length of the input vector without changing its direction. The second part controls the size of the first part using a vector of length 1. This preserves the direction of the input vector while controlling its size. The input vector can be determined by the following formula: ; ; where represents the output of the lower-level capsule, represents the weight parameter, and represents the coupling coefficient. There are coupling coefficients between the higher-level and lower-level capsules, and the sum of these coupling coefficients is 1.

[0057] In the process of updating the coupling coefficient, an intermediate parameter b can be used. Specifically, it is as follows: , where, ; ; where represents the intermediate parameter, represents the output of the lower-level capsule, and represents the output of the higher-level capsule. When and are in the same direction, it indicates that the features expressed by the lower-level capsule and the higher-level capsule are highly similar, and the weight of will increase; conversely, the features of the lower-level capsule are highly unlikely to belong to the higher-level capsule, and the weight of will decrease. The dynamic routing algorithm establishes the connection between the lower-level capsule and the higher-level capsule through the weight update method.

[0058] Of course, besides dynamic routing, clustering algorithms can also be used to generate initial capsule vectors. It can be understood that when using clustering algorithms, the process from lower-level capsules to higher-level capsules is similar to the process of generating cluster centroids during clustering. Assume the features of the lower-level capsules are ,,…, and they are divided into k classes. The process of determining the initial capsule vectors can be understood as finding the central features of the k higher-level capsules, ,,…, that minimize the intra-class margin. The intra-class margin can be calculated based on Formula 4.

[0059] Formula 4: ; Where, L represents the minimum intra-class margin, represents the output of the lower-level capsule, and represents the output of the higher-level capsule. represents the distance between the lower-level and higher-level capsules. The specific form depends on the clustering result.

[0060] The distances between all categories of high-level capsules are summed, and the goal is to minimize the distance. Then, where , , ..., represent the central features of the k high-level capsules, and L represents the minimum intra-class margin. L can then be obtained using approximation formulas. Specifically, Approximation Formula 1: ; Approximation Formula 2: ; where , ... represent n numerical values.

[0061] Based on the above approximation formula, the formula for calculating the minimum intra-class margin can be obtained: ; After mathematical calculation, we can obtain: ; Let , , represent the result of the r-th repeated operation, represent the scalar product operation, represent the coupling coefficient, represent the output of the lower-level capsule, and represent the output of the higher-level capsule, so that the relationship between the lower-level capsule and the higher-level capsule can be obtained. That is: ; where represents the coupling coefficient of the r-th repeated operation, represents the output of the lower-level capsule, and represents the output of the higher-level capsule of the (r+1)-th repeated operation.

[0062] The introduction of the transformation matrix allows for arbitrary changes to the dimensions of the centers of the low-level capsules and high-level capsules, ensuring the feature representation capability of the high-level capsules. Correspondingly, the relationship between the low-level capsules and high-level capsules will change to: ; where represents the transformation matrix, represents the coupling coefficient of the r-th iteration, represents the output of the low-level capsule, and represents the output of the high-level capsule in the (r+1)-th iteration.

[0063] In this embodiment, by taking advantage of the characteristics of dynamic routing, the relationship between various parameters can be strengthened, thereby better capturing the internal structure and relationships of the processing object. Compared with other clustering algorithms, the network structure in this embodiment is more lightweight.

[0064] To adapt to process parameters in different execution chambers, in some implementation methods, before performing feature processing on the initial capsule vector by a digital capsule layer to generate the target number of result capsule vectors, the method further includes: determining the execution chamber based on target process information using a target network model, wherein the execution chamber is a chamber in the process equipment that executes the process recipe to be determined; and determining the number of process parameters corresponding to the execution chamber as the target number based on the correspondence between each chamber and the number of process parameters in the process equipment using the target network model.

[0065] It should be noted that the process equipment includes multiple execution chambers, and different execution chambers can perform different process production according to different process parameters or process recipes. For example, semiconductor process equipment includes: MOW chamber and CVDW chamber. The process parameters executed by the MOW chamber include: process temperature, process pressure, gas flow rate, etc. The process parameters executed by the CVDW chamber include: soak time, process temperature, etc.

[0066] The target network model can be applied to multiple execution chambers. Since the process results differ between different execution chambers, the process results can be used to distinguish between different execution chambers, thereby determining which process parameters need to be output. Of course, the target network model can also be applied only to a single execution chamber. Regardless of which execution chamber's target process information is input to the target network model, its output is the process parameters for a specific execution chamber.

[0067] In this embodiment, the target network model can determine the execution chamber based on the target process information, thereby predicting process parameters for the determined execution chamber, so that the target network model can adapt to the process parameters in different execution chambers.

[0068] In order to further improve the accuracy of the model output and avoid gradient vanishing or gradient explosion problems, in some implementation methods, the target network model also includes: a long short-term memory network layer constructed based on the long short-term memory network, wherein the input of the long short-term memory network layer is the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

[0069] It should be noted that the Long Short-Term Memory (LSTM) network is the same as the Long Short-Term Memory network. The LSTM layer in the target network model integrates the advantages of the LSTM network in terms of gradients, which can avoid the problems of gradient vanishing and gradient exploding. In this embodiment, the LSTM layer is located after the capsule network layer, and the input of the LSTM layer is the output of the capsule network layer. The output of the LSTM layer is the output of the target network model.

[0070] In this embodiment, the advantages of LSTM network in terms of gradient are integrated. By setting a long short-term memory network layer in the target network model, not only can the problems of gradient vanishing and gradient explosion be avoided, but the temporal characteristics of the target process information can also be taken into account to improve the accuracy of the model output.

[0071] In some embodiments, predicting the process parameters required to achieve the process result by means of a target network model includes: processing the target process information by means of a capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; processing the result capsule vectors by means of a forget gate, an input gate, an output gate and an output layer of a long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0072] It should be noted that the network architecture of the Long Short-Term Memory (LSTM) network layer is shown in Figure 4. The forget gate is , the input gate is , and the output gate is . The input to the input gate is determined by the historical state and the current node state. is a sigmoid function that controls the output between 0 and 1. 1 indicates that historical information is retained, and 0 indicates that historical information is forgotten. The input gate can be calculated using the following formula: ; where represents the output result of the input gate, represents the weight matrix of the current state at the input gate, represents the weight matrix of the historical state at the input gate, and represents the weight bias of the input gate.

[0073] Similarly, the forget gate and the output gate can be calculated by the following formula: ;; where represents the output result of the forget gate, represents the weight matrix of the current state in the forget gate, represents the weight matrix of the historical state in the forget gate, and represents the weight bias of the forget gate; represents the output result of the output gate, represents the weight matrix of the current state in the output gate, represents the weight matrix of the historical state in the output gate, and represents the weight bias of the output gate.

[0074] Then, based on the previous state and the current state, new information is selected and transmitted to the next neuron. The specific process is as follows: The current state is processed using a function and multiplied with the output gate to realize the hidden vector, which is then connected to the next unit to extract the temporal feature information associated with the preceding and following data packets during transmission. Finally, the softmax function is used to obtain the final prediction output result.

[0075] In this embodiment, a long short-term memory network layer is formed by a forget gate, an input gate, an output gate and an output layer to process the resulting capsule vector. By taking into account the temporal characteristics of the data, more accurate process parameters can be obtained.

[0076] To further improve the accuracy of the model output and avoid gradient vanishing or gradient exploding problems, in some implementation methods, the target network model also includes: a long short-term memory network layer built based on a long short-term memory network and an attention module built based on an attention mechanism; wherein, the input of the attention module is the target process information, the input of the long short-term memory network layer is the fusion result of the output of the attention module and the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

[0077] It should be noted that the introduction of an LSTM network in the target network model is similar to the introduction of an LSTM network in the above embodiments, and will not be repeated here. The difference lies in that this application also introduces an attention module based on an attention mechanism. The attention mechanism can be understood as a method that mimics the human visual and cognitive system, allowing the neural network model to focus its attention on relevant parts when processing input data. By introducing the attention mechanism, the neural network model can automatically learn and selectively focus on important information in the input, thereby improving the model's performance and generalization ability. After model training, the output of the attention module can indicate the importance of each feature output by the capsule network layer. Furthermore, fusing the output of the attention module with the output of the capsule network layer can increase the proportion of features with higher importance, thereby focusing on important information. Then, the fused result is input into the LSTM network, and by continuously adjusting the weights between features, a more accurate result can be obtained.

[0078] In this embodiment, the advantages of LSTM network in terms of gradient are integrated. By setting a long short-term memory network layer in the target network model, not only can the problems of gradient vanishing and gradient explosion be avoided, but also the temporal characteristics of the target process information can be taken into account, and an attention mechanism is introduced, which can further improve the accuracy of the model output.

[0079] In some embodiments, predicting the process parameters required to achieve the process result using a target network model includes: processing the target process information using a capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; processing the target process information using an attention module to generate a context vector corresponding to each result capsule vector; and processing the fusion result of the result capsule vector and the context vector using the forget gate, input gate, output gate, and output layer of a long short-term memory network to obtain the process parameters required to achieve the process result.

[0080] It should be noted that the network architecture of the Long Short-Term Memory (LSTM) network layer is shown in Figure 4. The processing of the fusion result by the LTM network layer in the target network model is similar to the processing of the result capsule vector by the LTM network layer in the above embodiment, and will not be repeated here. However, the object processed in this application is different, namely the fusion result of the result capsule vector and the context vector. The attention mechanism will not be detailed here, but it can be understood that the context vector is the output of the attention module. The context vector corresponding to each result capsule vector is positively correlated with the importance of the result capsule vector. That is, the higher the importance of a certain result capsule vector in the process of predicting process parameters, the larger its corresponding context vector will be. This is the ability learned by the attention module based on the attention mechanism during model training. Specifically, multiple partially overlapping continuous subsequences can be extracted from the original input sequence, i.e., the target process information, as input to the attention module from the input of the input layer. The context vector output by the attention module can be regarded as a saliency feature, which can identify the importance of each output feature of the digital capsule layer. The higher the importance of the output features of the digital capsule layer, the closer the output of its corresponding attention module is to 1; conversely, the lower the importance of the output features of the digital capsule layer, the closer the output value of its corresponding attention module is to 0. Then, the output features of the digital capsule layer are fused with the saliency features output by its corresponding attention module. The fusion method involves element-wise multiplication of the output features of the digital capsule layer with the saliency features output by its corresponding attention module. Since the value of the attention module output reflects the importance of the output features of the digital capsule layer, the identification of important features is completed, which is more beneficial for subsequent processing by the LSTM network layers, thus further improving the model's accuracy. Introducing an attention mechanism during model training allows for high-weighting of important information and continuous adjustment of the weights between features, resulting in improved prediction accuracy compared to existing algorithms.

[0081] In this embodiment, a long short-term memory network layer is formed by a forget gate, an input gate, an output gate, and an output layer to process the fusion result. By taking into account the temporal characteristics of the data, more accurate process parameters can be obtained. At the same time, the introduction of an attention mechanism can reduce the interference of useless parameters, solve the problem of information overload, and weight the data with greater influence on the result among many input information, thereby improving the accuracy of the final prediction.

[0082] In some implementations, in response to user-inputted target process information, before inputting the target process information into the target network model, the method further includes: acquiring training data; wherein the training data includes: historical process recipes and the process results achievable by the historical process recipes; using the training data to train the network model constructed by the capsule network, and determining the trained network model as the target network model.

[0083] It should be noted that historical process recipes are the process recipes used in the historical process generation process. The corresponding process result is the achievable process result. For example, in the historical process generation process, using historical process recipe A can achieve process result a. Using historical process recipe B can achieve process result b. Therefore, both historical process recipe A and historical process recipe B can be used as training data.

[0084] The training process for the network model constructed by the capsule network is the same as that for the neural network model. Both use pre-prepared training data to train the model, enabling it to accurately predict process parameters based on the process results. In some implementations, a dataset for training can be prepared in advance and then divided into 80% offline training data and 20% real-time testing data. This facilitates both model training and testing. During testing, parameters are adjusted based on the accuracy of the prediction results. If overfitting occurs in the loss function or gradient descent function, the network architecture and parameters are further adjusted to improve generalization ability. The final adjusted model is used to obtain the predicted process results.

[0085] In this embodiment, the training method of the neural network model can be used to train the network model constructed by the capsule network.

[0086] In some embodiments, during the model training process of the network model constructed by the capsule network using training data, the sum of the interval loss and the reconstruction loss is used as the model loss.

[0087] It should be noted that the interval loss can be determined as the sum of the interval losses of K classes. Specifically, , where ; represents the interval loss. represents the loss value of the prediction result of the k-th class; if the prediction result matches the label, it is 1, otherwise it is 0. Usually, it is taken as 0.5, , , representing the output of the k-th high-level capsule.

[0088] The reconstruction loss can be obtained by calculating the Euclidean distance between the prediction and the input. Therefore, in some implementations, when the intermediate interval loss is used as the dominant factor, the model loss is as follows: , where L represents the model loss, represents the interval loss, and represents the reconstruction loss.

[0089] In this embodiment, the sum of the interval loss and the reconstruction loss is used as the model loss, which can combine the advantages of the two loss functions and prevent overfitting.

[0090] In another embodiment of this application, the model is continuously adjusted and optimized during training using offline data, and the modified model is synchronized online in real time for real-time data processing. The data generated during real-time data processing is then used as offline training data to expand the training library, thereby improving the model's prediction accuracy. Specifically, as shown in Figure 5, this includes an offline data processing stage and a real-time data processing stage. The offline data processing stage includes: offline data training, adjusting the gradient optimization method and objective function, model parameter tuning, outputting the accuracy and analyzing it, and modifying the model based on the analysis. This yields an optimized model, which is then updated to the real-time data processing stage. The real-time data processing stage involves: real-time input of data, prediction of the real-time data, outputting the accuracy and analyzing it, and optimizing the model based on the results. Simultaneously, the generated data is synchronized to the offline training data to expand the training library.

[0091] The method for determining process parameters provided in this application will be described below with a specific example. As shown in Figure 6, the method is applied to a process equipment and specifically includes: Step S601: Inputting original process requirement data into the process equipment, wherein the original process requirement data is equivalent to the target process information in the aforementioned embodiments, which will not be described again here.

[0092] Step S602: Data processing. This is equivalent to the input layer of the aforementioned capsule network layer, where the original process requirement data is preprocessed.

[0093] Step S603: Using the capsule long short-term memory network model to predict the data after data processing, process parameters that meet the original process requirements can be obtained.

[0094] Step S604: Determine the process parameters output by the capsule long short-term memory network model as process parameters that can meet the original process requirements data.

[0095] It is understood that the application architecture of this embodiment, as shown in Figure 7, includes: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, a long short-term memory (LSTM) network layer, and an output layer. Alternatively, the application architecture of this embodiment can also be as shown in Figure 8, including: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, an attention module, an LSM network layer, and an output layer. The input layer is used to execute step S602. The convolutional layer, main capsule layer, digital capsule layer, attention module, and LSM network layer can be found in the descriptions of the convolutional layer, main capsule layer, digital capsule layer, attention module, and LSM network layer in the aforementioned embodiments. The output layer is composed of a softmax function. For a description of each part of this application architecture, please refer to the descriptions of the corresponding parts in the aforementioned embodiments; they will not be described again here.

[0096] In this embodiment, the efficiency of acquiring process parameters is improved. Process operators no longer need to manually try each parameter or guess its approximate range. It can also adapt to different inputs from different chambers to obtain different outputs, making it widely applicable. Furthermore, the capsule long short-term memory network, through its unique dynamic routing algorithm, can comprehensively obtain the characteristics of the process results, resulting in higher accuracy in prediction. Exemplary Device

[0097] Some embodiments of this application also provide a process parameter determination device, as shown in FIG9. The process parameter determination device includes: a response module 91, used to respond to target process information input by a user and input the target process information to a target network model; wherein, the target process information includes the process result that the process formulation to be determined can achieve; a model processing module 92, used to predict the process parameters required to achieve the process result by means of the target network model; wherein, the target network model includes: a capsule network layer constructed based on capsule network; and a determination module 93, used to determine the prediction result output by the target network model as the process parameters of the process formulation to be determined.

[0098] In some embodiments, the capsule network layer includes: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, and an output layer; the model processing module 92 includes: a preprocessing unit, used to preprocess the target process information through the input layer to generate input features; a first feature extraction unit, used to extract features from the input features through the convolutional layer to generate an initial feature vector; a second feature extraction unit, used to extract features from the initial feature vector through the main capsule layer to generate an initial capsule vector; a model processing unit, used to perform feature processing on the initial capsule vector through the digital capsule layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; and a model output unit, used to output the predicted value with the highest prediction probability for each process parameter based on the result capsule vector through the output layer.

[0099] In some embodiments, the second feature extraction unit is specifically used to extract features from the initial feature vector by means of the main capsule layer in a dynamic routing manner to generate the initial capsule vector.

[0100] In some embodiments, the apparatus further includes: a chamber determination module, used to determine the execution chamber based on target process information using a target network model, wherein the execution chamber is a chamber in the process equipment that executes the process recipe to be determined; and a quantity determination module, used to determine the number of process parameters corresponding to the execution chamber as a target quantity based on the correspondence between the number of chambers and the number of process parameters in the process equipment using the target network model.

[0101] In some embodiments, the target network model further includes: a long short-term memory network layer constructed based on a long short-term memory network, wherein the input of the long short-term memory network layer is the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

[0102] In some embodiments, the model processing module 92 is specifically used to: process the target process information through the capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; process the result capsule vectors through the forget gate, input gate, output gate and output layer of the long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0103] In some embodiments, the target network model further includes: a long short-term memory network layer constructed based on a long short-term memory network, and an attention module constructed based on an attention mechanism; wherein, the input of the attention module is target process information, the input of the long short-term memory network layer is the fusion result of the output of the attention module and the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

[0104] In some embodiments, the model processing module 92 is specifically used to: process the target process information through a capsule network layer to generate a target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; process the target process information through an attention module to generate a context vector corresponding to each result capsule vector; and process the fusion result of the result capsule vector and the context vector through the forget gate, input gate, output gate, and output layer of the long short-term memory network layer to obtain the process parameters required to achieve the process result.

[0105] In some embodiments, the device further includes: a model training module, used to: acquire training data; wherein the training data includes: historical process recipes and the process results that the historical process recipes can achieve; use the training data to train the network model constructed by the capsule network, and determine the trained network model as the target network model.

[0106] In some embodiments, during the model training process of the network model constructed by the capsule network using training data, the sum of the interval loss and the reconstruction loss is used as the model loss.

[0107] The process parameter determination apparatus provided in this application embodiment belongs to the same inventive concept as the process parameter determination method provided in the above-mentioned embodiments of this application. Technical details not described in detail in this embodiment can be found in the specific processing content of the process parameter determination method provided in the above-mentioned embodiments of this application, and will not be repeated here. Exemplary semiconductor process equipment and electronic equipment

[0108] Another embodiment of this application also proposes a semiconductor manufacturing process apparatus, including: a host computer and a slave computer connected to the host computer; the host computer is used to execute the process parameter determination method of various embodiments of this application to determine the process parameters of the process recipe to be determined, and send the process parameters of the process recipe to be determined to the slave computer; the slave computer is used to receive the process parameters of the process recipe to be determined, and perform process production according to the process parameters of the process recipe to be determined.

[0109] Another embodiment of this application also provides an electronic device. Referring to FIG10, an exemplary embodiment of this application also provides an electronic device, including: a memory and a processor. The memory stores a computer program. When the processor executes the computer program, it performs the steps in the method for determining process parameters according to various embodiments of this application described in the above embodiments.

[0110] The internal structure of the electronic device can be shown in FIG10. The electronic device includes a processor, memory, network interface, and input device connected via a system bus. The processor of the electronic device provides computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores an operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The network interface of the electronic device is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it follows the steps in the process parameter determination method according to various embodiments of this application described in the above embodiments.

[0111] The processor may include the main processor, as well as baseband chips, modems, etc.

[0112] The memory stores a computer program that executes the technical solution of this invention, and may also store an operating system and other key business functions. Specifically, the computer program may include program code, which includes computer operation instructions. More specifically, the memory may include read-only memory (ROM), other types of static storage devices capable of storing static information and instructions, random access memory (RAM), other types of dynamic storage devices capable of storing information and instructions, magnetic disk memory, flash memory, etc.

[0113] The processor can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits used to control the execution of the program of the present invention. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, or discrete hardware components.

[0114] Input devices may include devices that receive data and information input by the user, such as keyboards, mice, cameras, scanners, light pens, voice input devices, touch screens, pedometers, or gravity sensors.

[0115] Output devices may include devices that allow information to be output to users, such as display screens, printers, speakers, etc.

[0116] The communication interface may include a device such as any transceiver for communicating with other devices or communication networks, such as Ethernet, Radio Access Network (RAN), Wireless Local Area Network (WLAN), etc.

[0117] The processor executes the computer program stored in the memory and calls other devices, which can be used to implement the various steps of any of the process parameter determination methods provided in the above embodiments of this application.

[0118] The electronic device may also include a display component and a voice component. The display component may be a liquid crystal display screen or an electronic ink display screen. The input device of the electronic device may be a touch layer covering the display component, or a button, trackball or touchpad set on the casing of the electronic device, or an external keyboard, touchpad or mouse, etc.

[0119] Those skilled in the art will understand that the structure shown in FIG10 is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the electronic device to which the present application is applied. A specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have different component arrangements. Exemplary computer program products and computer-readable storage media

[0120] In addition to the methods and devices described above, the method for determining process parameters provided in the embodiments of this application can also be a computer program product, which includes a computer program. When the computer program is run by a processor, it causes the processor to execute the steps in the method for determining process parameters according to various embodiments of this application as described in the "Exemplary Methods" section above.

[0121] Computer program products can be written in any combination of one or more programming languages ​​to perform the operations of the embodiments of this application. The programming languages ​​include object-oriented programming languages ​​such as Java and C++, as well as conventional procedural programming languages ​​such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computing device, partially on the user's device, as a standalone software package, partially on the user's computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0122] In addition, embodiments of this application also provide a computer-readable storage medium having a computer program stored thereon, the computer program being executed by a processor of the steps in the method for determining process parameters according to various embodiments of this application as described in the "Exemplary Method" section above.

[0123] It is understood that the specific examples in this document are only intended to help those skilled in the art to better understand the implementation of this application, and are not intended to limit the scope of this application.

[0124] It is understood that in the various embodiments of this application, the order of the process numbers does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0125] It is understood that the various implementation methods described in this application can be implemented individually or in combination, and the implementation methods of this application are not limited in this respect.

[0126] Unless otherwise stated, all technical and scientific terms used in the embodiments of this application have the same meaning as commonly understood by one of ordinary skill in the art. The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to limit the scope of this application. The term "and / or" as used in this application includes any and all combinations of one or more of the associated listed items. The singular forms "a," "the," and "the" as used in the embodiments of this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0127] It is understood that the processor in the embodiments of this application can be an integrated circuit chip with signal processing capabilities. During implementation, each step of the above method embodiments can be completed by the integrated logic circuitry in the processor's hardware or by instructions in software form. The processor can be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly implemented by a hardware decoding processor, or implemented by a combination of hardware and software modules in the decoding processor. The software module can reside in mature storage media in the field, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically readable and writable programmable memory, and registers. This storage medium is located in memory, and the processor reads information from the memory and, in conjunction with its hardware, completes the steps of the above method.

[0128] It is understood that the memory in the embodiments of this application can be volatile memory or non-volatile memory, or may include both volatile and non-volatile memory. Non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. Volatile memory can be random access memory (RAM). It should be noted that the memory in the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0129] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0130] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices and units described above can be referred to the corresponding processes in the aforementioned method implementations, and will not be repeated here.

[0131] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is merely a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interface; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0132] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0133] In addition, each functional unit in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0134] If the aforementioned function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0135] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of protection of the claims. [Simplified Explanation of the Diagram]

[0028] Figure 1 is a flowchart of a conventional method for determining process parameters provided in one embodiment of this application; Figure 2 is a schematic flowchart of a method for determining process parameters provided in one embodiment of this application; Figure 3 is a schematic flowchart of dynamic routing in a capsule network in one embodiment of this application; Figure 4 is a network structure diagram of a long short-term memory network in one embodiment of this application; Figure 5 is a schematic flowchart of a method for determining process parameters provided in yet another embodiment of this application; Figure 6 is a flowchart of the actual application of a method for determining process parameters provided in one embodiment of this application; Figure 7 is one of the application architecture diagrams of a method for determining process parameters provided in one embodiment of this application; Figure 8 is another application architecture diagram of a method for determining process parameters provided in one embodiment of this application; Figure 9 is a structural schematic diagram of a process parameter determining device provided in one embodiment of this application; Figure 10 is a structural schematic diagram of an electronic device provided in one embodiment of this application.

Claims

1. A method for determining process parameters, comprising: In response to user-inputted target process information, the target process information is input into a target network model; wherein, the target process information includes the process result achievable by the process formulation to be determined; the target network model determines the execution chamber based on the target process information, wherein the execution chamber is a chamber in the process equipment that executes the process formulation to be determined; the target network model determines the number of process parameters corresponding to the execution chamber as the target number based on the correspondence between the number of chambers and the number of process parameters in the process equipment; the target network model predicts the process parameters required to achieve the process result; wherein, the target network model includes: a capsule network layer constructed based on capsule networks, the capsule network layer including: an input layer, a convolutional layer, a master capsule layer, a digital capsule layer, and an output layer; wherein, the prediction of the process parameters required to achieve the process result by the target network model includes: preprocessing the target process information through the input layer to generate input features; The convolutional layer extracts features from the input features to generate an initial feature vector; the main capsule layer extracts features from the initial feature vector to generate an initial capsule vector; the digital capsule layer processes the initial capsule vector to generate the target number of result capsule vectors; each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; the output layer outputs the predicted value with the highest prediction probability for each process parameter based on the result capsule vectors; the prediction result output by the target network model is determined as the process parameter of the process formulation to be determined.

2. The method as described in request item 1, wherein, The initial capsule vector is generated by extracting features from the initial feature vector through the main capsule layer, including: extracting features from the initial feature vector through the main capsule layer in a dynamic routing manner to generate the initial capsule vector.

3. The method as described in request item 1, wherein, The target network model also includes: a long short-term memory network layer constructed based on a long short-term memory network, wherein the input of the long short-term memory network layer is the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

4. The method as described in request item 3, wherein, The process parameters required to achieve the process result are predicted by the target network model, and the process parameters required to achieve the process result are obtained by processing the result capsule vector through the forget gate, input gate, output gate and output layer of the long short-term memory network layer.

5. The method as described in request item 1, wherein, The target network model also includes: a long short-term memory network layer constructed based on a long short-term memory network, and an attention module constructed based on an attention mechanism; wherein, the input of the attention module is the target process information, the input of the long short-term memory network layer is the fusion result of the output of the attention module and the output of the capsule network layer, and the output of the long short-term memory network layer is the output of the target network model.

6. The method as described in claim 5, wherein, The method of predicting the process parameters required to achieve the process result using the target network model further includes: processing the target process information using the attention module to generate a context vector corresponding to each result capsule vector; and processing the fusion result of the result capsule vector and the context vector using the forget gate, input gate, output gate, and output layer of the long short-term memory network to obtain the process parameters required to achieve the process result.

7. The method as described in request item 1, wherein, In response to user-inputted target process information, before inputting the target process information into the target network model, the method further includes: acquiring training data; wherein the training data includes: historical process recipes and the process results achievable by the historical process recipes; using the training data to train the network model constructed by the capsule network, and identifying the trained network model as the target network model.

8. The method as described in request item 7, wherein, During the training of the network model constructed using the training data, the sum of the interval loss and the reconstruction loss is used as the model loss.

9. A process parameter determination apparatus, comprising: The system comprises the following modules: a response module, used to respond to user-inputted target process information and input the target process information into the target network model; wherein the target process information includes the process result achievable by the process formulation to be determined; a chamber determination module, used to determine the execution chamber based on the target process information using the target network model, wherein the execution chamber is a chamber in the process equipment that executes the process formulation to be determined; a quantity determination module, used to determine the quantity of process parameters corresponding to the execution chamber as the target quantity based on the correspondence between the number of chambers and the number of process parameters in the process equipment using the target network model; and a model processing module, used to predict the process parameters required to achieve the process result using the target network model; wherein the target network model includes: a capsule network layer constructed based on capsule networks, the capsule network layer including: an input layer, a convolutional layer, a main capsule layer, a digital capsule layer, and an output layer; and the model processing module includes: a preprocessing unit, used to preprocess the target process information using the input layer to generate input features; The first feature extraction unit is used to extract features from the input features using the convolutional layer to generate an initial feature vector; the second feature extraction unit is used to extract features from the initial feature vector using the main capsule layer to generate an initial capsule vector; the model processing unit is used to process the initial capsule vector using the digital capsule layer to generate the target number of result capsule vectors; wherein each result capsule vector corresponds to a process parameter, and the result capsule vector includes multiple predicted values ​​of its corresponding process parameter and the prediction probability of each predicted value; the model output unit is used to output the predicted value with the highest prediction probability for each process parameter based on the result capsule vectors using the output layer; and the determination module is used to determine the prediction result output by the target network model as the process parameter of the process formulation to be determined.

10. A semiconductor manufacturing apparatus, comprising: A host computer and a slave computer connected to the host computer; The host computer is used to execute the process parameter determination method as described in any one of claims 1 to 8, to determine the process parameters of the process recipe to be determined, and to send the process parameters of the process recipe to be determined to the slave computer; the slave computer is used to receive the process parameters of the process recipe to be determined, and to perform process production according to the process parameters of the process recipe to be determined.

11. An electronic device comprising: A processor and a memory; wherein the memory is connected to the processor and is used to store a computer program; the processor is used to implement a method for determining process parameters as described in any one of claims 1 to 8 by running the computer program stored in the memory.

12. A computer-readable storage medium, wherein, The computer-readable storage medium contains a computer program that, when executed by a processor, implements the method for determining process parameters as described in any one of requests 1 to 8.

Images