AI Edge Computing Platform, Method, Terminal and System for Fab System

Abstract

The present invention provides an AI edge computing platform, method, terminal and system for a Fab system. The platform is designed specifically for the Fab system, customized and developed according to the business data processing task requirements in each Fab system, deployed on the edge side of multiple machines and equipment in a wafer manufacturing plant, and communicated with each machine and equipment. The platform can collect and screen process parameter data that meets the high-quality wafer standards, analyze and process using a specific algorithm model, dynamically adjust the process parameters of the machine equipment according to the analysis results, compensate for the Fab system index, and optimize the performance of the machine equipment, the production process, and the algorithm model. By combining edge computing with AI technology, the present invention realizes low-latency processing and real-time analysis of the process parameters of semiconductor manufacturing equipment, improves the system processing efficiency and response speed, and integrates the full-process automated management of equipment data processing, reduces the need for manual intervention, and reduces the workload of developers.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor technology, and particularly to an AI edge computing platform, method, terminal and system for a Fab system. Background Art

[0002] With the development of big data and AI technologies, the semiconductor industry has entered the application stage of big data and AI technologies. The AI applications combining enterprise business systems and business data in multiple scenarios can reduce costs and increase efficiency. There are an increasing number of domestic wafer fabs, and there are higher requirements for the efficiency of processing data after the Fab system goes online, and calculations need to be performed and corresponding results obtained in a timely manner. Currently, most domestic wafer manufacturing plants' Fab systems upload massive amounts of data to the cloud data center for processing and return the results to users. Although the Fab system under the traditional cloud computing paradigm can meet the need to upload basic business data to the cloud data center for processing, with the continuous development and update of individual latency-sensitive services such as artificial intelligence application programs, it is difficult to meet the higher requirements for data volume, latency, and data controllability and security. Summary of the Invention

[0003] In view of the above-mentioned disadvantages of the prior art, the purpose of the present invention is to provide an AI edge computing platform, method, terminal and system for a Fab system, which is used to solve the technical problem that with the continuous development and update of individual latency-sensitive services such as artificial intelligence application programs in the prior art, it is difficult to meet the higher requirements for data volume, latency, and data controllability and security.

[0004] To achieve the above and other related objectives, the present invention provides an AI edge computing platform for the Fab system. Developed based on the business data processing requirements in the Fab system, it is deployed on the edge side of multiple machine tools in the wafer fabrication plant and is communicatively connected to each machine tool. The platform includes: a machine tool data acquisition module, which is used to collect the process parameter values of each machine tool according to the user parameter requirements and screen the data that belongs to the normal wafer production process and meets the high-quality wafer standards; a data analysis module, connected to the machine tool data acquisition module, which is used to analyze and process the data output by the machine tool data acquisition module by using an algorithm model with the Fab system business data processing function selected according to the amount of data that needs to be analyzed and processed by the data analysis module, and obtain the analysis result; a data optimization module, connected to the data analysis module, which is used to dynamically adjust the process parameter values of each machine tool and compensate the Fab system index by using the analysis result output by the data analysis module, so as to feedback the adjusted process parameter values to the user to optimize the performance and production process of the machine tool, and use the compensated Fab system index to optimize the model parameters of the algorithm model in the data analysis module; it is also used to adjust the type of the algorithm model used by the data analysis module based on the amount of data that needs to be processed by the data analysis module.

[0005] In an embodiment of the present invention, the machine tool data acquisition module includes: a user demand data acquisition unit, which is used to determine the user parameter requirements and collect the process parameter values of each machine tool based on the user parameter requirements; wherein, the process parameter values include one or more of the temperature and humidity of the machine tool cavity, the liquid flow rate, and the gas concentration; a normal wafer production process screening unit, connected to the user demand data acquisition unit, which is used to screen the data of the normal wafer production process in the collected data to eliminate the data of the R & D and test processes; a high-quality data screening unit, connected to the normal wafer production process screening unit, which is used to screen the data without process problems in the screened data of the normal wafer production process as the data that meets the high-quality standards; a data storage unit, connected to the high-quality data screening unit, which is used to store the data that meets the high-quality standards screened by the high-quality data screening unit.

[0006] In an embodiment of the present invention, the data analysis module is used to perform key parameter analysis on the data output by the machine tool data acquisition module by using a machine learning model or a deep learning model with the Fab system business data processing function selected according to the amount of data that needs to be analyzed by the data analysis module, and obtain the corresponding analysis result; wherein, the Fab systems include: the YMS system, the APC system, the FDC system, the MES system, and the SPC system.

[0007] In one embodiment of the present invention, the data analysis module includes: a machine learning model prediction unit, configured to output a predicted analysis result according to the data output by the machine tool data acquisition module through a trained machine learning algorithm model when the amount of data to be analyzed is within the standard data volume range; wherein, the machine learning algorithm model adopts a decision tree model; a deep learning model prediction unit, configured to output a predicted analysis result according to the data output by the machine tool data acquisition module through a trained deep learning algorithm model when the amount of data to be analyzed exceeds the standard data volume range.

[0008] In one embodiment of the present invention, the types of decision tree models adopted by the machine learning algorithm model include: CatBoost model and XGBoost model; the types of deep learning algorithm models include: CNN and DNN models.

[0009] In one embodiment of the present invention, the data optimization module includes: a parameter adjustment and compensation unit, configured to dynamically adjust the process parameter values and compensate the Fab system index by using the analysis result, and feed back the adjusted process parameter values to the user to optimize the performance of the machine tool equipment and the production process and use the Fab system index optimization algorithm model to optimize the model parameters; a model adjustment unit, configured to monitor the amount of data input to the data analysis module, and control the data analysis module to process the data by using the machine learning model when the data volume is within the standard data volume range and control the data analysis module to process the data by using the deep learning algorithm model when the data volume exceeds the standard data volume range.

[0010] In one embodiment of the present invention, the development process of the platform includes: the user determines relevant parameters, determines the AI computing power requirements of the AI edge computing platform according to the type and scale of the business data processing tasks in each required Fab system after the communication of the AI edge computing platform and various tests in the traditional development mode are completed, configures the corresponding appropriate edge computing hardware specifications, deploys the computing, network and storage resources of the cloud server to the edge side of each machine tool equipment, and constructs an algorithm model and deploys an AI application on the edge server.

[0011] To achieve the above and other related objectives, the present invention provides an AI edge computing method for a Fab system, which is applied to an AI edge computing platform of the Fab system. The platform is developed based on the business data processing requirements in each system of the Fab and is deployed on the edge side of multiple machine tools in a wafer fabrication plant and is communicatively connected to each machine tool. The method includes: collecting process parameter values of each machine tool according to user parameter requirements and screening data belonging to normal wafer production processes and meeting the high-quality wafer standards; analyzing and processing the screened data using an algorithm model with Fab system business data processing functions selected according to the amount of data to be analyzed and processed to obtain an analysis result; dynamically adjusting the process parameter values of each machine tool and compensating the Fab system index using the analysis result, so as to feed the adjusted process parameter values back to the user to optimize the performance and production process of the machine tool, and optimizing the model parameters of the algorithm model using the compensated Fab system index.

[0012] To achieve the above and other related objectives, the present invention provides an electronic terminal, including: one or more memories and one or more processors; the one or more memories are used for storing computer programs; the one or more processors are connected to the memories and are used for running the computer programs to execute the AI edge computing method for the Fab system.

[0013] To achieve the above and other related objectives, the present invention provides an AI edge computing system, the system includes: a cloud server and one or more AI edge computing subsystems; wherein, each AI edge computing subsystem includes: a machine tool group composed of multiple machine tools in a wafer fabrication plant; wherein, each machine tool group is obtained by grouping each machine tool in the wafer fabrication plant; an AI edge computing platform for the Fab system deployed corresponding to the edge side of the machine tool group; the AI edge computing platform for the Fab system is communicatively connected between each machine tool of the corresponding machine tool group and the cloud server.

[0014] As described above, the present invention is an AI edge computing platform, method, terminal and system for a Fab system, and has the following beneficial effects: The present invention provides an AI edge computing platform specifically designed for a Fab system. This platform is customized and developed according to the requirements of business data processing tasks in each system of the Fab, deployed on the edge side of multiple machine tools in a wafer fabrication plant, and communicatively connected to each machine tool. The platform can collect and screen process parameter data that meets the high-quality wafer standard, perform analysis and processing using a specific algorithm model, dynamically adjust the process parameters of the machine tool according to the analysis results, compensate the Fab system index, and optimize the performance of the machine tool and the production process as well as the algorithm model. By combining edge computing and AI technology, the present invention realizes low-latency processing and real-time analysis of the process parameters of semiconductor manufacturing equipment, improves the system processing efficiency and response speed, and at the same time integrates the full-process automated management of equipment data processing, reduces the need for manual intervention, and alleviates the workload of developers. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It shows a schematic structural diagram of an AI edge computing platform for a Fab system in an embodiment of the present invention.

[0016] Figure 2 It shows a schematic structural diagram of an AI edge computing platform for a Fab system in an embodiment of the present invention.

[0017] Figure 3 It shows a schematic flow diagram of an AI edge computing method for a Fab system in an embodiment of the present invention.

[0018] Figure 4 It shows a schematic structural diagram of an electronic terminal in an embodiment of the present invention.

[0019] Figure 5 It shows a schematic structural diagram of an AI edge computing system in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0020] The following specific examples illustrate the embodiments of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other.

[0021] It should be noted that in the following description, with reference to the accompanying drawings, several embodiments of the present invention are described. It should be understood that other embodiments may also be used, and mechanical composition, structure, electrical, and operational changes may be made without departing from the spirit and scope of the present invention. The following detailed description should not be considered restrictive, and the scope of the embodiments of the present invention is only defined by the claims of the published patent. The terms used herein are only for describing specific embodiments and are not intended to limit the present invention. Spatially related terms, such as "upper", "lower", "left", "right", "below", "beneath", "lower part", "above", "upper part", etc., may be used in the text to facilitate the description of the relationship between one element or feature shown in the figure and another element or feature.

[0022] Throughout the specification, when it is said that a part is "connected" to another part, this includes not only the case of "direct connection", but also the case of "indirect connection" with other elements placed therebetween. Additionally, when it is said that a certain part "includes" a certain constituent element, unless there is a particularly contrary record, it does not exclude other constituent elements, but means that other constituent elements may also be included.

[0023] The first, second, and third, etc. terms mentioned therein are used to describe various parts, components, regions, layers, and / or segments, but are not limited thereto. These terms are only used to distinguish one part, component, region, layer, or segment from other parts, components, regions, layers, or segments. Therefore, the first part, component, region, layer, or segment described below may refer to the second part, component, region, layer, or segment within the scope not exceeding the present invention.

[0024] Furthermore, as used herein, the singular forms "a", "an", and "the" are intended to also include the plural forms unless the context indicates otherwise. It should be further understood that the terms "comprise", "include" indicate the presence of the described features, operations, elements, components, items, kinds, and / or groups, but do not exclude the presence, occurrence, or addition of one or more other features, operations, elements, components, items, kinds, and / or groups. The terms "or" and "and / or" used herein are interpreted as inclusive, or meaning any one or any combination. Thus, "A, B, or C" or "A, B, and / or C" means "any one of the following: A; B; C; A and B; A and C; B and C; A, B, and C". An exception to this definition only occurs when the combination of elements, functions, or operations is inherently mutually exclusive in some way.

[0025] Edge computing technology, with its characteristics of low latency, low power consumption, and enhanced privacy and security, has shown significant advantages in the semiconductor manufacturing field. It is particularly suitable for latency-sensitive services, effectively alleviating network congestion and reducing the computing and storage burdens on cloud data centers. By sinking cloud resources closer to terminal devices, edge servers undertake more task processing, reducing both transmission latency and the computing pressure on the cloud. However, with the increase in data scale and computing complexity, as well as the heterogeneity and finiteness of edge cluster resources, traditional edge computing faces challenges and is difficult to meet the low-latency, low-power consumption requirements of device processes and the needs for automated optimization.

[0026] Therefore, the present invention provides an AI edge computing platform for the Fab system. This platform is specifically designed for the Fab system, custom-developed according to the requirements of business data processing tasks in each system of the Fab, deployed on the edge side of multiple machine tools in the semiconductor wafer fabrication plant, and communicatively connected to each machine tool. The platform can collect and screen process parameter data that meet the high-quality wafer standards, analyze and process it using specific algorithm models, dynamically adjust the process parameters of the machine tools and compensate for the Fab system index according to the analysis results, and optimize the performance of the machine tools and the production process as well as the algorithm models. By combining edge computing and AI technology, the present invention realizes low-latency processing and real-time analysis of the process parameters of semiconductor manufacturing equipment, improves the system processing efficiency and response speed, and at the same time integrates the full-process automated management of device data processing, reduces the need for manual intervention, and alleviates the workload of developers.

[0027] The following will be a detailed description of the embodiments of the present invention with reference to the accompanying drawings, so that those skilled in the technical field of the present invention can easily implement it. The present invention can be embodied in many different forms and is not limited to the embodiments described herein.

[0028] As Figure 1 shows a schematic structural diagram of an AI edge computing platform for the Fab system in an embodiment of the present invention.

[0029] During the semiconductor wafer manufacturing process, the Fab system generates a large amount of business data, which is crucial for real-time monitoring of the production status, optimizing the production process, predicting equipment failures, etc. Traditional business data processing methods often rely on cloud servers. With the continuous development and update of individual latency-sensitive services such as artificial intelligence application programs, higher requirements are put forward for data volume, latency, and the controllability and security of data. Therefore, developing an AI-based edge computing platform has become an effective way to solve the computing performance problems of data-intensive tasks in the semiconductor manufacturing process.

[0030] The present invention is specifically designed for the Fab system. The Fab system, namely the Fabrication system, is the abbreviation of semiconductor manufacturing factories and their manufacturing processes. The purpose of the present invention is to optimize equipment performance and production processes through artificial intelligence means to improve overall operation efficiency. Each system in Fab includes: EAP system, YMS system, APC system, FDC system, MES system, SPC system, etc. These systems each undertake different business responsibilities and generate a large amount of business data in the process.

[0031] The AI edge computing platform is developed based on the business data processing requirements in each Fab system. The business data processing requirements in each Fab system include the requirements for the business data processing functions of each Fab system. It is deployed on the edge side of multiple machine tools in the wafer manufacturing factory, that is, at a position directly close to the data source. This deployment method can significantly reduce the latency of data transmission and improve the real-time performance of data processing. The platform is communicatively connected to each machine tool. The platform includes:

[0032] The machine tool data acquisition module 1, whose main responsibility is to accurately acquire the process parameter values of each machine tool in the semiconductor manufacturing factory (Fab system) according to the parameter requirements set by the user. This module is not only responsible for data collection but also undertakes the important task of data screening. In terms of data acquisition, the machine tool data acquisition module 1 captures key process parameters such as temperature, pressure, flow rate, time, etc. from each machine tool in real time and accurately according to the user parameter requirements. These parameters are crucial for understanding the state of the production process and product quality. The machine tool data acquisition module 1 also needs to strictly screen and filter the acquired data. It only screens data belonging to the normal wafer production link and meeting the high-quality wafer standards to ensure the accuracy and effectiveness of subsequent analysis and optimization work. This screening mechanism helps to reduce the interference of noise data and improve the efficiency and accuracy of data processing.

[0033] The data analysis module 2, connected to the machine tool data acquisition module 1, is built-in with a variety of AI algorithm models with the functions of business data processing tasks in the Fab system. The data analysis module 2 uses the AI algorithm model selected according to the amount of data that the data analysis module needs to analyze and process to analyze and process the data output by the machine tool data acquisition module 1 to obtain an analysis result;

[0034] The data optimization module 3 is connected to the data analysis module 2. The data optimization module 3 dynamically adjusts the process parameter values of each machine tool device by using the analysis results, and feeds the adjusted process parameter values back to the user. This process aims to optimize the performance of the machine tool devices, improve production efficiency, and ensure that the produced wafers meet high-quality standards. By adjusting the process parameters in real time, the data optimization module 3 helps to reduce fluctuations and uncertainties in the production process, and improve the stability and controllability of the overall production line. In addition to adjusting the process parameters, the data optimization module 3 can also use the analysis results to compensate the Fab system index to optimize the model parameters of the algorithm model in the data analysis module. This step is to reflect the actual situation in the production process and ensure that the algorithm model in the data analysis module 2 can more accurately reflect the state of the production line. By compensating the Fab system index, it helps to improve the prediction ability and accuracy of the algorithm model, that is, by continuously adjusting and optimizing the model parameters, the data optimization module 3 can ensure that the algorithm model can more accurately predict and interpret the data changes in the production process, and improve the efficiency and accuracy of data analysis and optimization. It provides a more reliable basis for subsequent data analysis and optimization. In addition, the data optimization module 3 can also intelligently adjust the type of algorithm model used according to the amount of data to be processed by the data analysis module 2. This function helps to ensure that the data analysis module 2 can maintain efficient and accurate performance under different data scales. By dynamically selecting and optimizing the algorithm model, the data optimization module 3 helps to improve the flexibility and adaptability of the entire AI edge computing platform.

[0035] The present invention integrates edge computing and an artificial intelligence (AI) platform to optimize the computing performance of data-intensive tasks in an edge environment. By intelligently allocating tasks to a suitable AI edge computing platform and processing the data after edge computing, low-latency, low-power consumption, and low-cost transmission of Fab system data are achieved. This solution not only supports low-latency transmission and interaction of device process parameters, but also uses the model of the AI edge computing platform to analyze key parameters, optimize the process, and feed the results back to the user in real time. This innovation promotes the industrial digitalization and intelligentization process of the Fab system, significantly reduces the data transmission cost, and provides strong support for the transformation and upgrading of the semiconductor manufacturing industry.

[0036] In one embodiment, as Figure 2 , the machine tool data acquisition module 1 includes:

[0037] The user requirement data acquisition unit 101 is used to determine the user's parameter requirements and collect the process parameter values of each machine tool device based on the user's parameter requirements. Among them, the process parameter values include one or more of the temperature and humidity in the machine tool cavity, the liquid flow rate, and the gas concentration. These parameters are crucial for the wafer manufacturing process because they directly affect the product quality and production efficiency. The user requirement data acquisition unit 101 can implement the relevant business functions of the EAP system of the Fab system. The EAP system is a system specifically designed to achieve real-time monitoring and automated control of the machine tools in the Fab system.

[0038] The normal wafer production process screening unit 102 is connected to the user requirement data acquisition unit 101 and is used to screen the data of the normal wafer production process in the collected data by using an effective data cleaning method to eliminate the data of the R & D test process. For example, based on the data characteristics of the normal wafer production process and the R & D test process, the data of the normal wafer production process can be screened. Specifically, the data of the normal wafer production process can be screened according to the production plan and test plan time, the data-related identifiers of the production equipment and test equipment, and the formats of the production data and R & D test data.

[0039] The high-quality data screening unit 103 is connected to the normal wafer production process screening unit 102 and is used to screen the data without process problems in the screened data of the normal wafer production process by using a preprocessing method as the data meeting the high-quality standard. For example, the data with process problems can be screened by identifying the failure factors. The failure factor is the key factor that can cause process problems in the wafer production process. For example, the process problems close to the scrapped state and with large fluctuations can be judged according to the defect density, defect size, defect type, etc.

[0040] The data storage unit 104 is connected to the high-quality data screening unit 103 and is used to store the data meeting the high-quality standard screened by the high-quality data screening unit.

[0041] In an embodiment, the data analysis module 2 is an advanced artificial intelligence processing center integrated with the platform. This center deploys high-performance computing resources and advanced algorithm models and can receive and process the data of each Fab system in real time. The data is analyzed and processed through deep learning and machine learning technologies and regression prediction is performed, and the optimized solutions are fed back to different users to help users optimize the equipment performance and adjust the production plan in real time and comprehensively manage the production data.

[0042] The data analysis module 2 performs key parameter analysis on the data output by the machine data acquisition module by using a machine learning model or a deep learning model with the function of processing business data of each Fab system, and obtains the corresponding analysis results. For example, the key parameters are key parameters such as production progress, equipment status, and material consumption; the data analysis module 2 performs data processing by using a model selected according to the amount of data to be analyzed. The Fab systems mentioned here cover the YMS system, APC system, FDC system, MES system, and SPC system, and each system plays an important role in semiconductor production.

[0043] YMS system: Yield Management System, which is a system integrating data management, data analysis, and professional tools. It is mainly used in semiconductor manufacturing, packaging and testing, etc., especially in the mass production stage, which can help engineers greatly improve the data analysis efficiency, quickly analyze one or more types of data, find the key points to improve the yield, thereby promoting the stability and controllability of the entire production process, improving product quality, and reducing enterprise costs.

[0044] APC system: Advanced Process Control, which uses mathematical models and real-time data to precisely control the production process to improve product quality and production efficiency.

[0045] FDC system: Fault Detection and Classification system, which is used to monitor the equipment status in real time and diagnose faults.

[0046] MES system: Manufacturing Execution System is an indispensable part of semiconductor production. It is responsible for converting the production plan into specific production operations and monitoring the production progress and equipment status in real time.

[0047] SPC system: Statistical Process Control, which is a method of monitoring and controlling product quality by collecting and analyzing data in the production process. It is based on statistical principles, and by monitoring and predicting key parameters in the production process in real time, it helps enterprises to detect abnormal fluctuations in the production process in a timely manner, so as to take corresponding measures for adjustment and optimization.

[0048] In one embodiment, as Figure 2 , the data analysis module 2 includes:

[0049] The machine learning model prediction unit 201 is used when processing data within the standard data volume range. It utilizes a trained decision tree model, which can output accurate prediction analysis results based on the data output by the machine tool data acquisition module. The decision tree model shows the decision-making process through a tree-like structure, where each internal node represents an attribute test, each branch represents the test result, and the leaf node corresponds to the final prediction result. This model structure is clear, easy to understand, and performs well in processing structured data.

[0050] The deep learning model prediction unit 202, when processing data volume exceeding the standard range, utilizes a trained deep learning algorithm model, also based on the data of the machine tool data acquisition module, to perform prediction analysis and output the predicted analysis results. Deep learning algorithm models have significant advantages in processing large-scale and high-dimensional data. They can automatically extract complex features from the data and achieve high-precision predictions through multi-layer non-linear transformations.

[0051] By integrating the machine learning model prediction unit and the deep learning model prediction unit, the data analysis module can flexibly handle different-scale data processing requirements and provide strong support for the analysis of key parameters in the wafer production process.

[0052] In one embodiment, the types of decision tree models adopted by the machine learning algorithm model include: CatBoost model and XGBoost model;

[0053] CatBoost is a decision tree algorithm based on gradient boosting, which performs well in processing classification and regression problems, especially suitable for preliminary data analysis and model construction. It can automatically handle categorical features and reduce the risk of overfitting through a unique algorithm. CatBoost makes the model more stable during the training process and improves the prediction accuracy by introducing a symmetric tree structure. In the wafer production process, the CatBoost model can be used to predict key indicators such as equipment failure rate and product yield rate. Since it can automatically handle categorical features, it is very suitable for processing complex scenarios containing various types of data.

[0054] XGBoost is another powerful gradient boosting algorithm, which performs well in processing large-scale data and can handle missing values and categorical features. XGBoost improves the generalization ability of the model by optimizing the loss function and regularization term, and supports parallel computing, greatly improving the training speed. The XGBoost model can be used for various prediction tasks in wafer production, such as predicting the production cycle of products and the maintenance cycle of equipment. Due to its fast training speed and high accuracy, it is very suitable for processing large-scale data sets.

[0055] The deep learning algorithm model adopts a CNN or DNN model;

[0056] CNN is a convolutional neural network model, and its network structure has excellent performance in image processing. Through structures such as convolutional layers, pooling layers, and fully connected layers, CNN can automatically extract features and perform tasks such as classification or regression. CNN has a wide range of applications in fields such as image processing and video analysis. During the wafer production process, the amount of data to be analyzed is usually very large, and CNN can quickly process this data and output prediction results. This helps to promptly discover problems and take corresponding measures, thereby improving production efficiency and product quality.

[0057] DNN is a computational model that simulates the structure and function of the human brain neural network, with powerful feature learning capabilities and non-linear processing capabilities. Through multiple layers of non-linear hidden layers, it can achieve the approximation of complex functions, reaching the effect of universal approximation. DNN can automatically extract useful features from raw data, greatly improving the generalization ability of the model. During the wafer production process, DNN can be used for advanced tasks such as predicting product performance and optimizing production parameters.

[0058] In one embodiment, as Figure 2 , the data optimization module 3 includes:

[0059] The parameter adjustment and compensation unit 301 can, based on the analysis results, adjust the key process parameters in the wafer production process, such as temperature, pressure, time, etc., in real-time and accurately. The adjusted process parameter values will be fed back to the user in real-time, enabling the user to promptly understand the production status and make further optimizations and adjustments as needed. This helps to improve the transparency and efficiency of production management. And it also compensates the model parameters of the Fab system indexing algorithm model based on the analysis results. Through this optimization, the accuracy and reliability of the algorithm model can be further improved, thereby ensuring that the process parameter adjustment in the production process is more precise and effective.

[0060] The parameter adjustment and compensation unit 301 can quickly adjust the process parameter values based on the real-time analysis results. This immediate response ability helps prevent potential problems before they occur, thus reducing the triggering of OCap alarms. This unit not only adjusts the process parameters but also compensates for the Fab system indices. For example, in the APC system, the compensated system indices are the indices (which can be understood as slopes, with a value range of 0 to 1) in front of each input process parameter in the algorithm equation. This precise compensation can ensure that the production environment operates in the best state and reduce OCap alarms caused by system fluctuations or instability. By continuously monitoring and adjusting the process parameter values and compensating for the Fab system indices, this unit 301 can ensure that the equipment maintains a stable operating state during production. This helps reduce equipment failures and downtime, and improve production efficiency and product quality. In addition to ensuring the stability of equipment operation, this unit 301 can further enhance the stability of equipment operation by continuously optimizing the algorithm model and process parameter values. This helps reduce the volatility and uncertainty during production and improve the controllability and predictability of production. During the wafer production process, it may be affected by various external factors, such as temperature changes, humidity fluctuations, power fluctuations, etc. By dynamically adjusting the process parameter values and compensating for the Fab system indices, this unit 301 can, to a certain extent, offset the impact of these external factors on the equipment, thus ensuring the stability and controllability of the production process.

[0061] The model adjustment unit 302 is configured to monitor the data volume input to the data analysis module, and when the data volume is within the standard data volume range, control the data analysis module 2 to process the data using a machine learning model, and when the data volume exceeds the standard data volume range, control the data analysis module 2 to process the data using a deep learning algorithm model;

[0062] The model adjustment unit 302 can make intelligent decisions based on the real-time changes in the data volume and select an appropriate algorithm model for processing. This decision-making method can ensure the efficiency and accuracy of data processing. This unit 302 can flexibly adjust the standard data volume range according to changes in system processing capabilities and business requirements. This highly adaptable feature enables the system to handle data processing tasks of different scales and complexities.

[0063] In one embodiment, the development process of the platform includes:

[0064] Users determine the relevant parameters of the AI edge computing platform according to their own needs, and these parameters may include data processing capabilities, real-time requirements, security requirements, etc. Based on the user needs, the platform developer sets the corresponding parameters in the system to establish a foundation for subsequent system development and configuration.

[0065] Ensure that the AI edge computing platform can communicate stably and efficiently. Before introducing AI technology, test the system through traditional development modes, namely local simulation environment testing, actual simulation environment testing, and actual production environment testing, to ensure the stability and reliability of basic functions.

[0066] According to the types (such as image recognition, data analysis, prediction, etc.) and scales (such as data volume, processing speed, etc.) of business data processing tasks in each Fab system, analyze the required AI computing power requirements.

[0067] According to the AI computing power requirements, select appropriate edge computing hardware specifications, including servers, storage devices, network devices, etc. According to the hardware selection results, configure the specification parameters of the edge computing hardware, such as processor model, memory capacity, storage type, etc.

[0068] Deploy the computing, network, and storage resources of the cloud server to the edge side of each machine tool device to obtain the corresponding edge server, realizing the localization sinking of data, that is, storing and processing data in the edge area to reduce network transmission latency.

[0069] Build an algorithm model suitable for the Fab system on the edge server and deploy the AI application to provide real-time data processing and optimization services on the edge side. Specifically, the machine tool data acquisition module collects the process parameter values for processing the business data tasks of each Fab system from each machine tool device according to the user parameter requirements, and respectively screens the data belonging to the normal wafer production process and meeting the high-quality wafer standards; initially select the data for training and testing in the machine learning model. As the data volume increases (for example, when the data volume exceeds ten thousand), consider adjusting the model and switching to deep learning algorithms. These deep learning algorithms have stronger expressive and generalization abilities when dealing with large-scale and high-dimensional data. Based on in-depth data mining and analysis, we built a system model that can accurately reflect the complex relationship between equipment manufacturing processes and parameters. Through this model, we optimized the equipment manufacturing processes and parameters, significantly improving the equipment manufacturing capacity and product yield. At the same time, we also optimized the system model itself, enhancing its accuracy and robustness to ensure that it can better adapt to the actual production environment. Finally, we successfully built an algorithm model specifically designed for the Fab system on the edge server and deployed the AI application. The deployed edge server can receive and process data from each Fab system in real time, and achieve real-time analysis and optimization with the help of AI algorithms, thus greatly improving the real-time and accuracy of data processing.

[0070] The entire development process is centered around user requirements, ensuring that the AI edge computing platform can meet the actual needs of users. By deploying cloud server resources to the edge side, data transmission latency is reduced, and data processing efficiency is improved. According to the characteristics and scale of business data processing tasks, the edge computing hardware specifications and cloud server resources are flexibly configured to achieve optimized resource allocation. As the business develops and technology advances, the AI edge computing platform can be easily extended and upgraded to meet higher performance requirements.

[0071] Similar to the principle of the above embodiment, the present invention provides an AI edge computing method for the Fab system.

[0072] The following provides specific embodiments in conjunction with the accompanying drawings:

[0073] As Figure 3 Show a schematic flowchart of an AI edge computing method for the Fab system in an embodiment of the present invention.

[0074] An AI edge computing platform applied to the Fab system, which is developed based on the business data processing requirements in each Fab system, is deployed on the edge side of multiple machine tools in the wafer manufacturing plant, and is communicatively connected to each machine tool. The method includes:

[0075] Step S1: Collect the process parameter values of each machine tool according to the user parameter requirements, and screen the data that belongs to the normal wafer production process and meets the high-quality wafer standard.

[0076] In one embodiment, step S1 includes:

[0077] Determine the user parameter requirements, and collect the process parameter values of each machine tool based on the user parameter requirements; wherein, the process parameter values include one or more of the temperature and humidity in the machine tool cavity, liquid flow rate, and gas concentration;

[0078] Screen the data of the normal wafer production process in the collected data to eliminate the data of the R & D and test process;

[0079] Screen the data without process problems in the screened data of the normal wafer production process as the data that meets the high-quality standard;

[0080] Store the data that meets the high-quality standard screened by the high-quality data screening unit.

[0081] Step S2: Analyze and process the screened data by using an algorithm model with the Fab system business data processing function selected according to the amount of data to be analyzed and processed, and obtain an analysis result.

[0082] In one embodiment, step S2 includes:

[0083] Use a machine learning model or a deep learning model with the function of processing business data of each Fab system selected according to the amount of data to be analyzed by the data analysis module to analyze the key parameters of the data output by the machine tool data acquisition module, and obtain the corresponding analysis results; among them, each Fab system includes: YMS system, APC system, FDC system, MES system, and SPC system.

[0084] In one embodiment, use an algorithm model with the function of processing business data of the Fab system selected according to the amount of data to be analyzed and processed to analyze and process the screened data, and the obtained analysis results include:

[0085] When the amount of data to be analyzed is within the standard data volume range, the trained machine learning algorithm model outputs a predicted analysis result according to the data output by the machine tool data acquisition module; among them, the machine learning algorithm model uses a decision tree model;

[0086] When the amount of data to be analyzed exceeds the standard data volume range, the trained deep learning algorithm model outputs a predicted analysis result according to the data output by the machine tool data acquisition module.

[0087] In one embodiment, the types of decision tree models used by the machine learning algorithm model include: CatBoost model and XGBoost model; the types of deep learning algorithm models include: CNN or DNN model.

[0088] Step S3: Dynamically adjust the process parameter values of each machine tool device and compensate the Fab system index by using the analysis results, so as to feedback the adjusted process parameter values to the user to optimize the performance and production process of the machine tool device, and use the compensated Fab system index to optimize the model parameters of the algorithm model.

[0089] In one embodiment, step S3 includes:

[0090] Dynamically adjust the process parameter values and compensate the Fab system index by using the analysis results, and feedback the adjusted process parameter values to the user to optimize the performance and production process of the machine tool device and use the Fab system index to optimize the model parameters of the algorithm model;

[0091] Monitor the amount of data to be processed, and control the use of the machine learning model to process the data when the data volume is within the standard data volume range and control the use of the deep learning algorithm model to process the data when the data volume exceeds the standard data volume range.

[0092] In one embodiment, the development process of the AI edge computing platform for the Fab system includes: the user determines relevant parameters. After the communication of the AI edge computing platform and various tests in the traditional development mode are completed, the AI computing power requirements of the AI edge computing platform are determined according to the types and scales of business data processing tasks in each Fab system, and the corresponding appropriate edge computing hardware specifications are configured. By deploying the computing, network, and storage resources of the cloud server to the edge side of each machine device, and building an algorithm model and deploying an AI application on the edge server.

[0093] Since the implementation principle of the AI edge computing method for the Fab system has been described in the foregoing embodiments, it will not be repeated here.

[0094] The AI edge computing platform for the Fab system provided by the embodiments of the present invention can be implemented on the terminal side or the server side. For the hardware structure of the electronic terminal, please refer to Figure 4 , which is an optional hardware structure schematic diagram of the AI edge computing terminal 1000 for the Fab system provided by the embodiments of the present invention. The terminal 1000 can be a mobile phone, a computer device, a tablet device, a personal digital processing device, a factory background processing device, etc. The terminal 1000 includes: at least one processor 1001, a memory 1002, at least one network interface 10010, and a user interface 1009. Each component in the device is coupled together through a bus system 1005. It can be understood that the bus system 1005 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 1005 also includes a power bus, a control bus, and a status signal bus. However, for the sake of clarity, in Figure 4 all kinds of buses are labeled as the bus system.

[0095] Among them, the user interface 1009 can include a display, a keyboard, a mouse, a trackball, a click gun, a button, a button, a touchpad, or a touch screen, etc.

[0096] It can be understood that the memory 1002 can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM, Static Random Access Memory), synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory). The memory described in the embodiments of the present invention is intended to include but not limited to these and any other suitable categories of memories.

[0097] The memory 1002 in the embodiments of the present invention is used to store various categories of data to support the operation of the terminal 1000. Examples of these data include: any executable programs for operating on the terminal 1000, such as the operating system 10021 and application programs 10022; the operating system 10021 contains various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application programs 10022 can include various application programs, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The AI edge computing platform provided for the Fab system in the embodiments of the present invention can be included in the application programs 10022.

[0098] The method disclosed in the embodiments of the present invention above can be applied to the processor 1001 or implemented by the processor 1001. The processor 1001 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit in the hardware of the processor 1001 or the instructions in the form of software. The above-mentioned processor 1001 may be a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The processor 1001 can implement or execute each method, step, and logic block diagram disclosed in the embodiments of the present invention. The general-purpose processor 1001 may be a microprocessor or any conventional processor, etc. Combining the steps of the accessory optimization method provided in the embodiments of the present invention can be directly embodied as being completed by the hardware decoding processor, or completed by a combination of the hardware and software modules in the decoding processor. The software module may be located in a storage medium, and this storage medium is located in the memory. The processor reads the information in the memory and combines its hardware to complete the steps of the foregoing method.

[0099] In an exemplary embodiment, the terminal 1000 may be one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs) for executing the foregoing method.

[0100] Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by hardware related to a computer program. The foregoing computer program may be stored in a computer-readable storage medium. When the program is executed, it executes the steps including the above method embodiments; and the foregoing storage medium includes: various media such as ROM, RAM, magnetic disks, or optical discs that can store program codes.

[0101] In the embodiments provided by the present application, the computer-readable and writable storage medium may include a read-only memory, a random access memory, an EEPROM, a CD-ROM, or other optical disc storage devices, a magnetic disk storage device, or other magnetic storage devices, a flash memory, a USB flash drive, a mobile hard disk, or any other medium that can be used to store desired program code in the form of instructions or data structures and can be accessed by a computer. Additionally, any connection may be appropriately referred to as a computer-readable medium. For example, if instructions are sent from a website, server, or other remote source using coaxial cables, fiber optic cables, twisted pairs, digital subscriber lines (DSLs), or wireless technologies such as infrared, radio, and microwave, then the coaxial cables, fiber optic cables, twisted pairs, DSLs, or wireless technologies such as infrared, radio, and microwave are included in the definition of the medium. However, it should be understood that computer-readable and writable storage media and data storage media do not include connections, carrier waves, signals, or other transient media, but are intended to refer to non-transient, tangible storage media. As used in the application, magnetic disks and optical discs include compact discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, where magnetic disks typically replicate data magnetically, while optical discs use lasers to optically replicate data.

[0102] As Figure 5 A schematic structural diagram of an AI edge computing system in an embodiment of the present invention is shown.

[0103] The AI edge computing system is composed of a cloud server and one or more AI edge computing subsystems. Each AI edge computing subsystem is further divided into a machine set and a corresponding AI edge computing platform. The machine set is composed of multiple machine devices with close geographical locations or related functions within a wafer fabrication plant, and the AI edge computing platform is deployed near these machine devices, implemented on the edge side of each machine device in the corresponding machine set, and communicatively connected between each machine device in the corresponding machine set and the cloud server to serve as a communication bridge between each machine device and the cloud server.

[0104] Among them, each AI edge computing subsystem includes:

[0105] For each AI edge computing subsystem, the AI edge computing platform of each AI edge computing subsystem is responsible for data collection and analysis of each machine tool device in the machine tool group within the system; the AI edge computing platform collects the process parameter values of each machine tool device in the machine tool group within the system according to the user parameter requirements, and screens the data belonging to the normal wafer production process and meeting the high-quality wafer standard; then uses the algorithm model with the Fab system business data processing function selected according to the amount of data to be analyzed and processed to analyze and process the screened data to obtain the analysis result; uses the analysis result to dynamically adjust the process parameter values of each machine tool device and compensate the Fab system index, so as to feedback the adjusted process parameter values to the user to optimize the performance and production process of the machine tool device, and uses the compensated Fab system index to optimize the model parameters of the algorithm model.

[0106] Each AI edge computing platform for the Fab system can transmit the data of the platform to the cloud server according to the demand, so that the cloud server can perform backup or other analysis and processing.

[0107] Through distributed deployment in this system, the AI edge computing platform can process the data generated by the machine tool device nearby without long-distance transmission to the cloud, thus significantly reducing the data transmission delay and ensuring the response speed of application scenarios with high real-time requirements. And because the need to transmit a large amount of raw data to the cloud server is reduced, the data transmission cost and network load are reduced. In addition, for the situation of many machine tool devices and large amounts of data in the wafer fabrication plant, through the distributed deployment platform, multiple AI edge computing platforms can process the data of different machine tool devices at the same time to achieve parallel computing, improve the overall data processing speed. By reasonably allocating tasks to different edge computing platforms, the overload of a single platform can be avoided, load balancing can be achieved, and the system stability and reliability can be improved. The edge computing platform can also dynamically adjust the computing resources according to the actual demand, optimize the resource utilization rate, and reduce the energy consumption and operation cost.

[0108] The present invention has the following advantages compared with the prior art:

[0109] 1. Through the deep integration of edge computing and AI technology, the present invention realizes the real-time analysis and optimization of the process parameters of semiconductor manufacturing equipment, significantly improving the system processing efficiency and response speed. The AI model intelligently identifies and processes multi-type device data, quickly executes low-latency optimization on the edge device, greatly reducing the cloud transmission cost, and enhancing the device stability and production efficiency. At the same time, using the AI edge computing technology, the present invention performs low-latency processing and real-time analysis on the device data, intelligently analyzes and optimizes the data, automatically extracts the machine tool data and standardizes and configures it to the edge system, thereby optimizing the device process, realizing the efficient operation of the system, and further improving the factory automation level.

[0110] 2. The present invention integrates the full - process management of device data processing. From data collection, analysis to optimization feedback, automated operations are realized, greatly reducing the need for manual intervention and alleviating the workload of developers. Developers only need to write a small amount of code and adjust the model to quickly complete the deployment of the system. This standardized processing method is widely applicable to various semiconductor devices, and can help various wafer fabs achieve process optimization, and promote the production line to reach the state of efficient operation and intelligent management in a short time.

[0111] 3. Through the forward supply and feedback of data, the present invention effectively monitors the process and the operating state of the device, optimizes the device process parameters in real - time, and makes dynamic adjustments according to production requirements to improve the product yield. The system integrates functional modules such as data processing, model inference, and decision - making feedback through an edge - computing platform, ensuring the high efficiency and accuracy of device operation. Especially when dealing with complex production scenarios, it shows strong adaptability.

[0112] 4. The present invention has strong integration capabilities, covering resources such as design, development, and testing, and realizes the full - process intelligent management from data collection to optimization feedback. This technology - integrated resource ensures the low - latency response and high - performance data - processing capabilities of the system, and significantly reduces the cost of data transmission to the cloud during the industrial digital transformation of the Fab system.

[0113] In summary, the AI edge - computing platform, method, terminal, and system for the Fab system of the present invention are designed specifically for the Fab system, customized and developed according to the requirements of business data - processing tasks in each Fab system, deployed on the edge side of multiple machine tools in the wafer manufacturing factory, and communicatively connected to each machine tool. The platform can collect and screen process - parameter data that meet the high - quality wafer standards, analyze and process them using specific algorithm models, dynamically adjust the process parameters of the machine tools according to the analysis results, compensate the Fab system index, and optimize the performance of the machine tools and the production process as well as the algorithm model. By combining edge computing and AI technologies, the present invention realizes the low - latency processing and real - time analysis of the process parameters of semiconductor manufacturing equipment, improves the system processing efficiency and response speed, and at the same time integrates the full - process automated management of device data processing, reduces the need for manual intervention, and alleviates the workload of developers. Therefore, the present invention effectively overcomes various shortcomings in the prior art and has high industrial utilization value.

[0114] The above - mentioned embodiments only exemplarily illustrate the principles and effects of the present invention, rather than limiting the present invention. Any person familiar with this technology can modify or change the above - mentioned embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or changes completed by those with ordinary knowledge in the technical field without departing from the spirit and technical idea disclosed by the present invention should still be covered by the claims of the present invention.

Claims

1. An AI edge computing platform for Fab system, characterized in that: Developed based on the business data processing requirements of each Fab system, deployed on the edge of multiple machines in the wafer manufacturing plant, and connected to each machine, the platform includes: The machine data acquisition module is used to collect the process parameter values ​​of each machine equipment according to the user's parameter requirements, and screen the data belonging to the normal wafer production link and meeting the high-quality wafer standards; wherein the process parameter values ​​include: one or more of the temperature and humidity of the machine chamber, the liquid flow rate, and the gas concentration; A data analysis module, connected to the machine data acquisition module, used to analyze and process the data output by the machine data acquisition module using an algorithm model with Fab system business data processing function selected according to the amount of data to be analyzed and processed by the data analysis module to obtain an analysis result; A data optimization module, connected to the data analysis module, used to dynamically adjust the process parameter values ​​of each machine equipment and compensate the Fab system index using the analysis results output by the data analysis module, so as to feed back the adjusted process parameter values ​​to the user to optimize the performance and production process of the machine equipment, and use the compensated Fab system index to optimize the model parameters of the algorithm model in the data analysis module; and also used to adjust the type of the algorithm model used by the data analysis module based on the amount of data to be processed by the data analysis module; The data analysis module is used to analyze the key parameters of the data output by the machine data acquisition module using a machine learning model or a deep learning model with the business data processing function of each Fab system selected by the amount of data to be analyzed by the data analysis module to obtain corresponding analysis results; wherein each Fab system includes: YMS system, APC system, FDC system, MES system and SPC system; The data optimization module includes: A parameter adjustment and compensation unit, used to dynamically adjust the process parameter values ​​and compensate the Fab system index using the analysis results, and feed back the adjusted process parameter values ​​to the user to optimize the performance and production process of the machine equipment and optimize the model parameters of the algorithm model using the Fab system index; The model adjustment unit is used to monitor the amount of data input by the data analysis module, and control the data analysis module to process the data using a machine learning model when the data amount is within a standard data amount range, and control the data analysis module to process the data using a deep learning algorithm model when the data amount exceeds the standard data amount range.

2. The AI ​​edge computing platform for Fab system according to claim 1, characterized in that: The machine data acquisition module includes: A user demand data collection unit is used to determine the user parameter requirements and collect the process parameter values ​​of each machine equipment based on the user parameter requirements; wherein the process parameter values ​​include: one or more of the temperature and humidity of the machine cavity, the liquid flow rate and the gas concentration; A normal wafer production link screening unit, connected to the user demand data collection unit, is used to screen the data of the normal wafer production link in the collected data to exclude the data of the R&D test link; A high-quality data screening unit, connected to the normal wafer production link screening unit, is used to screen the data without process problems from the screened normal wafer production link data as data that meets the high-quality standard; The data storage unit is connected to the high-quality data screening unit and is used to store the data that meets the high-quality standard and is screened by the high-quality data screening unit.

3. The AI ​​edge computing platform for Fab system according to claim 1, characterized in that: The data analysis module includes: A machine learning model prediction unit, used to output a predicted analysis result based on the data output by the machine data acquisition module through a trained machine learning algorithm model when the amount of data to be analyzed is within the standard data amount range; wherein the machine learning algorithm model adopts a decision tree model; The deep learning model prediction unit is used to output the predicted analysis results based on the data output by the machine data acquisition module through the trained deep learning algorithm model when the amount of data to be analyzed exceeds the standard data amount range.

4. The AI ​​edge computing platform for Fab system according to claim 3, characterized in that: The types of tree-buffering models adopted by the machine learning algorithm model include: CatBoost model and XGBoost model; the types of deep learning algorithm models include: CNN and DNN models.

5. The AI ​​edge computing platform for Fab system according to claim 1, characterized in that: The development process of the platform includes: the user determines the relevant parameters, and after the communication of the AI ​​edge computing platform and various tests in the traditional development model are completed, the AI ​​computing power required for the AI ​​edge computing platform is determined according to the type and scale of the business data processing tasks required in each Fab system, and the corresponding appropriate edge computing hardware specifications are configured, by deploying the computing, network and storage resources of the cloud server to the edge side of each machine device, and building an algorithm model on the edge server and deploying AI applications.

6. An AI edge computing method for a Fab system, characterized in that: The AI ​​edge computing platform applied to the Fab system is developed based on the business data processing requirements of each Fab system, deployed on the edge side of multiple machine devices in the wafer manufacturing plant, and communicated with each machine device. The method includes: Collect the process parameter values ​​of each machine equipment according to the user's parameter requirements, and screen the data that belongs to the normal wafer production process and meets the high-quality wafer standards; wherein the process parameter values ​​include: one or more of the temperature and humidity of the machine chamber, the liquid flow rate, and the gas concentration; Analyze and process the screened data using an algorithm model with Fab system business data processing function selected according to the amount of data to be analyzed and processed to obtain analysis results; Dynamically adjust the process parameter values ​​of each machine equipment and compensate the Fab system index by using the analysis results, so as to provide feedback to the user on the adjusted process parameter values ​​to optimize the performance and production process of the machine equipment, and use the compensated Fab system index to optimize the model parameters of the algorithm model; The selected data is analyzed and processed using an algorithm model with Fab system business data processing function selected according to the amount of data to be analyzed and processed, and the analysis results obtained include: Use the machine learning model or deep learning model with business data processing function of each Fab system selected by the amount of data to be analyzed to analyze the key parameters of the screened data and obtain the corresponding analysis results; among which, each Fab system includes: YMS system, APC system, FDC system, MES system and SPC system; The process parameter values ​​of each machine equipment and the Fab system index are dynamically adjusted by using the analysis results, so as to provide feedback to the user on the adjusted process parameter values ​​to optimize the performance and production process of the machine equipment, and the model parameters of the algorithm model are optimized by using the compensated Fab system index, including: Dynamically adjust the process parameter values ​​and compensate the Fab system index using the analysis results, so as to feed back the adjusted process parameter values ​​to the user to optimize the performance and production process of the machine equipment and optimize the model parameters of the algorithm model using the Fab system index; Monitor the amount of input data, and control the use of machine learning models to process the data when the data amount is within the standard data amount range, and control the use of deep learning algorithm models to process the data when the data amount exceeds the standard data amount range.

7. An electronic terminal, characterized in that: include: one or more memories and one or more processors; The one or more memories are used to store computer programs; The one or more processors, connected to the memory, are configured to run the computer program to perform the method according to claim 6.

8. An AI edge computing system, characterized in that: The system includes: a cloud server and one or more AI edge computing subsystems; Among them, each AI edge computing subsystem includes: A tool group, consisting of a plurality of tool equipments in a wafer manufacturing plant; wherein each tool group is obtained by grouping tool equipments in a wafer manufacturing plant; An AI edge computing platform for the Fab system as described in claims 1 to 5 is deployed correspondingly on the edge side of the machine group; the AI ​​edge computing platform for the Fab system is communicatively connected between each machine device of the corresponding machine group and the cloud server.

Images