Wafer processing process technological parameter correlation analysis method and related equipment

Abstract

The invention provides a correlation analysis method for technological parameters in a wafer processing process and related equipment. The correlation analysis method comprises the following steps: determining target parameters needing correlation analysis in the wafer processing process; according to the target parameter, acquiring all other process parameters belonging to the same wafer batch as the target parameter and corresponding parameter values in the data warehouse, and packaging into a data set; inputting the data set into a machine learning algorithm model, and calculating the correlation between the target parameter and other process parameters through a machine learning algorithm; and determining key process parameters influencing the target parameters according to a correlation calculation result. The correlation between the target parameter and other process parameters is automatically calculated and identified through a machine learning algorithm. In this way, the key process parameters influencing the target parameters can be effectively screened out, objective data support and decision basis are provided for the process defect problem caused by the common influence of multiple factors, and the difficulty of fault analysis and problem positioning is reduced.

Description

Technical Field

[0001] The present application relates to the field of semiconductor technology, and particularly relates to a method for analyzing the correlation of process parameters in the wafer processing process and related equipment. Background Art

[0002] During the wafer manufacturing process, the stability of the process and the operating state of the equipment have an important impact on the product yield. Manufacturing engineers rely on the Fault Detection and Classification (FDC) system to monitor and analyze various process parameters and related indicators that affect the product yield during the processing.

[0003] In the prior art, the conventional approach is to display the monitored data in the form of charts for engineers to visually identify and analyze. The characteristic of this method is simple and easy to use, but the disadvantage is that it cannot perform quantitative analysis. The analysis results rely on the subjective judgment of engineers, and different engineers may draw different conclusions from the same chart. Therefore, there is a lack of a unified and standard quantitative evaluation index, and it is difficult to form a consistent conclusion. Moreover, in the wafer manufacturing process, the influence on product quality is often the result of the combined action of multiple factors. When the problem defect is caused by the combined action of multiple parameters, it is difficult to analyze the root cause relying on a single chart analysis, which increases the difficulty of fault analysis. Summary of the Invention

[0004] Aiming at the deficiencies of the prior art, the present application provides a method for analyzing the correlation of process parameters in the wafer processing process and related equipment, so as to at least solve the problem in the prior art that the correlation between process parameters cannot be quantitatively analyzed.

[0005] To achieve the above object and other advantages, the present application is implemented by adopting the following technical solutions:

[0006] In a first aspect, the present application provides a method for analyzing the correlation of process parameters in the wafer processing process, including:

[0007] Determine the target parameters that need to be analyzed for correlation in the wafer processing process;

[0008] According to the target parameters, obtain all other process parameters belonging to the same wafer batch as the target parameters and the corresponding parameter values in the data warehouse, and package them into a data set;

[0009] Input the data set into a machine learning algorithm model, and calculate the correlation between the target parameter and other process parameters through the machine learning algorithm;

[0010] According to the correlation calculation result, determine the key process parameters that affect the target parameter.

[0011] According to a method for analyzing the correlation of process parameters in a wafer processing process provided by the present application, the step of obtaining all other process parameters and corresponding parameter values belonging to the same wafer manufacturing batch as the target parameter in the data warehouse according to the target parameter and packing them into a data set includes:

[0012] According to the alarm information in the fault detection and classification system, determine the target parameter and manufacturing process data associated with the alarm information, where the manufacturing process data includes: wafer batch and wafer number;

[0013] Query all process parameters and corresponding parameter values of the current wafer batch in the data warehouse according to the manufacturing process data;

[0014] Pack the process parameters and corresponding parameter values into a data set in the form of key-value pairs.

[0015] According to a method for analyzing the correlation of process parameters in a wafer processing process provided by the present application, the machine learning algorithm uses mutual information to calculate the correlation between the target parameter and other process parameters.

[0016] According to a method for analyzing the correlation of process parameters in a wafer processing process provided by the present application, the calculation of the mutual information is based on the theory of information entropy and is specifically defined as:

[0017] I(X; Y) = H(Y) - H(Y|X)

[0018] Where I(X; Y) is the mutual information between parameters X and Y, H(Y) is the information entropy of Y, and H(Y|X) is the conditional entropy of Y given X.

[0019] According to a method for analyzing the correlation of process parameters in a wafer processing process provided by the present application, it further includes:

[0020] Package the machine learning algorithm model into an application programming interface service for the fault detection and classification system to call.

[0021] According to a method for analyzing the correlation of process parameters in a wafer processing process provided by the present application, deploy the machine learning algorithm model on a separate server. When the fault detection and classification system needs to perform analysis, send a data request to the server. After receiving the data, the server performs algorithm analysis and returns the analysis result to the fault detection and classification system.

[0022] According to a method for analyzing the correlation of process parameters in a wafer processing process provided by the present application, the analysis result includes the target parameter, related parameters, and correlation values, and is visually presented on the interface of the fault detection and classification system.

[0023] Second aspect, the present application provides an electronic device, which includes:

[0024] One or more processors; and a memory storing computer program instructions, which when executed cause the processors to execute the method for analyzing the correlation of process parameters in the wafer processing process as described in any one of the above.

[0025] Third aspect, the present application provides a computer-readable storage medium, on which computer programs / instructions are stored, and when the computer programs / instructions are executed by a processor, the method for analyzing the correlation of process parameters in the wafer processing process as described in any one of the above is implemented.

[0026] Fourth aspect, the present application provides a computer program product, including computer programs / instructions, which when executed by a processor, implement the method for analyzing the correlation of process parameters in the wafer processing process as described in any one of the above.

[0027] A method for analyzing the correlation of process parameters in the wafer processing process and related devices provided by the present application determine the target parameters that need to be analyzed for correlation in the wafer processing process; according to the target parameters, obtain all other process parameters and corresponding parameter values belonging to the same wafer batch in the data warehouse, and package them into a data set; input the data set into a machine learning algorithm model, and calculate the correlation between the target parameter and other process parameters through the machine learning algorithm; according to the correlation calculation result, determine the key process parameters affecting the target parameter. The present application automatically calculates and identifies the correlation between the target parameter and other process parameters through the machine learning algorithm, enabling the relationship between the target parameter and other process parameters to be quantitatively expressed. In this way, the key process parameters affecting the target parameter can be effectively screened out, providing objective data support and decision-making basis for process defect problems caused by the joint influence of multiple factors, and reducing the difficulty of fault analysis and problem location. Description of the Drawings

[0028] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other implementation manners can be obtained according to these drawings without creative efforts.

[0029] Figure 1 is a flowchart of the method for analyzing the correlation of process parameters in the wafer processing process provided by the embodiment of the present application;

[0030] Figure 2 is the alarm information feedback interface of the FDC system provided by the embodiment of the present application;

[0031] Figure 3 It is a schematic flowchart of the interaction among users, FDC systems, data warehouses, and algorithm servers provided by the embodiments of the present application;

[0032] Figure 4 It is a schematic structural diagram of an electronic device provided by the embodiments of the present application. Detailed implementation manners

[0033] The above description is only an overview of the technical solution of the present application. In order to be able to understand the technical means of the present application more clearly, it can be implemented in accordance with the content of the specification. And in order to make the above and other purposes, features, and advantages of the present application more obvious and understandable, the following preferred embodiments are specifically given and described in detail in conjunction with the accompanying drawings as follows.

[0034] It should be noted that those of ordinary skill in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments without conflict. Unless otherwise defined, the technical terms or scientific terms involved in the present application should be the ordinary meanings understood by those with ordinary skills in the technical field to which the present application belongs. The terms "a", "one", "kind", "the", and other similar words involved in the present application do not indicate a quantity limitation and can represent a single or plural number. The terms "including", "comprising", "having", and any variations thereof involved in the present application are intended to cover non-exclusive inclusion; the terms "first", "second", "third", etc. involved in the present application are only used to distinguish similar objects and do not represent a specific order for the objects.

[0035] A Fault Detection and Classification (FDC) system is an important system used for real-time monitoring, detection, and classification of process faults in semiconductor manufacturing processes. The FDC system collects process parameters, equipment status, and environmental data in real time through various sensors installed on production equipment, thereby continuously monitoring the production process. The system uses preset thresholds and statistical models to automatically determine whether the collected data exceeds the normal range to detect potential equipment faults or process anomalies. Once an anomaly is detected, the FDC system can not only give an alarm (Alarm: set a threshold for parameters, and if it exceeds this threshold, trigger a warning action to notify the engineer to handle), but also perform classification analysis based on the characteristics of the abnormal data to help the engineer judge the nature and possible causes of the fault, thereby providing a basis for subsequent fault handling and process optimization.

[0036] Referring to Figure 1 As shown, the embodiments of the present application provide a method for analyzing the correlation of process parameters in a wafer processing process, including:

[0037] Step S1: Determine the target parameters that need to be analyzed for correlation during the wafer processing.

[0038] Specifically, various sensors are usually installed on semiconductor manufacturing equipment, such as temperature sensors, pressure sensors, flow sensors, humidity sensors, etc. These sensors collect real-time data on the equipment operating status and process environment, generating process parameters including temperature, pressure, gas flow, humidity, etc. During the wafer processing, these parameters are collected and stored in real-time through the equipment control system. The FDC system records various process parameters collected by the equipment. When a certain process parameter exceeds the preset threshold, the FDC system generates an alarm message and records the relevant process parameter data at that time. The alarm message usually contains equipment information, wafer information, and the specific process parameter and its abnormal value that triggered the alarm. By analyzing these alarm records, the process parameters that frequently appear or have abnormal values in the alarm events are obtained as the target parameters for correlation analysis.

[0039] It is also possible to provide a preset list of process parameters or allow users to customize the input on the operation interface of the FDC system. Engineers can, based on production experience and the current process situation, check one or more key process parameters from the list as the target parameters. For example, in a certain wafer processing flow, parameters such as temperature, pressure, and flow are focused on.

[0040] Step S2: According to the target parameters, obtain all other process parameters and their corresponding parameter values belonging to the same wafer batch in the data warehouse, and package them into a data set.

[0041] In this embodiment, step S2 specifically includes:

[0042] Step S201: According to the alarm information in the fault detection and classification system, determine the target parameters and manufacturing process data associated with the alarm information. The manufacturing process data includes: wafer batch and wafer number;

[0043] Step S202: Query all process parameters and their corresponding parameter values of the current wafer batch in the data warehouse according to the manufacturing process data;

[0044] Step S203: Package the process parameters and their corresponding parameter values into a data set in the form of key-value pairs.

[0045] Specifically, such as Figure 2As shown, alarm information is obtained from the alarm information feedback interface of the FDC system. The alarm information usually includes process parameters (Parameter) that trigger the alarm, alarm time, equipment information (EQP), etc. The process parameters recorded as abnormal or exceeding the preset range in the alarm are determined as the target parameters for which correlation analysis needs to be performed. Associated manufacturing process data is obtained from the alarm information, including wafer lot (Lot) and wafer number (Wafer). These data can determine the specific manufacturing lot and specific wafer when the alarm occurs.

[0046] The data warehouse stores all process parameters and their corresponding real-time or historical parameter values during the processing of each wafer lot. The FDC system queries all other process parameter data related to the target parameter within the wafer lot according to the specified lot number (LOT) and wafer number (Wafer). The query results include multiple process parameters (possibly a dozen or dozens), and each process parameter has a corresponding numerical record (which can be data at a time point or continuous data over a period of time).

[0047] Organize and format the data queried in step S202. The data can be organized in the form of key-value pairs, where the "key" can be the process parameter name (such as "temperature", "pressure", "humidity", etc.), and the corresponding "value" is the specific value or time series data of the parameter within the current wafer lot. Pack the organized data into a structured data set, such as a two-dimensional data table, dictionary, or JSON format, for easy calling and processing by subsequent machine learning models. The data set should also include identification information such as wafer lot and wafer number to trace the data source when performing cross-lot or multi-data source analysis.

[0048] Step S3: Input the data set into the machine learning algorithm model, and calculate the correlation between the target parameter and other process parameters through the machine learning algorithm.

[0049] During the wafer manufacturing process, product quality is usually affected by the combined action of multiple process parameters, and there may be non-linear relationships between the parameters. Traditional linear analysis methods are difficult to identify these complex relationships. Machine learning methods can discover non-linear, multi-variable interaction effects, so as to more accurately identify the key influencing factors leading to abnormal target parameters.

[0050] In this embodiment, the machine learning algorithm uses mutual information to calculate the correlation between the target parameter and other process parameters.

[0051] Before calculating the mutual information, it is necessary to preprocess the data to improve the accuracy of the calculation. If there are missing values in some parameters, methods such as mean filling, interpolation, or deleting abnormal samples can be used to handle them. Since the numerical ranges of different process parameters may vary greatly (for example, the pressure unit is Pa and the temperature is °C), normalization is required to ensure that all parameters are on the same order of magnitude. After such normalization, the data range is unified to [0, 1], which is convenient for calculating the mutual information.

[0052] In probability theory and information theory, mutual information is a measure of the degree of information sharing between two random variables. The mutual information of two random variables is a measure of the mutual dependence between the variables. This method applies the mutual information algorithm to analyze the correlation between different process parameters in the wafer manufacturing process. For example, if the target parameter is X, the algorithm calculates the mutual information between all other parameters and the target parameter X in the same wafer processing batch, and the parameter with the largest calculated value is the parameter with the highest correlation with X.

[0053] According to the theory of information entropy, H(X) is the information entropy of X, representing the uncertainty of X. Then H(Y|X) is the measure of the remaining uncertainty of Y when X is known. Thus, the functional formula for the mutual information I(X; Y) is:

[0054] I(X; Y) = H(Y) - H(Y|X)

[0055] Among them, I(X; Y) is the mutual information between parameters X and Y, H(Y) is the information entropy of Y, and H(Y|X) is the conditional entropy of Y when X is known.

[0056] I(X; Y) = 0 indicates that X and Y are completely independent and have no correlation.

[0057] I(X; Y) > 0 indicates that there is a certain statistical correlation between X and Y.

[0058] The larger I(X; Y) is, the stronger the influence between X and Y.

[0059] Therefore, process parameters with higher mutual information values indicate that they have a greater impact on the target parameter and may be key influencing factors. While process parameters with lower mutual information values may have a smaller impact on the target parameter or their changes are independent.

[0060] In the wafer manufacturing process, the values of each process parameter are usually continuous random variables rather than discrete values. Therefore, when calculating mutual information, it is necessary to estimate based on the probability density function. Using Kernel Density Estimation (KDE) or the histogram method, calculate the marginal probability density P(X) of the target parameter X and the marginal probability density P(Y) of each process parameter (such as Y). Based on the joint distribution data of X and Y, estimate the joint probability density P(X,Y). Therefore, the derivation process of the mutual information I(X;Y) functional formula is as follows:

[0061]

[0062] where P(X,Y) is the joint probability density function of X and Y, and P(X) and P(Y) are the marginal probability density functions of X and Y respectively.

[0063] Therefore, the mutual information functional formula is defined as:

[0064]

[0065] Based on the functions of the FDC system, this method introduces a machine learning algorithm to automatically calculate the mutual information between process parameters, directly quantify the correlation between the target parameter and other parameters, thereby reducing manual intervention and improving analysis efficiency.

[0066] Step S4: Determine the key process parameters that affect the target parameter according to the correlation calculation results.

[0067] Specifically, according to the correlation calculation results, all process parameters are sorted in descending order of mutual information values. Set a correlation threshold. Process parameters with higher mutual information values are regarded as key process parameters and may be the main factors causing changes in the target parameter. Process parameters with lower mutual information values may have less impact on the target parameter and can be ignored. Hidden process defects can be discovered through key process parameters, improving the fault tracing ability and accelerating the abnormal troubleshooting process.

[0068] Based on the functions of the FDC system, this method introduces a machine learning algorithm to automatically calculate and identify several process parameters with high correlation with the target parameter. This enables the quantitative expression of the relationship between the target parameter and other process parameters. In this way, key process parameters affecting the target parameter can be effectively screened out, providing objective data support and decision-making basis for process defect problems caused by the joint influence of multiple factors, and reducing the difficulty of fault analysis and problem location.

[0069] In this embodiment, the method further includes:

[0070] The machine learning algorithm model is encapsulated into an application programming interface service for the fault detection and classification system to call. This enables the FDC system to interact with the machine learning model through HTTP requests without having to run the algorithm locally. It allows FDC systems on different production lines and in different factories to access the same set of machine learning models, improving data consistency. An API server is built using Flask / FastAPI in a Python environment and the machine learning model is loaded.

[0071] This embodiment also includes deploying the machine algorithm model. Specifically, the machine learning algorithm model is deployed on a separate server. When the fault detection and classification system needs to perform analysis, it sends a data request to the server. The server receives the data, performs algorithm analysis, and returns the analysis result to the fault detection and classification system.

[0072] The algorithm server can use a local server or a cloud server (such as AWS, Tencent Cloud, Alibaba Cloud, etc.). For small-scale deployments, the machine algorithm model can be directly run on a physical server. For large-scale concurrent computing, the model is containerized with Docker and managed using Kubernetes.

[0073] As Figure 3 shown, when the FDC system detects an abnormality in the target parameter or needs to perform correlation analysis, the system will automatically trigger a data request. That is, the background program queries all other process parameters and parameter values in the current wafer processing batch in the data warehouse based on information such as Lot, Wafer, and Parameter. The queried data is packaged into a data set and passed to the algorithm server through an interface. The algorithm server receives the request, parses the data, extracts the target parameter and the set of process parameters. It calls the mutual information calculation model to calculate the correlation between the target parameter and the process parameters. The algorithm server returns the analysis result (target parameter, relevant parameters, mutual information value, etc.) to the FDC system. The FDC system displays the analysis result on the user interface for engineers to refer to. The mutual information value distribution between the target parameter and other parameters can be presented in ways such as tables, bar charts, or heat maps, facilitating engineers to intuitively judge the strength of the correlation.

[0074] Taking the target parameter "FLOW01" as an example, all the calculated mutual information values are sorted by size. The analysis result is formed into a correlation analysis table as shown in Table 1 below.

[0075] Table 1 Correlation between relevant parameters and target parameter

[0076]

[0077] This table shows the correlations between different parameters (GAS01, GAS02, GAS03, GAS04, PRESSURE1, PRESSURE2, PRESSURE3, PRESSURE4) and the target parameter FLOW01. The correlation values range from 0 to 1, and the closer the value is to 1, the stronger the correlation. It can be seen from the table that the correlation between GAS01 and FLOW01 is the strongest, with a value of 0.88; the correlation between PRESSURE4 and FLOW01 is the weakest, with a value of 0.39.

[0078] Therefore, the machine learning model is encapsulated as an API service, and the computing tasks are deployed to an independent algorithm server. The FDC system can call the analysis service at any time through API interaction. For example, multiple FDC instances can call the API simultaneously to achieve parallel analysis. Using a dedicated server for computing improves the data analysis speed, reduces the computing burden on the FDC system, and improves the system stability. The API can set access control to prevent unauthorized calls. Deploying the machine learning model independently allows its machine learning algorithm to be updated at any time without modifying the FDC system code. In this way, even users who do not understand the algorithm can quickly use it, improving the quality and efficiency of process parameter analysis, and ultimately achieving the goal of improving the wafer yield.

[0079] In summary, a method for analyzing the correlations of process parameters in the wafer processing process provided by this application includes determining the target parameters that need to be analyzed for correlations in the wafer processing process; according to the target parameters, obtaining all other process parameters and their corresponding parameter values belonging to the same wafer batch in the data warehouse, and packaging them into a data set; inputting the data set into a machine learning algorithm model, and calculating the correlations between the target parameters and other process parameters through the machine learning algorithm; according to the correlation calculation results, determining the key process parameters that affect the target parameters. This application automatically calculates and identifies the correlations between the target parameters and other process parameters through the machine learning algorithm, enabling the relationships between the target parameters and other process parameters to be quantitatively expressed. In this way, the key process parameters that affect the target parameters can be effectively screened out, providing objective data support and decision-making basis for process defect problems caused by the joint influence of multiple factors, and reducing the difficulty of fault analysis and problem location.

[0080] Those skilled in the art can understand that in the above method of the specific implementation manner, the writing order of each step does not mean a strict execution order that constitutes any limitation on the implementation process, and the specific execution order of each step should be determined by its function and possible internal logic.

[0081] In addition, some embodiments of the present application also provide an electronic device. The electronic device may be various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and so on. The electronic device may also be various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices, and other similar computing devices.

[0082] The electronic device includes: one or more processors; and a memory storing computer program instructions that, when executed, cause the processors to execute the wafer processing process parameter correlation analysis method provided in any one or more of the above embodiments. Figure 4 An exemplary structural diagram of the electronic device is disclosed. As Figure 4 shown, the electronic device includes: one or more processors 1101, a memory 1102, and interfaces for connecting the components, including high-speed interfaces and low-speed interfaces. Each component is interconnected using different buses and may be mounted on a common motherboard or otherwise installed as required. The processor can process instructions executed within the electronic device, including instructions stored in the memory or on the memory to display graphical information of a GUI on an external input / output device (such as a display device coupled to the interface). In some other embodiments, if needed, multiple processors and / or multiple buses may be used together with multiple memories and multiple memories. Similarly, multiple electronic devices may be connected, each device providing some necessary operations (for example, as a server array, a set of blade servers, or a multi-processor system). Among them, the components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present application described herein and / or claimed.

[0083] The electronic device may further include: an input device 1103 and an output device 1104. The processor 1101, the memory 1102, the input device 1103, and the output device 1104 may be connected by a bus or other means, Figure 4 taking connection by bus as an example.

[0084] The input device 1103 can receive input digital or character information and generate key signal inputs related to the user settings and function controls of the electronic device, such as input devices like touchscreens, keypads, mice, trackpads, touchpads, pointing sticks, one or more mouse buttons, trackballs, joysticks, etc. The output device 1104 can include display devices, auxiliary lighting devices (e.g., LEDs), and haptic feedback devices (e.g., vibration motors), etc. The display device can include, but is not limited to, liquid crystal displays (LCDs), light-emitting diode (LED) displays, and plasma displays. In some embodiments, the display device can be a touchscreen.

[0085] To provide interaction with the user, the electronic device can be a computer. The computer has: a display device for displaying information to the user (e.g., a cathode ray tube (CRT) or an LCD monitor); and a keyboard and a pointing device (e.g., a mouse or a trackball), through which the user can provide inputs to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or haptic feedback); and inputs from the user can be received in any form (including acoustic input, voice input, or haptic input).

[0086] In the embodiments of this application, a computer program / instructions is stored on a computer-readable medium. When the computer program / instructions are executed by a processor, the wafer processing process parameter correlation analysis method provided by any one or more of the above embodiments is implemented. The computer-readable medium can be included in the electronic device described in the above embodiments; or it can exist alone without being assembled into the device. The above computer-readable medium carries one or more computer-readable instructions.

[0087] The memory 1102 can be used as a non-transitory computer-readable storage medium for storing non-transitory software programs, non-transitory computer-executable programs, and modules. The processor 1101 executes various functional applications and data processing of the server by running the non-transitory software programs, instructions, and modules stored in the memory 1102, so as to implement the program instructions / modules corresponding to the method provided by any one or more of the above embodiments in the embodiments of this application.

[0088] The memory 1102 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the electronic device and the like. In addition, the memory 1102 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory 1102 may optionally include a memory remotely disposed relative to the processor 1101, and these remote memories may be connected to the electronic device through a network. Examples of the above networks include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0089] It should be noted that more specific examples of computer-readable storage media may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), or a flash memory, an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium may be any tangible medium that contains or stores a program, and the program may be used by or in combination with an instruction execution system, apparatus, or device.

[0090] A computer-readable storage medium includes permanent and non-permanent, removable and non-removable media and can implement information storage by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of the computer's storage medium 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 technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0091] Computer program code for performing the operations of the present application can be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., by using an Internet service provider to connect through the Internet).

[0092] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. For example, an application-specific integrated circuit (ASIC) or a general-purpose computer or any other similar hardware device can be used. In some embodiments, the software program of the present application can be executed by a processor to implement the above steps or functions. Similarly, the software program (including related data structures) of the present application can be stored in a computer-readable recording medium, such as a RAM memory, a magnetic or optical drive, or a floppy disk and the like. In addition, some steps or functions of the present application can be implemented by hardware, for example, as a circuit that cooperates with the processor to execute each step or function.

[0093] The computer program product provided by the embodiments of the present application includes one or more computer programs / instructions. When the computer program / instructions are executed by a processor, they wholly or partly generate the processes or functions described in the embodiments of the present application. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center by wire (such as coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or a data center that includes one or more integrated available media. The available medium can be a magnetic medium (such as a floppy disk, a hard disk, a magnetic tape), an optical medium (such as a DVD), or a semiconductor medium (such as a solid-state drive, SSD).

[0094] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of devices, methods, and computer program products according to various embodiments of the present application. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a part of code, which contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0095] As described above, the above are only specific embodiments of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily make changes or replacements, which should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims, and the above embodiments should be regarded as exemplary and non-limiting.

Claims

1. A method for analyzing the correlation of process parameters in a wafer processing process, characterized in that, Including: Determine the target parameters that need to be analyzed for correlation during the wafer processing; According to the target parameters, obtain all other process parameters and their corresponding parameter values belonging to the same wafer batch in the data warehouse, and package them into a data set; Input the data set into a machine learning algorithm model, and calculate the correlation between the target parameter and other process parameters through the machine learning algorithm; According to the correlation calculation result, determine the key process parameters that affect the target parameter.

2. The method for analyzing the correlation of process parameters in the wafer processing process according to claim 1, wherein The step of obtaining all other process parameters and their corresponding parameter values belonging to the same wafer manufacturing batch as the target parameter in the data warehouse according to the target parameter and packaging them into a data set includes: According to the alarm information in the fault detection and classification system, determine the target parameter and manufacturing process data associated with the alarm information, where the manufacturing process data includes: wafer batch and wafer number; Query all process parameters and their corresponding parameter values of the current wafer batch in the data warehouse according to the manufacturing process data; Package the process parameters and their corresponding parameter values into a data set in the form of key-value pairs.

3. The method for analyzing the correlation of process parameters in the wafer processing process according to claim 1, characterized in that, The machine learning algorithm uses mutual information to calculate the correlation between the target parameter and other process parameters.

4. The method for analyzing the correlation of process parameters in the wafer processing process according to claim 3, characterized in that, The calculation of the mutual information is based on the theory of information entropy and is specifically defined as: I(X; Y) = H(Y) - H(Y|X) Where I(X; Y) is the mutual information between parameter X and Y, H(Y) is the information entropy of Y, and H(Y|X) is the conditional entropy of Y given X.

5. The method for analyzing the correlation of process parameters in the wafer processing process according to any one of claims 1 to 4, characterized in that, It also includes: Package the machine learning algorithm model into an application programming interface service for the fault detection and classification system to call.

6. The method for analyzing the correlation of process parameters in the wafer processing process according to claim 5, characterized in that Deploy the machine learning algorithm model on a separate server. When the fault detection and classification system needs to perform analysis, send a data request to the server. After receiving the data, the server performs algorithm analysis and returns the analysis result to the fault detection and classification system.

7. The method for analyzing the correlation of process parameters in the wafer processing process according to claim 6, wherein, The analysis result includes the target parameter, related parameters, and correlation values, and is visually presented on the interface of the fault detection and classification system.

8. An electronic device, characterized in that, The electronic device includes: One or more processors; and a memory storing computer program instructions, where the computer program instructions, when executed, cause the processors to execute the method for analyzing the correlation of process parameters in the wafer processing as described in any one of claims 1-7.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, The computer program / instructions, when executed by the processor, implement the method for analyzing the correlation of process parameters in the wafer processing as described in any one of claims 1-7.

10. A computer program product, comprising a computer program / instructions, characterized in that, The computer program / instructions, when executed by the processor, implement the method for analyzing the correlation of process parameters in the wafer processing as described in any one of claims 1-7.

Images