Method and device for determining electrical technological parameters of semiconductor device

Abstract

The invention provides a method and device for determining electrical technological parameters of a semiconductor device, and belongs to the technical field of device manufacturing. The method for determining the electrical technological parameters of the semiconductor device comprises the following steps: obtaining device manufacturing technological parameters and current equipment state data; based on the device manufacturing process parameters, a preset process electrical correlation model is adopted to determine electrical parameters, and the preset process electrical correlation model is used for determining associated device electrical parameter information according to the device manufacturing process parameter information; based on the current equipment state data, a preset uncertainty model is adopted to determine the process electrical fluctuation range, and the preset uncertainty model is used for determining the influence of the equipment state on the process fluctuation according to the equipment state; and based on the electrical parameters and the electrical fluctuation range of the process, obtaining electrical process parameters of the device. The working efficiency is greatly improved, the determination process is simple and convenient, and repeated use can be achieved.

Description

Technical Field

[0001] The present invention relates to the technical field of device manufacturing, and in particular to a method for determining electrical process parameters of a semiconductor device, an apparatus for determining electrical process parameters of a semiconductor device, a machine-readable storage medium and an electronic device. Background Art

[0002] The manufacturing process of integrated circuits is precise and complex. The manufacturing process of devices requires hundreds of processes, and the parameter adjustment of each process will have more or less influence on the electrical properties of the final device. Therefore, in order to obtain a device with excellent electrical properties, it is necessary to continuously improve the process parameters and go through multiple rounds of iterative optimization.

[0003] Device electrical process parameters refer to a set of parameters used to describe the electrical performance and characteristics of devices during the semiconductor device manufacturing process. These parameters reflect the electrical performance of the device under different working conditions and are of great significance for evaluating device performance, optimizing process design, and adjusting device performance.

[0004] Currently, the electrical process parameters of a device are determined by adjusting the theoretical parameters. However, the parameter adjustment based on the theory often deviates from the expected results, which increases the number of experiments to continuously correct the results in order to obtain the final electrical process parameters of the device.

[0005] Therefore, the existing device electrical process parameter determination has the problem of complicated process and low efficiency. Summary of the invention

[0006] The purpose of the embodiments of the present invention is to provide a method for determining the electrical process parameters of a semiconductor device, a device for determining the electrical process parameters of a semiconductor device, a machine-readable storage medium and an electronic device. The method for determining the electrical process parameters of a semiconductor device can provide device electrical process parameters that can meet current process parameters, facilitate rapid determination of the device electrical process parameters, greatly improve work efficiency, and make the determination process simple and convenient.

[0007] In order to achieve the above-mentioned object, the first aspect of the present application provides a method for determining electrical process parameters of a semiconductor device, comprising:

[0008] Acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data are status data of equipment used in the current semiconductor device manufacturing process;

[0009] Based on the device manufacturing process parameters, a preset process electrical property related model is used to determine the electrical property parameter information of the associated device according to the device manufacturing process parameter information;

[0010] Based on the current equipment status data, a preset uncertainty model is used to determine the range of process electrical property fluctuations, wherein the preset uncertainty model is used to determine the impact of the equipment status on the process fluctuations according to the equipment status;

[0011] Based on the electrical parameters and the process electrical fluctuation range, device electrical process parameters are obtained, and the device electrical process parameters are used to describe the electrical performance and characteristics of the semiconductor device.

[0012] In the embodiment of the present application, the process of constructing the preset uncertainty model includes:

[0013] Acquire historical process fluctuation data of the device, wherein the historical process fluctuation data of the device includes multiple groups of fluctuation data, each group of fluctuation data includes: historical device status data and corresponding process fluctuation data;

[0014] Performing data mining on the historical process fluctuation data of the device to obtain a correlation relationship, wherein the correlation relationship is a correlation relationship between the device state and the process fluctuation;

[0015] Based on the correlation, an uncertainty envelope model is used to describe the impact of the equipment state on the device manufacturing process fluctuation, thereby obtaining an uncertainty model.

[0016] In the embodiment of the present application, the uncertainty envelope model is used to describe the influence of the equipment state on the fluctuation of the device manufacturing process, and the uncertainty model is obtained, including:

[0017] Based on the association relationship, an uncertainty set U is constructed;

[0018] The uncertainty envelope model is used to describe the range of the uncertain set U to obtain an uncertainty model. The uncertainty envelope model is: The linear programming problem is constructed as:

[0019] Where x∈R n×1 , c∈R n×1 , X represents the bounded feasible domain of decision variable x, is the coefficient matrix containing uncertain parameters on the left side of the constraint, To constrain the uncertainty parameter vector on the right side, R is the real number domain, m and n represent different dimensions, for The elements in for For the elements in the ith constraint, let and They are:

[0020]

[0021] Among them, a ij and b i are the nominal parts of the uncertain parameters, which are the device status data. and are the floating amplitudes respectively, and are obtained from the above relationship, ξ ij With ξ i0 is the unit variable of fluctuation, J i is the set of parameters affected by uncertainty in the i-th constraint, and They respectively represent the upper and lower limit fluctuation ranges of the i-th constraint, that is, the impact of the equipment status on the process fluctuation.

[0022] In the embodiment of the present application, the current device status data is based on the preset uncertainty model to determine the process electrical property fluctuation range, including:

[0023] Based on the current device state data, a preset uncertainty model is used to determine a range description of the uncertainty set of the current device;

[0024] Based on the range description of the uncertainty set of the current device, determine the corresponding upper and lower limit fluctuation range of the constraint;

[0025] Based on the corresponding upper and lower limit fluctuation ranges of the constraints, the process electrical property fluctuation range is obtained.

[0026] In the embodiment of the present application, data mining is performed on the historical process fluctuation data of the device to obtain the correlation relationship, including:

[0027] The XGBoost algorithm is used to perform data mining on the historical process fluctuation data of the device to obtain the correlation relationship.

[0028] In the embodiment of the present application, the process of constructing the preset process electrical property related model includes:

[0029] Acquire multiple sample data, each sample data includes sample process parameters and corresponding device basic parameters;

[0030] Based on the multiple sample data, a deep learning algorithm is used to perform model training to obtain a process electrical property related model.

[0031] In the embodiment of the present application, the step of obtaining a plurality of sample data includes:

[0032] Acquire device historical data, wherein the device historical data includes one or more of device historical simulation data, device historical DOE data, and device historical electrical performance data;

[0033] Feature extraction is performed on the device historical data to obtain a plurality of sample data.

[0034] In the embodiment of the present application, it also includes:

[0035] Based on the device manufacturing process parameters, a preset simulation system is used to perform simulation to obtain device electrical simulation parameters;

[0036] The device electrical simulation parameters are compared with the device electrical process parameters to obtain a comparison result.

[0037] A second aspect of the present application provides a device for determining electrical process parameters of a semiconductor device, comprising:

[0038] An acquisition module, used to acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data are status data of equipment used in the current semiconductor device manufacturing process;

[0039] A parameter calculation module, used to determine electrical parameters based on the device manufacturing process parameters using a preset process electrical property related model, wherein the preset process electrical property related model is used to determine associated device electrical property parameter information based on the device manufacturing process parameter information;

[0040] A fluctuation calculation module, used to determine the range of process electrical property fluctuations based on the current equipment state data and using a preset uncertainty model, wherein the preset uncertainty model is used to determine the impact of the equipment state on the process fluctuations according to the equipment state;

[0041] The determination module is used to obtain device electrical process parameters based on the electrical parameters and the process electrical fluctuation range, wherein the device electrical process parameters are used to describe the electrical performance and characteristics of the semiconductor device.

[0042] A third aspect of the present application provides an electronic device, the electronic device comprising:

[0043] at least one processor;

[0044] a memory connected to the at least one processor;

[0045] The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the above-mentioned method for determining electrical process parameters of a semiconductor device by executing the instructions stored in the memory.

[0046] A fourth aspect of the present application provides a machine-readable storage medium having instructions stored thereon, which, when executed by a processor, configures the processor to execute the above-mentioned method for determining electrical process parameters of a semiconductor device.

[0047] Through the above technical scheme, by obtaining the device manufacturing process parameters and the current equipment status data; based on the device manufacturing process parameters, using the preset process electrical related model to determine the electrical parameters, the preset process electrical related model is used to determine the associated device electrical parameter information according to the process parameter information; based on the current equipment status data, using the preset uncertainty model to determine the process electrical fluctuation range, the preset uncertainty model is used to determine the impact of the equipment state on the process fluctuation according to the equipment state; based on the electrical parameters and the process electrical fluctuation range, the device electrical process parameters are obtained. The volatility of the process parameters can be obtained through the device manufacturing process parameters and the current equipment status data, and the device electrical process parameters that can meet the current process parameters are provided, which is convenient for quickly determining the device electrical process parameters. Compared with the existing scheme of increasing the number of experiments to adjust the parameters, the work efficiency is greatly improved, and the determination process is simple and convenient. At the same time, based on the current equipment status data, the process electrical fluctuation range is determined, which is obtained by considering the uncertainty factors brought by the equipment in the key manufacturing process. Therefore, the obtained device electrical process parameters are more accurate and reusable. The device electrical parameter information is obtained through the device manufacturing process parameters, so that the device electrical properties can be estimated based on the process parameters, which is helpful for the research and development and design of the device.

[0048] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the embodiments of the present invention, but do not constitute a limitation on the embodiments of the present invention. In the accompanying drawings:

[0050] Figure 1 A schematic diagram of a process flow of a method for determining electrical process parameters of a semiconductor device according to an embodiment of the present application is shown;

[0051] Figure 2 A schematic diagram of the steps for generating electrical process parameters of a semiconductor device according to an embodiment of the present application is shown schematically;

[0052] Figure 3 A schematic diagram of the structure of a device for determining electrical process parameters of a semiconductor device according to an embodiment of the present application is shown;

[0053] Figure 4 The internal structure diagram of a computer device according to an embodiment of the present application is schematically shown.

[0054] Description of Reference Numerals

[0055] 410 - acquisition module; 420 - parameter calculation module; 430 - fluctuation calculation module; 440 - determination module; A01 - processor; A02 - network interface; A03 - internal memory; A04 - display screen; A05 - input device; A06 - non-volatile storage medium; B01 - operating system; B02 - computer program. DETAILED DESCRIPTION

[0056] The specific implementation of the embodiment of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the embodiment of the present invention, and is not used to limit the embodiment of the present invention.

[0057] It should be noted that if the embodiments of the present application involve directional indications (such as up, down, left, right, front, back...), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0058] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present application, the descriptions of "first", "second", etc. are only used for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In addition, the technical solutions between the various embodiments can be combined with each other, but they must be based on the ability of ordinary technicians in the field to implement them. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0059] It should be noted that the equipment mentioned in this embodiment refers to the equipment used in the process involved in manufacturing the device.

[0060] Please see Figure 1 , Figure 1 The following is a schematic flow chart of a method for determining electrical process parameters of a semiconductor device according to an embodiment of the present application. This embodiment provides a method for determining electrical process parameters of a semiconductor device, comprising the following steps:

[0061] Step 210: Acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data are status data of equipment used in the current semiconductor device manufacturing process;

[0062] In this embodiment, the above-mentioned device manufacturing process parameters can be obtained from a device design of experiments (DOE) document or a device DOE table. Device DOE is a technology that uses experimental design methods to help optimize device performance and process parameters during the design and manufacturing of semiconductor devices. Through device DOE, a series of experiments can be designed to systematically study the effects of different influencing factors on device performance, such as material selection, process conditions, dimensional parameters, etc. Through statistical analysis and experimental data, it can be determined which factors play an important role in device performance and how to adjust these factors to achieve optimal performance.

[0063] The above-mentioned device manufacturing process parameters refer to various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, including key process parameters in the device manufacturing process, such as: ion implantation energy, metering, angle, or heating process parameters. The above-mentioned current equipment status data refers to the status data of the equipment used in the current semiconductor device manufacturing process. The equipment status data refers to the data that records the various parameters and status information of the process equipment in the production process to monitor and control the equipment operation status and ensure the normal operation of the production process. These data may include the numerical values ​​of various physical quantities such as the equipment's operating time, temperature, pressure, speed, current, voltage, and related information such as the equipment's fault information, alarm information, and maintenance records. By analyzing these data, it is possible to timely discover equipment operation anomalies, predict equipment failures, optimize production parameters, and improve production efficiency and product quality. The acquisition of the above-mentioned current equipment status data can be obtained by real-time collection from various devices, or it can be directly entered by personnel.

[0064] Step 220: Based on the device manufacturing process parameters, a preset process electrical property related model is used to determine electrical property parameters of the device, wherein the preset process electrical property related model is used to determine the associated device electrical property parameter information according to the device manufacturing process parameter information;

[0065] In this embodiment, the above-mentioned preset process electrical property related model is pre-established. For each type of device, a corresponding process electrical property related model is established. In specific implementation, the corresponding process electrical property related model can be selected according to the type of device to be manufactured. For example, CMOS devices correspond to process electrical property related models of CMOS devices, and optoelectronic devices correspond to process electrical property related models of optoelectronic devices. The above-mentioned process electrical property related model is a model that can infer device performance through process, and can be obtained by model training using a deep learning algorithm.

[0066] In some embodiments, in order to obtain an accurate process electrical property related model, the construction process of the preset process electrical property related model includes the following steps:

[0067] First, a plurality of sample data are obtained, each sample data including a sample process parameter and a corresponding device basic parameter;

[0068] In this embodiment, the sample data refers to sample data for the device, the sample process parameters refer to key process parameters in the device manufacturing process, and the basic device parameters refer to the corresponding device performance parameters under the key process parameters, such as saturation threshold voltage, linear threshold voltage, saturation current, leakage current, etc. The number of the sample data is not limited, and the more samples there are, the more accurate they are, and the better the performance of the process electrical property related model obtained by training.

[0069] In order to obtain more and more accurate sample data, the step of obtaining multiple sample data includes:

[0070] The first step is to obtain device historical data, wherein the device historical data includes one or more of device historical simulation data, device historical DOE data and device historical electrical performance data;

[0071] In this embodiment, the above-mentioned device history DOE data can be obtained from the device history DOE document, the device history simulation data can be obtained from the simulation system, and the device history electrical performance data can be obtained from the wafer acceptance test (WAT) test. WAT is used to detect the quality and performance of wafers during the manufacturing process, including electrical testing: testing the electrical properties on the wafer, such as resistance, capacitance and other parameters. Optical testing: checking the graphics, patterns and defects on the wafer. Feature testing: testing the performance and function of the devices on the wafer. Comprehensive testing: comprehensive testing of various performance indicators of the wafer to ensure that the quality of the wafer meets production requirements.

[0072] The second step is to extract features from the device historical data to obtain multiple sample data.

[0073] In this embodiment, the feature extraction mentioned above refers to extracting process parameters and corresponding basic device parameters. The feature extraction mentioned above can be achieved by using existing technologies, which will not be described in detail here.

[0074] By extracting features from historical device data, including historical device simulation data, historical device DOE data, or historical device electrical performance data, more accurate sample data can be obtained, which helps to train a process electrical performance-related model with better performance.

[0075] Then, based on the multiple sample data, a deep learning algorithm is used to perform model training to obtain a process electrical property related model.

[0076] In this embodiment, the deep learning algorithm includes a deep neural network algorithm, a convolutional neural network algorithm, etc., which realizes the learning and recognition of complex patterns and relationships through multi-level nonlinear transformation and feature extraction. The model is trained through multiple sample data so that the model can determine the associated device electrical parameter information based on the process parameter information.

[0077] In specific implementation, a fully connected network can be used to build a model, and the output is the basic parameters of the device, such as the saturation threshold voltage Vtsat, the linear threshold voltage Vtlin, the saturation current Idsat, the leakage current Ioff, etc. The network input is some key process parameters in the device manufacturing process, that is, the device manufacturing process parameters, such as the energy, metering, angle of ion implantation, or heating process parameters. The network includes an input layer, a hidden layer, and an output layer. The nodes between each layer are fully connected. Through training with large batches of sample data, a neural network model that can infer the device performance through the process is finally trained. The above-mentioned process of training using a fully connected network belongs to the prior art and will not be repeated here.

[0078] Deep learning algorithms can process large-scale, high-dimensional data and solve complex pattern recognition and decision-making problems. By using deep learning algorithms for model training, more accurate process electrical property related models can be obtained.

[0079] Step 230: Based on the current equipment state data, a preset uncertainty model is used to determine the range of process electrical property fluctuations, wherein the preset uncertainty model is used to determine the impact of the equipment state on the process fluctuations according to the equipment state;

[0080] In this embodiment, the above-mentioned preset uncertainty model can be pre-established, and for each type of device, a corresponding uncertainty model is established. In specific implementation, the corresponding uncertainty model can be selected according to the type of device to be manufactured. The uncertainty model is used to determine the impact of the device state on the process fluctuation.

[0081] In some embodiments, in order to accurately describe the impact of equipment status on process fluctuations, the construction process of the preset uncertainty model includes:

[0082] First, historical process fluctuation data of the device is obtained, wherein the historical process fluctuation data of the device includes multiple groups of fluctuation data, and each group of fluctuation data includes: historical equipment status data and corresponding process fluctuation data;

[0083] In this embodiment, the above-mentioned device historical process fluctuation data includes the fluctuation data when the process parameters fluctuate during the historical manufacturing process of the device and the equipment status that causes the process fluctuation. For example: the fluctuation data is: from the perspective of time, a certain device has been in the factory for x years, has been in high-intensity operation for y years, has been in operation without maintenance for z years recently, and the device has had a number of unwarned failures in the factory in history, which are the equipment status; then the historical fluctuations in the process are affected by these equipment statuses (x, y, z, a). The above-mentioned device historical process fluctuation data can be obtained from the Manufacturing Execution System (MES), which is a software system used to monitor and manage various links in the manufacturing process, which helps to monitor the production process in real time, collect and analyze production data, coordinate production plans, optimize resource utilization, etc., so as to improve production efficiency, reduce production costs, and ensure product quality and compliance with regulatory requirements.

[0084] Then, data mining is performed on the historical process fluctuation data of the device to obtain a correlation relationship, where the correlation relationship is a correlation relationship between the device state and the process fluctuation;

[0085] In this embodiment, the above-mentioned data mining is to discover the potential laws, trends and patterns hidden in a large amount of data by analyzing the data, so as to find the correlation between process fluctuation data and uncertainty data. The uncertainty data here refers to the equipment status data. Data mining can be carried out by using an optimized distributed gradient boosting library (XGBoost) algorithm, a random forest algorithm, etc.

[0086] In some embodiments, performing data mining on the historical process fluctuation data of the device to obtain the correlation relationship includes: performing data mining on the historical process fluctuation data of the device using an XGBoost algorithm to obtain the correlation relationship.

[0087] In this embodiment, in order to quickly obtain the accurate correlation between equipment status and process fluctuations, the XGBoost algorithm can be used for data mining. The XGBoost algorithm is an integrated learning algorithm based on a decision tree, which has high efficiency and accuracy, so that accurate management relationships can be quickly obtained.

[0088] In the specific implementation, some initial parameters are set first, including learning rate, number of trees, etc., and then iterative training is performed according to the device historical process fluctuation data and the objective function to gradually optimize the model parameters. The residual is fitted by calculating the first-order derivative and second-order derivative (Hessian matrix) of the loss function of each sample. Therefore, for the split of each tree node, the optimal split is made based on the gradient of its loss function and the Hessian matrix. The greedy algorithm is used to grow the tree, that is, the optimal split point is recursively selected from top to bottom to minimize the loss function. Through the greedy algorithm, XGBoost can efficiently build a tree model. In XGBoost, each leaf node predicts a value, which represents the predicted value corresponding to the leaf node, and the final prediction result is obtained by summing the leaf nodes. XGBoost repeatedly builds trees by iteratively, training a new tree model each time according to the residual, and weightedly adding the prediction results of each tree, and finally obtaining a learner. With this learner, the historical process fluctuation data of the device can be regressed to mine and fit the correlation between uncertainty data, that is, the correlation between uncertainty data and process fluctuation. It should be noted that the above process of data mining using the XGBoost algorithm belongs to the existing technology and will not be described in detail here.

[0089] Finally, based on the correlation, an uncertainty envelope model is used to describe the impact of equipment status on process fluctuations to obtain an uncertainty model.

[0090] In this embodiment, after obtaining the correlation relationship, in order to describe the impact of the equipment state on the process fluctuation, the uncertainty envelope model can be used for modeling. The uncertainty envelope model is a modeling method for processing data with uncertainty information. In the uncertainty envelope model, each data point of the data set is represented as an envelope rather than a definite point. The uncertainty of this data can come from measurement errors, ambiguity or other uncertain factors.

[0091] Specifically, through data mining, an association relationship is obtained, where the association relationship is an association relationship between equipment status and process fluctuations, and based on the association relationship, an uncertainty set U is constructed.

[0092] Then, the uncertainty envelope model is used to describe the range of the uncertainty set U to obtain the uncertainty model. The uncertainty envelope model is: The constructed assumed linear programming problem is:

[0093] Where x∈R n×1 , c∈R n×1 , X represents the bounded feasible domain of decision variable x, is the coefficient matrix containing uncertain parameters on the left side of the constraint, is the uncertainty parameter vector constraining the right side; R is the real number domain, and m and n represent different dimensions respectively.

[0094] For any of the constraints, such as the i-th constraint, for The elements in for The elements in and They are:

[0095]

[0096] Among them, a ij and b i They are the nominal parts of the uncertain parameters, where the uncertainty parameters refer to the equipment status data. and are the floating ranges, which are used to conveniently express the upper and lower fluctuation ranges in a unified manner, and the upper and lower limit fluctuation ranges can be obtained through the correlation relationship, ξ ij With ξ i0 The unit variable of the fluctuation can be set in advance. When constructing the paradigm, it is necessary to use an amplitude to express the upper and lower limit fluctuation range through the unit variable. i is the set of parameters affected by uncertainty in the i-th constraint, where and They respectively represent the fluctuation range of the upper and lower limits of any constraint, that is, the impact of the equipment status on the process fluctuation.

[0097] Based on the above content, we can construct a mathematical representation of the uncertainty set through different norms according to the actual fluctuations of the equipment. Specifically, we can construct an uncertainty set and construct a range description of the uncertainty set according to different norms. For example, we can use a mathematical representation of the uncertainty set with a box-shaped geometry type, that is, by setting the adjustable parameter Ψ as the upper limit, so that all the unit variables ξ of the fluctuations ij All of them do not exceed Ψ; we can also use the uncertainty set mathematical expression with the uncertainty set geometry type as ellipsoid, that is, by setting the adjustable parameter Ω as the upper limit, so that all ξ ij The sum of the squares does not exceed Ω 2 ; A polyhedron can also be constructed. Specifically, the most appropriate situation in the mathematical representation of the uncertainty set can be selected according to the characteristics of the uncertainty set to construct the upper and lower limits, and the range needs to be appropriately adjusted according to the robustness requirements to accommodate more low-frequency points.

[0098] The uncertainty set of key equipment is constructed through the historical process fluctuation data of the device to determine the upper and lower limits of the device impact within an acceptable range. The multidimensional uncertainty set is described by the envelope method, and the uncertainty of each device is statistically analyzed through data mining. In this way, the upper and lower limits of the impact of each device can be mapped to the impact on the electrical properties of the device and the total impact can be statistically calculated.

[0099] In some embodiments, the determining of the process electrical property fluctuation range based on the current device status data using a preset uncertainty model comprises the following steps:

[0100] Firstly, based on the current device state data, a preset uncertainty model is used to determine a range description of the uncertainty set of the current device;

[0101] In this embodiment, the preset uncertainty model describes the range of the correlation between the equipment status data and the process fluctuation. Therefore, by substituting the current equipment status data, the range description of the uncertainty set of the current equipment can be obtained, that is, the range description of the current equipment status data.

[0102] Then, based on the range description of the uncertainty set of the current device, the corresponding upper and lower limit fluctuation range of the constraint is determined;

[0103] Finally, based on the corresponding upper and lower limit fluctuation ranges of the constraints, the process electrical property fluctuation range is obtained.

[0104] In this embodiment, the influence of the current equipment state on the process fluctuation is described by constructing a range of uncertainty sets based on different norms, so the corresponding norm is the process electrical property fluctuation range. By reading the current equipment state data, the uncertainty set of the current equipment can be obtained, and the corresponding norm is determined based on this, that is, the corresponding upper and lower limit fluctuation range of the constraint is obtained, so as to obtain the upper and lower fluctuation percentages of the electrical property, that is, the process electrical property fluctuation range.

[0105] Step 240: Obtain device electrical process parameters based on the electrical parameters and the process electrical fluctuation range.

[0106] In this embodiment, the electrical process parameters of the device are obtained by taking the process electrical fluctuation range as the fluctuation range of the electrical parameters. For example, the electrical parameters include V1 and V2, and the process electrical fluctuation range is the upper and lower percentage of the electrical fluctuation, for example, it can be expressed as ±10%. Based on the electrical parameters and the process electrical fluctuation range, the device electrical process parameters can be obtained as V1±10% and V2±10%.

[0107] In the above implementation process, by obtaining the device manufacturing process parameters and the current equipment status data; based on the device manufacturing process parameters, using the preset process electrical related model to determine the electrical parameters, the preset process electrical related model is used to determine the associated device electrical parameter information according to the process parameter information; based on the current equipment status data, using the preset uncertainty model to determine the process electrical fluctuation range, the preset uncertainty model is used to determine the impact of the equipment state on the process fluctuation according to the equipment state; based on the electrical parameters and the process electrical fluctuation range, the device electrical process parameters are obtained. The volatility of the process parameters can be obtained through the device manufacturing process parameters and the current equipment status data, and the device electrical process parameters that can meet the current process parameters are provided, which is convenient for quickly determining the device electrical process parameters. Compared with the existing solution of increasing the number of experiments to adjust the parameters, the work efficiency is greatly improved, and the determination process is simple and convenient. At the same time, based on the current equipment status data, the process electrical fluctuation range is determined, which takes into account the uncertainty factors brought by the equipment in the key manufacturing process. Therefore, the obtained device electrical process parameters are more accurate and reusable. The device electrical parameter information is obtained through the device manufacturing process parameters, so that the device electrical properties can be estimated based on the process parameters, which is helpful for the research and development and design of the device.

[0108] In some embodiments, the following steps are also included:

[0109] Firstly, based on the manufacturing process parameters of the device, a preset simulation system is used to perform simulation to obtain device electrical simulation parameters;

[0110] In this embodiment, the simulation system can be used to perform simulation to obtain device electrical simulation parameters based on device manufacturing process parameters. Other device performance can also be evaluated through the simulation system. The above simulation coefficients belong to the prior art and will not be described in detail here.

[0111] Then, the device electrical simulation parameters are compared with the device electrical process parameters to obtain a comparison result.

[0112] In this embodiment, by comparing the device electrical simulation parameters with the device electrical process parameters, the comparison results may be the same or different. If they are the same, it means that the device electrical process parameters obtained by adopting this solution are correct. Otherwise, further evaluation can be performed.

[0113] By comparing the above device electrical simulation parameters with the device electrical process parameters, the accuracy of the device electrical process parameters can be evaluated, thereby ensuring the reliability of the device electrical process parameters.

[0114] In order to facilitate the explanation of the solution, the following is a detailed description of the process of determining the electrical process parameters of a CMOS device. Figure 2 , Figure 2 A schematic diagram of the steps for generating electrical process parameters of a semiconductor device according to an embodiment of the present application is schematically shown.

[0115] Relevant data are extracted from DOE documents, simulation systems, WAT and MES systems through data acquisition modules and stored in the database. The relevant data include device DOE historical data, historical simulation data, electrical performance historical data and process engineering fluctuation historical data. The device DOE historical data, historical simulation data and electrical performance historical data are combined to construct a process-electrical correlation model through empirical calculation and DNN deep learning methods, which corresponds to the process-electrical correlation integration module. The uncertainty set is constructed by describing the process engineering fluctuation historical data using envelope models and data mining; this part corresponds to the uncertainty model establishment module. The above two models are integrated to obtain a device electrical fluctuation calculation module to obtain a device electrical process parameter generation device. The device electrical process reference parameters can be obtained by inputting the device DOE table and the equipment status into the device electrical process parameter generation device. At the same time, the device DOE table can also be input into the simulation system for simulation, and the simulation results can be input into the device electrical process parameter generation device for comparison.

[0116] This embodiment provides a device for determining electrical process parameters of a semiconductor device. Figure 3 , Figure 3 The schematic diagram of the structure of a semiconductor device electrical process parameter determination device according to an embodiment of the present application is schematically shown. The semiconductor device electrical process parameter determination device includes an acquisition module 410, a parameter calculation module 420, a fluctuation calculation module 430 and a determination module 440, wherein:

[0117] An acquisition module 410 is used to acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data is the status data of the equipment used in the current semiconductor device manufacturing process;

[0118] A parameter calculation module 420, configured to determine electrical parameters based on the device manufacturing process parameters using a preset process electrical property related model, wherein the preset process electrical property related model is configured to determine associated device electrical property parameter information based on the device manufacturing process parameter information;

[0119] The fluctuation calculation module 430 is used to determine the process electrical property fluctuation range based on the current device state data by using a preset uncertainty model, wherein the preset uncertainty model is used to determine the influence of the device state on the process fluctuation according to the device state;

[0120] The determination module 440 is used to obtain device electrical process parameters based on the electrical parameters and the process electrical fluctuation range, where the device electrical process parameters are used to describe the electrical performance and characteristics of the semiconductor device.

[0121] The device for determining the electrical process parameters of the device includes a processor and a memory. The acquisition module 410, parameter calculation module 420, fluctuation calculation module 430 and determination module 440 are all stored in the memory as program units, and the processor executes the program units stored in the memory to implement corresponding functions.

[0122] The processor includes a kernel, which calls the corresponding program unit from the memory. One or more kernels can be set, and the electrical process parameters of the device can be quickly determined by adjusting the kernel parameters.

[0123] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM, and the memory includes at least one memory chip.

[0124] An embodiment of the present invention provides a machine-readable storage medium on which a program is stored. When the program is executed by a processor, the method for determining electrical process parameters of a semiconductor device is implemented.

[0125] An embodiment of the present invention provides a processor, which is used to run a program, wherein the method for determining electrical process parameters of a semiconductor device is executed when the program is run.

[0126] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 4As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, a method for determining electrical process parameters of a semiconductor device is implemented. The display screen A04 of the computer device can be a liquid crystal display or an electronic ink display, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0127] Those skilled in the art will understand that Figure 4 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0128] In one embodiment, the device electrical process parameter determination apparatus provided in the present application can be implemented in the form of a computer program. The computer program can be Figure 4 The computer device shown in the figure is run. The memory of the computer device can store various program modules constituting the device for determining the electrical process parameters of the device, for example, Figure 3 The acquisition module 410, parameter calculation module 420, fluctuation calculation module 430 and determination module 440 are shown. The computer program composed of various program modules enables the processor to execute the steps in the calling method of the file system of each embodiment of the present application described in this specification.

[0129] Figure 4 The computer device shown can be Figure 3 In the device electrical process parameter determination apparatus shown, the acquisition module 410 executes step 210 , the parameter calculation module 420 executes step 220 , the fluctuation calculation module 430 executes step 230 , and the determination module 440 executes step 240 .

[0130] The embodiment of the present application provides a device, which includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the following steps are implemented:

[0131] Acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data are status data of equipment used in the current semiconductor device manufacturing process;

[0132] Based on the device manufacturing process parameters, a preset process electrical property related model is used to determine the electrical property parameters of the device according to the process parameter information;

[0133] Based on the current equipment status data, a preset uncertainty model is used to determine the range of process electrical property fluctuations, wherein the preset uncertainty model is used to determine the impact of the equipment status on the process fluctuations according to the equipment status;

[0134] Based on the electrical parameters and the process electrical fluctuation range, device electrical process parameters are obtained, and the device electrical process parameters are used to describe the electrical performance and characteristics of the semiconductor device.

[0135] In one embodiment, the process of constructing the preset uncertainty model includes:

[0136] Acquire historical process fluctuation data of the device, wherein the historical process fluctuation data of the device includes multiple groups of fluctuation data, each group of fluctuation data includes: historical device status data and corresponding process fluctuation data;

[0137] Performing data mining on the historical process fluctuation data of the device to obtain a correlation relationship, wherein the correlation relationship is a correlation relationship between the device state and the process fluctuation;

[0138] Based on the correlation, an uncertainty envelope model is used to describe the impact of the equipment state on the device manufacturing process fluctuation, thereby obtaining an uncertainty model.

[0139] In one embodiment, based on the association relationship, an uncertainty envelope model is used to describe the influence of the equipment state on the device manufacturing process fluctuation, and the uncertainty model is obtained, including:

[0140] Based on the association relationship, an uncertainty set U is constructed;

[0141] The uncertainty set U is described by using the uncertainty envelope model to obtain the uncertainty model. The uncertainty envelope model is: The construction linear programming problem is:

[0142] Where x∈R n×1 , c∈R n×1, X represents the bounded feasible domain of decision variable x, is the coefficient matrix containing uncertain parameters on the left side of the constraint, To constrain the uncertainty parameter vector on the right side, R is the real number domain, m and n represent different dimensions, for The elements in for For the elements in the ith constraint, let and They are:

[0143]

[0144] Among them, a ij and b i are the nominal parts of the uncertain parameters, which are the device status data. and are the floating amplitudes respectively, and are obtained from the above relationship, ξ ij With ξ i0 is the unit variable of fluctuation, J i is the set of parameters affected by uncertainty in the i-th constraint, and They respectively represent the upper and lower limit fluctuation ranges of the i-th constraint, that is, the impact of the equipment status on the process fluctuation.

[0145] In one embodiment, the determining of the process electrical property fluctuation range based on the current equipment status data using a preset uncertainty model includes:

[0146] Based on the current device state data, a preset uncertainty model is used to determine a range description of the uncertainty set of the current device;

[0147] Based on the range description of the uncertainty set of the current device, determine the corresponding upper and lower limit fluctuation range of the constraint;

[0148] Based on the corresponding upper and lower limit fluctuation ranges of the constraints, the process electrical property fluctuation range is obtained.

[0149] In one embodiment, the data mining of the historical process fluctuation data of the device to obtain the correlation relationship includes:

[0150] The XGBoost algorithm is used to perform data mining on the historical process fluctuation data of the device to obtain the correlation relationship.

[0151] In one embodiment, the process of constructing the preset process electrical property related model includes:

[0152] Acquire multiple sample data, each sample data includes sample process parameters and corresponding device basic parameters;

[0153] Based on the multiple sample data, a deep learning algorithm is used to perform model training to obtain a process electrical property related model.

[0154] In one embodiment, the obtaining of a plurality of sample data includes:

[0155] Acquire device historical data, wherein the device historical data includes one or more of device historical simulation data, device historical DOE data, and device historical electrical performance data;

[0156] Feature extraction is performed on the device historical data to obtain a plurality of sample data.

[0157] In one embodiment, it further includes:

[0158] Based on the device manufacturing process parameters, a preset simulation system is used to perform simulation to obtain device electrical simulation parameters;

[0159] The device electrical simulation parameters are compared with the device electrical process parameters to obtain a comparison result.

[0160] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0161] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0162] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0163] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0164] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0165] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0166] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0167] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0168] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A method for determining electrical process parameters of a semiconductor device, It is characterized in that include: Acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data are status data of equipment used in the current semiconductor device manufacturing process; Based on the device manufacturing process parameters, a preset process electrical property related model is used to determine the electrical property parameter information of the associated device according to the device manufacturing process parameter information; Based on the current equipment status data, a preset uncertainty model is used to determine the range of process electrical property fluctuations, wherein the preset uncertainty model is used to determine the impact of the equipment status on the process fluctuations according to the equipment status; Based on the electrical parameters and the process electrical fluctuation range, device electrical process parameters are obtained, and the device electrical process parameters are used to describe the electrical performance and characteristics of the semiconductor device.

2. The method for determining electrical process parameters of a semiconductor device according to claim 1, It is characterized in that The construction process of the preset uncertainty model includes: Acquire historical process fluctuation data of the device, wherein the historical process fluctuation data of the device includes multiple groups of fluctuation data, each group of fluctuation data includes: historical device status data and corresponding process fluctuation data; Performing data mining on the historical process fluctuation data of the device to obtain a correlation relationship, wherein the correlation relationship is a correlation relationship between the device state and the process fluctuation; Based on the correlation, an uncertainty envelope model is used to describe the impact of the equipment state on the device manufacturing process fluctuation, thereby obtaining an uncertainty model.

3. The method for determining electrical process parameters of a semiconductor device according to claim 2, It is characterized in that Based on the association relationship, an uncertainty envelope model is used to describe the influence of the equipment state on the device manufacturing process fluctuation, and an uncertainty model is obtained, including: Based on the association relationship, an uncertainty set U is constructed; The uncertainty envelope model is used to describe the range of the uncertain set U to obtain an uncertainty model. The uncertainty envelope model is: The linear programming problem is constructed as: Where x∈R n×1 , c∈R n×1 , X represents the bounded feasible domain of decision variable x, is the coefficient matrix containing uncertain parameters on the left side of the constraint, To constrain the uncertainty parameter vector on the right side, R is the real number domain, m and n represent different dimensions, for The elements in for For the elements in the ith constraint, let and They are: Among them, a ij and b i are the nominal parts of the uncertain parameters, which are the device status data. and are the floating amplitudes respectively, and are obtained from the above relationship, ξ ij With ξ i0 is the unit variable of fluctuation, J i is the set of parameters affected by uncertainty in the i-th constraint, and They respectively represent the upper and lower limit fluctuation ranges of the i-th constraint, that is, the impact of the equipment status on the process fluctuation.

4. The method for determining electrical process parameters of a semiconductor device according to claim 3, It is characterized in that The determining of the process electrical property fluctuation range based on the current equipment status data and using a preset uncertainty model includes: Based on the current device state data, a preset uncertainty model is used to determine a range description of the uncertainty set of the current device; Based on the range description of the uncertainty set of the current device, determine the corresponding upper and lower limit fluctuation range of the constraint; Based on the corresponding upper and lower limit fluctuation ranges of the constraints, the process electrical property fluctuation range is obtained.

5. The method for determining electrical process parameters of a semiconductor device according to claim 2, It is characterized in that The data mining of the historical process fluctuation data of the device to obtain the correlation relationship includes: The XGBoost algorithm is used to perform data mining on the historical process fluctuation data of the device to obtain the correlation relationship.

6. The method for determining electrical process parameters of a semiconductor device according to claim 1, It is characterized in that The process of constructing the preset process electrical property related model includes: Acquire multiple sample data, each sample data includes sample process parameters and corresponding device basic parameters; Based on the multiple sample data, a deep learning algorithm is used to perform model training to obtain a process electrical property related model.

7. The method for determining electrical process parameters of a semiconductor device according to claim 6, It is characterized in that The obtaining of a plurality of sample data comprises: Acquire device historical data, wherein the device historical data includes one or more of device historical simulation data, device historical DOE data, and device historical electrical performance data; Feature extraction is performed on the device historical data to obtain a plurality of sample data.

8. The method for determining electrical process parameters of a semiconductor device according to claim 1, It is characterized in that Also includes: Based on the device manufacturing process parameters, a preset simulation system is used to perform simulation to obtain device electrical simulation parameters; The device electrical simulation parameters are compared with the device electrical process parameters to obtain a comparison result.

9. A device for determining electrical process parameters of a semiconductor device, It is characterized in that include: An acquisition module, used to acquire device manufacturing process parameters and current equipment status data, wherein the device manufacturing process parameters are various parameters used to control the characteristics and performance of semiconductor devices in the semiconductor device manufacturing process, and the current equipment status data are status data of equipment used in the current semiconductor device manufacturing process; A parameter calculation module, used to determine electrical parameters based on the device manufacturing process parameters using a preset process electrical property related model, wherein the preset process electrical property related model is used to determine associated device electrical property parameter information based on the device manufacturing process parameter information; A fluctuation calculation module, used to determine the range of process electrical property fluctuations based on the current equipment state data and using a preset uncertainty model, wherein the preset uncertainty model is used to determine the impact of the equipment state on the process fluctuations according to the equipment state; The determination module is used to obtain device electrical process parameters based on the electrical parameters and the process electrical fluctuation range, wherein the device electrical process parameters are used to describe the electrical performance and characteristics of the semiconductor device.

10. An electronic device, It is characterized in that The electronic device includes: at least one processor; a memory connected to the at least one processor; The memory stores instructions that can be executed by the at least one processor, and the at least one processor implements the method for determining electrical process parameters of a semiconductor device according to any one of claims 1 to 8 by executing the instructions stored in the memory.

11. A machine-readable storage medium having instructions stored thereon, It is characterized in that When the instruction is executed by a processor, the processor is configured to execute the method for determining electrical process parameters of a semiconductor device according to any one of claims 1 to 8.

Images