Control method and device of intelligent chip factory, controller and medium

Abstract

The invention discloses a control method and device of an intelligent chip factory, a controller and a medium, and relates to the technical field of chips. The method comprises the following steps: acquiring offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; determining virtual measurement auxiliary data according to the offline monitoring data, the online monitoring data, the process tool sensor data and the measurement tool sensor data; determining non-virtual measurement auxiliary data according to the offline monitoring data and the online monitoring data; and controlling the intelligent chip factory according to the virtual measurement auxiliary data and the non-virtual measurement auxiliary data. According to the method and the device, missed areas and blind areas caused by training data measurement deviation or insufficient sampling of the preset virtual measurement AI model are reduced, so that the preset virtual measurement AI model can have a more accurate prediction result along with data increase, the practicability of the preset virtual measurement AI model is improved, prediction is performed by using the preset virtual measurement AI model, and the prediction accuracy of the preset virtual measurement AI model is improved. And the failure rate of chip production can be effectively reduced.

Description

Technical Field

[0001] The present application relates to the field of chip technology, and in particular to a control method for an intelligent chip factory, a control device for an intelligent chip factory, a computer-readable storage medium, and a controller. Background Art

[0002] The training data of the virtual measurement AI (Artificial Intelligence) model used in the related technology is distorted, resulting in the lack of practicality of the virtual measurement results, and thus failing to reduce the failure rate of chip production. Summary of the invention

[0003] The present application aims to solve at least one of the technical problems in the related art to a certain extent. To this end, the first purpose of the present application is to propose a control method for an intelligent chip factory, the method comprising: obtaining offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; determining virtual measurement auxiliary data based on offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; determining no virtual measurement auxiliary data based on offline monitoring data and online monitoring data; controlling the intelligent chip factory based on virtual measurement auxiliary data and no virtual measurement auxiliary data. The present application reduces the blind spots of the preset virtual measurement AI model caused by the measurement deviation of the training data or insufficient sampling, makes the data closer to the real and sample appearance, enables the preset virtual measurement AI model to have more accurate prediction results as the data increases, improves the practicality of the preset virtual measurement AI model, and by using the preset virtual measurement AI model for prediction, the failure rate of chip production can be effectively reduced.

[0004] The second objective of this application is to propose a control device for an intelligent chip factory.

[0005] The third object of the present application is to provide a computer-readable storage medium.

[0006] The fourth objective of the present application is to provide a controller.

[0007] To achieve the above-mentioned objectives, the first aspect of the present application proposes a control method for a smart chip factory, the method comprising: acquiring offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; determining virtual measurement auxiliary data based on the offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; determining no virtual measurement auxiliary data based on the offline monitoring data and the online monitoring data; and controlling the smart chip factory based on the virtual measurement auxiliary data and no virtual measurement auxiliary data.

[0008] According to one embodiment of the present application, virtual measurement auxiliary data is determined based on offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data, including: determining SPC data based on offline monitoring data and online monitoring data; determining FDC data based on process tool sensor data and measurement tool sensor data; training a preset virtual measurement AI model based on the SPC data and the FDC data, wherein the preset virtual measurement AI model is used to predict product parameters of the process tool; and determining virtual measurement auxiliary data based on process tool operating parameters and the preset virtual measurement AI model.

[0009] According to one embodiment of the present application, SPC data is determined based on offline monitoring data and online monitoring data, including: obtaining a performance change trend of a measurement tool; calibrating the offline monitoring data and the online monitoring data according to the performance change trend of the measurement tool to obtain first calibration data; filtering the first calibration data, and using the first calibration data that meets corresponding preset conditions as SPC data.

[0010] According to an embodiment of the present application, the method further includes: filtering the first calibration data, and using the first calibration data that does not meet the corresponding preset conditions as first filtered data; and storing the first filtered data in a preset SPC storage unit.

[0011] According to one embodiment of the present application, FDC data is determined based on process tool sensor data and measurement tool sensor data, including: obtaining a performance change trend of the process tool sensor and a performance change trend of the measurement tool sensor; calibrating the process tool sensor data and the measurement tool sensor data according to the performance change trend of the process tool sensor and the performance change trend of the measurement tool sensor to obtain second calibration data; filtering the second calibration data, and using the second calibration data that meets corresponding preset conditions as FDC data.

[0012] According to an embodiment of the present application, the method further includes: filtering the second calibration data, and using the second calibration data that does not meet the corresponding preset conditions as second filtered data; and storing the second filtered data in a preset SPC storage unit.

[0013] According to an embodiment of the present application, the method further includes: storing the offline monitoring data and the online monitoring data in the SPC database; and storing the process tool sensor data and the measurement tool sensor data in the FDC database.

[0014] To achieve the above-mentioned objectives, the second aspect of the present application proposes a control device for a smart chip factory, the device comprising: an acquisition module for acquiring offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; a first determination module for determining virtual measurement auxiliary data based on the offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; a second determination module for determining the absence of virtual measurement auxiliary data based on the offline monitoring data and the online monitoring data; and a control module for controlling the smart chip factory based on the virtual measurement auxiliary data and the absence of virtual measurement auxiliary data.

[0015] To achieve the above objectives, the third aspect of the present application proposes a computer-readable storage medium on which a control program of a smart chip factory is stored. When the control program of the smart chip factory is executed by a processor, the control method of the smart chip factory is implemented.

[0016] To achieve the above-mentioned objectives, the fourth aspect embodiment of the present application proposes a controller, including a memory, a processor, and a control program of a smart chip factory stored in the memory and executable on the processor. When the processor executes the control program of the smart chip factory, the aforementioned control method of the smart chip factory is implemented.

[0017] According to the control method, device, controller and medium of the smart chip factory of the embodiment of the present application, offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data are obtained; virtual measurement auxiliary data is determined according to the offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data; no virtual measurement auxiliary data is determined according to the offline monitoring data and the online monitoring data; the smart chip factory is controlled according to the virtual measurement auxiliary data and no virtual measurement auxiliary data. The present application reduces the blind spots of errors caused by the measurement deviation of training data or insufficient sampling of the preset virtual measurement AI model, makes the data closer to the real and sample appearance, enables the preset virtual measurement AI model to have more accurate prediction results as the data increases, improves the practicality of the preset virtual measurement AI model, and by using the preset virtual measurement AI model for prediction, the failure rate of chip production can be effectively reduced. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of a control method of a smart chip factory according to some embodiments of the present application;

[0019] Figure 2 An analysis diagram of a control method of a smart chip factory according to some embodiments of the present application;

[0020] Figure 3 A block diagram of a control device of a smart chip factory according to some embodiments of the present application;

[0021] Figure 4 is a block diagram of a controller according to some embodiments of the present application. DETAILED DESCRIPTION

[0022] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0023] The control method, device, controller and medium of the smart chip factory in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0024] Figure 1 Flow chart of a control method of a smart chip factory according to some embodiments of the present application. Figure 1 The control method of the smart chip factory in the embodiment of the present application may include the following steps:

[0025] S110, acquiring offline monitoring data, online monitoring data, process tool sensor data, and measurement tool sensor data.

[0026] Specifically, offline monitoring data refers to control wafer data measured by measurement tools. Offline monitoring data is usually obtained at a fixed time, after process tool maintenance or fault repair. For example, taking the process tool as an oxide film deposition tool, before using the oxide film deposition tool to deposit the oxide film, after the oxide film deposition tool is maintained or repaired, it is necessary to use the oxide film deposition tool to perform the oxide film deposition operation on the control wafer, and use the measurement tool to measure the oxide film deposition thickness, uniformity and other characteristics that need to be monitored.

[0027] Online monitoring data refers to product wafer data measured by measurement tools, which can usually be obtained during the etching and chemical mechanical polishing processes, such as the depth of the oxide film after etching, the polishing thickness of chemical mechanical polishing, and the thickness of the oxide film after chemical mechanical polishing.

[0028] Measurement tool sensor data refers to the measurement tool operating parameters obtained through detection by various sensors set on the measurement tool, such as the temperature value, pressure value, light intensity and flow rate of the measurement tool. Process tool sensor data refers to the process tool operating parameters obtained through detection by various sensors set on the process tool, such as the temperature, chemical concentration, temperature and humidity in the process chamber of the process tool.

[0029] S120, determining virtual measurement auxiliary data according to the offline monitoring data, the online monitoring data, the process tool sensor data, and the measurement tool sensor data.

[0030] Specifically, the offline monitoring data, online monitoring data, process tool sensor data, and measurement tool sensor data are processed (for example, data correction and data filtering), and the processed data is used to train the preset virtual measurement AI model. In actual use, the operating parameters of the process tool are input into the preset virtual measurement AI model to determine the virtual measurement auxiliary data. For example, the operating parameters of the oxide film deposition tool are input into the preset virtual measurement AI model to predict the deposition time and deposition rate of the oxide film deposition tool when the target deposition thickness is reached, that is, the virtual measurement auxiliary data.

[0031] S130, determining that there is no virtual measurement auxiliary data according to the offline monitoring data and the online monitoring data.

[0032] Specifically, offline monitoring data and online monitoring data that have not been corrected and filtered are virtual measurement auxiliary data. Retaining the original data that have not been corrected and filtered can ensure the authenticity and integrity of the data to a certain extent and avoid information loss.

[0033] S140, controlling the smart chip factory according to the virtual measurement auxiliary data and the non-virtual measurement auxiliary data.

[0034] Specifically, both virtual measurement auxiliary data and non-virtual measurement auxiliary data are stored in the SPC (Statistic Process Control) database. When the virtual measurement auxiliary data is valid, APC (Auto Process Control) and RMS (Recipe Management System) will control the process tools based on the virtual measurement auxiliary data and non-virtual measurement auxiliary data in the SPC database, and then control the smart chip factory, which can more effectively carry out quality control and process improvement. When the virtual measurement auxiliary data is invalid, APC and RMS can control the process tools only based on the non-virtual measurement auxiliary data, and then control the smart chip factory, which can ensure the stability of the system to a certain extent.

[0035] The present application reduces the blind spots of errors caused by the measurement deviation of training data or insufficient sampling of the preset virtual measurement AI model, makes the data closer to the reality and sample appearance, enables the preset virtual measurement AI model to have more accurate prediction results as the data increases, and improves the practicality of the preset virtual measurement AI model. By using the preset virtual measurement AI model for prediction, the failure rate of chip production can be effectively reduced.

[0036] In some embodiments, virtual measurement auxiliary data is determined based on offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data, including: determining SPC data based on offline monitoring data and online monitoring data; determining FDC data based on process tool sensor data and measurement tool sensor data; training a preset virtual measurement AI model based on the SPC data and the FDC data, wherein the preset virtual measurement AI model is used to predict product parameters of the process tool; and determining virtual measurement auxiliary data based on process tool operating parameters and the preset virtual measurement AI model.

[0037] Specifically, since both offline monitoring data and online monitoring data are obtained through measurement by measurement tools, but there may be errors in the measurement of measurement tools, after obtaining offline monitoring data and online monitoring data, they need to be processed (for example, calibrated and filtered) to obtain SPC data. Similarly, since both process tool sensor data and measurement tool sensor data are obtained through sensor detection, but there may be errors in sensor detection, after obtaining process tool sensor data and measurement tool sensor data, they also need to be processed (for example, calibrated and filtered) to obtain FDC data.

[0038] Furthermore, after data cleaning, standardization and feature extraction of the SPC data and FDC data, a machine learning model is selected, such as a regression model, random forest, support vector machine, neural network, etc., and then the model is trained using the SPC data and FDC data to obtain a preset virtual measurement AI model. The trained preset virtual measurement AI model is deployed to the production environment, and the process tool operating parameters are input for real-time virtual measurement to determine the virtual measurement auxiliary data.

[0039] Exemplarily, the process tool is an oxide film deposition tool. However, it is not intended to limit the present application. When virtual measurement is not used, the oxide film deposition tool needs to be used to perform an oxide film deposition operation on the control wafer at a preset time (e.g., 24 hours), and the deposition thickness of the oxide film needs to be measured using a measurement tool. Whether the oxide film deposition tool can operate normally is determined based on the deposition thickness of the oxide film. When the oxide film deposition tool can operate normally, the oxide film deposition operation is performed on the product wafer. When virtual measurement is used, before the oxide film deposition tool performs an oxide film deposition operation on each product wafer, the operating parameters of the oxide film deposition tool can be input into a preset virtual measurement AI model to predict the corresponding relationship between the deposition time, deposition rate, and deposition thickness of the current oxide film deposition tool. The deposition time and deposition rate of the oxide film deposition tool are determined based on the target deposition thickness and the deposition corresponding relationship, i.e., virtual measurement auxiliary data. The deposition time and deposition rate determined by the virtual measurement are uploaded to the SPC database. The APC and RMS control the oxide film deposition tool to perform oxide film deposition based on the virtual measurement auxiliary data in the SPC database.

[0040] During the process of depositing oxide film on product wafers online, the operating parameters of the oxide film deposition tool when the oxide film deposition operation was performed on the previous product wafer can also be input into the preset virtual measurement AI model to predict the deposition time and deposition rate when the current product wafer reaches the target deposition thickness, that is, virtual measurement auxiliary data. The deposition time and deposition rate determined by the virtual measurement are uploaded to the SPC database, and APC and RMS control the oxide film deposition tool to perform oxide film deposition according to the virtual measurement auxiliary data in the SPC database.

[0041] It should be noted that in actual applications, the performance of the preset virtual measurement AI model should be continuously monitored, and the model should be updated according to the new SPC and FDC data to ensure the accuracy and reliability of the preset virtual measurement AI model.

[0042] In some embodiments, SPC data is determined based on offline monitoring data and online monitoring data, including: obtaining a performance change trend of a measurement tool; calibrating the offline monitoring data and the online monitoring data according to the performance change trend of the measurement tool to obtain first calibration data; filtering the first calibration data, and using the first calibration data that meets corresponding preset conditions as SPC data.

[0043] Specifically, the measuring tool may experience device aging during use, so the offline monitoring data and online monitoring data acquired by the measuring tool will gradually deviate from the actual values. Therefore, it is necessary to obtain the performance change trend of the measuring tool, and calibrate the offline monitoring data and online monitoring data according to the performance change trend of the measuring tool to obtain the first calibration data.

[0044] Exemplarily, the MMS (Measurement Management System) performs preprocessing (such as denoising, standardization, and interpolation) on the actual measurement results obtained by the measurement tool, and then uses time series analysis methods (such as moving average, exponential smoothing, ARIMA, etc.) to analyze the change trend of the actual measurement results over time, and finally identifies the key factors affecting the performance of the measurement tool through regression analysis and determines the performance change trend of the measurement tool. Then, the offline monitoring data and the online monitoring data are calibrated according to the performance change trend of the measurement tool, for example, a correction factor is determined according to the performance change trend of the measurement tool, and the corresponding correction factor is added to the offline monitoring data and the online monitoring data, and then the polynomial regression model is used for calibration to obtain the first calibration data.

[0045] Furthermore, the measurement tool may measure abnormal values ​​during the process of measuring offline monitoring data and online monitoring data. In order to weaken the influence of abnormal values ​​on the preset virtual measurement AI model, it is necessary to further filter the first calibration data, filter out the first calibration data that does not meet the corresponding preset conditions, and use the first calibration data that meets the corresponding preset conditions as SPC data. Exemplarily, the basic statistics of the first calibration data are obtained, such as obtaining the standard deviation of the first calibration data, filtering out the first calibration data outside the positive and negative 3 standard deviations, and using the first calibration data within the positive and negative 3 standard deviations as SPC data.

[0046] In some embodiments, the above method further includes: filtering the first calibration data, and using the first calibration data that does not meet the corresponding preset conditions as first filtered data; and storing the first filtered data in a preset SPC storage unit.

[0047] Specifically, when filtering the first calibration data, the first calibration data that meets the corresponding preset conditions is SPC data, and the first calibration data that does not meet the corresponding preset conditions is the first filtered data. SPC data is used to train the preset virtual measurement AI model, so that the training data is not disturbed by bias or misplaced data, and the first filtered data will be stored in the preset SPC storage unit as sample data, which is used as a synchronous verification of part of the sample data to solve the problem of insufficient samples.

[0048] In some embodiments, FDC data is determined based on process tool sensor data and measurement tool sensor data, including: obtaining a performance change trend of the process tool sensor and a performance change trend of the measurement tool sensor; calibrating the process tool sensor data and the measurement tool sensor data according to the performance change trend of the process tool sensor and the performance change trend of the measurement tool sensor to obtain second calibration data; filtering the second calibration data, and using the second calibration data that meets corresponding preset conditions as FDC data.

[0049] Specifically, the process tool sensor and the measuring tool sensor also experience device aging during use, so the process tool sensor data and the measuring tool sensor data obtained by sensor detection will gradually deviate from the actual value, so it is necessary to obtain the performance change trend of the process tool sensor and the measuring tool sensor, and calibrate the process tool sensor data and the measuring tool sensor data according to the performance change trend of the process tool sensor and the measuring tool sensor to obtain the second calibration data. It should be noted that the method for determining the sensor performance change trend and the specific process of correcting the sensor data according to the performance change trend are not described in detail here.

[0050] Furthermore, the sensor may measure abnormal values ​​in the process of detecting process tool sensor data and measurement tool sensor data. In order to weaken the influence of abnormal values ​​on the preset virtual measurement AI model, it is necessary to further filter the second calibration data, filter out the second calibration data that does not meet the corresponding preset conditions, and use the second calibration data that meets the corresponding preset conditions as FDC data. It should be noted that the filtering process of the second calibration data is the same as that of the first calibration data, which will not be repeated here.

[0051] In some embodiments, the above method further includes: filtering the second calibration data, and using the second calibration data that does not meet the corresponding preset conditions as second filtered data; and storing the second filtered data in a preset SPC storage unit.

[0052] Specifically, when filtering the second calibration data, the second calibration data that meets the corresponding preset conditions is FDC data, and the second calibration data that does not meet the corresponding preset conditions is the second filtered data. FDC data is used to train the preset virtual measurement AI model, so that the training data is not interfered by bias or misplaced data, and the second filtered data will also be stored in the preset SPC storage unit as sample data, which is used as a synchronous verification of part of the sample data to solve the problem of insufficient samples.

[0053] In this way, by adding the correction and deviation correction functions of offline monitoring data, online monitoring data, process tool sensor data, and measurement tool sensor data, the training data of the preset virtual measurement AI model can be made more accurate. By adding the filtering functions of offline monitoring data, online monitoring data, process tool sensor data, and measurement tool sensor data, the training data of the preset virtual measurement AI model can be free from interference from biased or misplaced data, thereby improving the accuracy and reliability of the preset virtual measurement AI model. In this way, the blind spots of errors caused by training data measurement deviation or insufficient sampling of the preset virtual measurement AI model are reduced, making the data closer to the real and sample appearance, so that the preset virtual measurement AI model can have more accurate prediction results as the data increases, and improve the practicality of virtual measurement.

[0054] In some embodiments, the method further includes: storing the offline monitoring data and the online monitoring data in an SPC database; and storing the process tool sensor data and the measurement tool sensor data in an FDC database.

[0055] Specifically, offline monitoring data and online monitoring data are stored in the SPC database at preset locations, and process tool sensor data and measurement tool sensor data are stored in the FDC database at preset locations. For example, the offline monitoring data of the oxide film deposition tool is stored in the preset location corresponding to the oxide film deposition tool to avoid confusion.

[0056] As a specific example, see Figure 2 , obtain offline monitoring data and online monitoring data and store them in the SPC database according to the preset corresponding positions, offset and calibrate the offline monitoring data and online monitoring data in the SPC database according to the performance change trend of the measurement tool to obtain the first calibration data, and then filter the first calibration data to obtain SPC data and first filtered data. Obtain process tool sensor data and measurement tool sensor data and store them in the FDC database according to the preset corresponding positions, offset and calibrate the process tool sensor data and measurement tool sensor data according to the performance change trend of the process tool sensor and the performance change trend of the measurement tool sensor to obtain the second calibration data, and then filter the second calibration data to obtain FDC data and second filtered data. The first filtered data and the second filtered data are stored in the preset SPC storage unit for synchronous verification of partial sample data to solve the problem of insufficient samples. The SPC data and FDC data are used to train the preset virtual measurement AI model. During use, the process tool operating parameters can be input into the preset virtual measurement AI model to predict the virtual measurement auxiliary data. The offline monitoring data and online monitoring data that have not been corrected and filtered can be used as non-virtual measurement auxiliary data. Both the virtual measurement auxiliary data and the non-virtual measurement auxiliary data are stored in the SPC database. APC and RMS will control the process tools based on the virtual measurement auxiliary data and the non-virtual measurement auxiliary data in the SPC database, and then control the smart chip factory.

[0057] In summary, this application can make the training data of the preset virtual measurement AI model more accurate by adding offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data correction and deviation correction functions. By adding offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data filtering functions, the training data of the preset virtual measurement AI model can be free from interference from biased or misplaced data, thereby improving the accuracy and reliability of the preset virtual measurement AI model. In this way, the blind spots of errors caused by training data measurement deviation or insufficient sampling of the preset virtual measurement AI model are reduced, making the data closer to reality and sample appearance, so that the preset virtual measurement AI model can have more accurate prediction results as the data increases, and improve the practicality of virtual measurement.

[0058] By using the preset virtual measurement AI model, the control wafer data after the process tool operates on the control wafer can be predicted at any time. Based on the control wafer data, it can be determined whether the process tool can operate normally, and the preparation work for the standardization of the process tool can be strengthened. When producing product wafers online, the current product wafer data can be predicted based on the previous product wafer data, and APC and RMS can be dynamically supported to adjust the production process parameters to reduce the failure rate. It can also reduce the measurement frequency of process tools or the number of product wafer samples, search for machines with poor performance or outliers in the machine group, and assist in machine evaluation to assist in the dynamic optimization of the process machine system.

[0059] Corresponding to the above embodiments, the present application also proposes a control device for an intelligent chip factory.

[0060] Reference Figure 3 The control device 300 of the smart chip factory includes: an acquisition module 310, a first determination module 320, a second determination module 330 and a control module 340.

[0061] Among them, the acquisition module 310 is used to acquire offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data. The first determination module 320 is used to determine virtual measurement auxiliary data based on the offline monitoring data, online monitoring data, process tool sensor data and measurement tool sensor data. The second determination module 330 is used to determine no virtual measurement auxiliary data based on the offline monitoring data and the online monitoring data. The control module 340 is used to control the smart chip factory based on the virtual measurement auxiliary data and no virtual measurement auxiliary data.

[0062] According to one embodiment of the present application, the first determination module 320 is specifically used to determine SPC data based on offline monitoring data and online monitoring data; determine FDC data based on process tool sensor data and measurement tool sensor data; train a preset virtual measurement AI model based on the SPC data and the FDC data, wherein the preset virtual measurement AI model is used to predict product parameters of the process tool; and determine virtual measurement auxiliary data based on process tool operating parameters and the preset virtual measurement AI model.

[0063] According to one embodiment of the present application, the first determination module 320 is also used to obtain the performance change trend of the measurement tool; calibrate the offline monitoring data and the online monitoring data according to the performance change trend of the measurement tool to obtain first calibration data; filter the first calibration data, and use the first calibration data that meets the corresponding preset conditions as SPC data.

[0064] According to an embodiment of the present application, data filtering is performed on the first calibration data, and the first calibration data that does not meet the corresponding preset conditions is used as the first filtered data; the first filtered data is stored in a preset SPC storage unit.

[0065] According to one embodiment of the present application, the first determination module 320 is also used to obtain the performance change trend of the process tool sensor and the performance change trend of the measurement tool sensor; calibrate the process tool sensor data and the measurement tool sensor data according to the performance change trend of the process tool sensor and the performance change trend of the measurement tool sensor to obtain second calibration data; filter the second calibration data, and use the second calibration data that meets the corresponding preset conditions as FDC data.

[0066] According to an embodiment of the present application, data filtering is performed on the second calibration data, and the second calibration data that does not meet the corresponding preset conditions is used as the second filtered data; the second filtered data is stored in a preset SPC storage unit.

[0067] According to an embodiment of the present application, the offline monitoring data and the online monitoring data are stored in the SPC database; and the process tool sensor data and the measurement tool sensor data are stored in the FDC database.

[0068] It should be pointed out that the above-mentioned explanation of the embodiments and beneficial effects of the control method of the smart chip factory is also applicable to the control device of the smart chip factory of the embodiment of the present application. In order to avoid redundancy, it will not be elaborated here.

[0069] Corresponding to the above embodiments, the present application also proposes a computer-readable storage medium.

[0070] The computer-readable storage medium of the present application stores a control program of a smart chip factory, and when the control program of the smart chip factory is executed by a processor, the control method of the smart chip factory described above is implemented.

[0071] It should be pointed out that the above-mentioned explanation of the embodiments and beneficial effects of the control method of the smart chip factory is also applicable to the computer-readable storage medium of the embodiment of the present application. In order to avoid redundancy, it will not be elaborated here.

[0072] Corresponding to the above embodiments, the present application also proposes a controller.

[0073] See also Figure 4 As shown, the controller 400 of the present application includes a memory 410, a processor 420, and a control program of the smart chip factory stored in the memory 410 and executable on the processor 420. When the processor 420 executes the control program of the smart chip factory, the aforementioned control method of the smart chip factory is implemented.

[0074] It should be pointed out that the above-mentioned explanation of the embodiments and beneficial effects of the control method of the smart chip factory are also applicable to the controller of the embodiment of the present application. In order to avoid redundancy, they will not be elaborated here.

[0075] It should be noted that the logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection portion with one or more wirings (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0076] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0077] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0078] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0079] In this application, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements, unless otherwise clearly defined. For ordinary technicians in this field, the specific meanings of the above terms in this application can be understood according to specific circumstances.

[0080] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limitations on the present application. Ordinary technicians in this field can change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A control method for a smart chip factory, characterized in that: The method comprises: Acquire offline monitoring data, online monitoring data, process tool sensor data, and metrology tool sensor data; determining virtual metrology auxiliary data based on the offline monitoring data, the online monitoring data, the process tool sensor data, and the metrology tool sensor data; Determine no virtual measurement auxiliary data according to the offline monitoring data and the online monitoring data; The smart chip factory is controlled according to the virtual measurement auxiliary data and the non-virtual measurement auxiliary data.

2. The control method of the smart chip factory according to claim 1, characterized in that: Determining virtual metrology auxiliary data according to the offline monitoring data, the online monitoring data, the process tool sensor data, and the metrology tool sensor data includes: Determine SPC data according to the offline monitoring data and the online monitoring data; determining FDC data based on the process tool sensor data and the metrology tool sensor data; Training a preset virtual measurement AI model according to the SPC data and the FDC data, wherein the preset virtual measurement AI model is used to predict product parameters of a process tool; The virtual measurement auxiliary data is determined according to the process tool operating parameters and the preset virtual measurement AI model.

3. The control method of the smart chip factory according to claim 2, characterized in that: Determining SPC data according to the offline monitoring data and the online monitoring data includes: Obtain performance change trends of measurement tools; Calibrate the offline monitoring data and the online monitoring data according to the performance change trend of the measurement tool to obtain first calibration data; The first calibration data is filtered, and the first calibration data satisfying corresponding preset conditions is used as the SPC data.

4. The control method of the smart chip factory according to claim 3, characterized in that: The method further comprises: Performing data filtering on the first calibration data, and using the first calibration data that does not meet corresponding preset conditions as first filtered data; The first filtering data is stored in a preset SPC storage unit.

5. The control method of the smart chip factory according to claim 2, characterized in that: Determining FDC data based on the process tool sensor data and the metrology tool sensor data includes: Obtain the performance change trend of process tool sensors and the performance change trend of measurement tool sensors; Calibrate the process tool sensor data and the measurement tool sensor data respectively according to the performance change trend of the process tool sensor and the performance change trend of the measurement tool sensor to obtain second calibration data; The second calibration data is filtered, and the second calibration data satisfying corresponding preset conditions is used as the FDC data.

6. The control method of the smart chip factory according to claim 5, characterized in that: The method further comprises: Performing data filtering on the second calibration data, and using the second calibration data that does not meet corresponding preset conditions as second filtered data; The second filtering data is stored in the preset SPC storage unit.

7. The control method of the smart chip factory according to any one of claims 1 to 6, characterized in that: The method further comprises: storing the offline monitoring data and the online monitoring data in an SPC database; The process tool sensor data and the metrology tool sensor data are stored in an FDC database.

8. A control device for a smart chip factory, characterized in that: The device comprises: An acquisition module, used to acquire offline monitoring data, online monitoring data, process tool sensor data, and measurement tool sensor data; A first determination module, configured to determine virtual measurement auxiliary data according to the offline monitoring data, the online monitoring data, the process tool sensor data and the measurement tool sensor data; A second determination module, configured to determine no virtual measurement auxiliary data according to the offline monitoring data and the online monitoring data; A control module is used to control the smart chip factory according to the virtual measurement auxiliary data and the non-virtual measurement auxiliary data.

9. A computer-readable storage medium, characterized in that: A control program of the smart chip factory is stored thereon, and when the control program of the smart chip factory is executed by a processor, the control method of the smart chip factory according to claims 1-7 is implemented.

10. A controller, characterized in that: It includes a memory, a processor, and a control program of an intelligent chip factory stored in the memory and executable on the processor. When the processor executes the control program of the intelligent chip factory, the control method of the intelligent chip factory according to claims 1-7 is implemented.

Images