Product Quality Monitoring Method and Monitoring System for Semiconductor Manufacturing Factory

Abstract

The present application discloses a product quality monitoring method and a monitoring system for a semiconductor manufacturing plant. The product quality monitoring method includes: obtaining target data, where the target data includes environmental data obtained by monitoring various environmental parameters of the semiconductor manufacturing plant and quality data obtained by monitoring the quality parameters of the products manufactured by the semiconductor manufacturing plant; performing partial correlation analysis based on the environmental data and the quality data to determine key environmental parameters related to the quality parameters from among the various environmental parameters; fitting a regression equation between the key environmental parameters and the quality parameters based on the environmental data and the quality data; predicting the quality parameters according to the regression equation and / or controlling the quality parameters by adjusting the key environmental parameters. The present application can achieve precise monitoring of the quality of the products manufactured by the semiconductor manufacturing plant.

Description

Technical Field

[0001] The present application relates to the technical field of semiconductor manufacturing, and particularly relates to a method and a monitoring system for product quality monitoring in a semiconductor manufacturing factory. Background Art

[0002] As the semiconductor manufacturing process becomes more precise, the environmental requirements for semiconductor manufacturing factories (Fabrication, abbreviated as FAB) are also getting higher and higher. The quality of products produced by high-precision processes such as 28nm, 40nm, and 55nm is very sensitive to environmental changes. Major semiconductor manufacturers have begun to pay attention to the impact of environmental changes on product quality. Currently, there are frequent cases where environmental anomalies affect product quality. Through the analysis of these cases, it is found that there are phenomena where multiple environmental parameters interact with each other to jointly affect product quality. However, there is currently a lack of technology for analyzing the interaction of multiple environmental parameters, so it is impossible to accurately monitor product quality based on environmental parameters. Summary of the Invention

[0003] In view of the above problems, the present application provides a method and a monitoring system for product quality monitoring in a semiconductor manufacturing factory, aiming to accurately monitor the quality of products manufactured in a semiconductor manufacturing factory based on environmental parameters in the semiconductor manufacturing factory.

[0004] According to a first aspect of the present invention, there is provided a method for product quality monitoring in a semiconductor manufacturing factory, including:

[0005] Obtaining target data, where the target data includes environmental data obtained by monitoring multiple environmental parameters of a semiconductor manufacturing factory and quality data obtained by monitoring the quality parameters of products manufactured by the semiconductor manufacturing factory;

[0006] Performing partial correlation analysis based on the environmental data and the quality data to determine key environmental parameters related to the quality parameters from multiple environmental parameters;

[0007] Fitting a regression equation between the key environmental parameters and the quality parameters based on the environmental data and the quality data;

[0008] Predicting the quality parameters according to the regression equation and / or controlling the quality parameters by adjusting the key environmental parameters.

[0009] Optionally, the monitoring frequency of environmental parameters is lower than the monitoring frequency of quality parameters, and the matched environmental data and quality data are used for the partial correlation analysis and fitting the regression equation;

[0010] The product quality monitoring method further includes: extracting a first quantity of quality data with the closest monitoring time interval to the environmental data, and determining the mean value of the extracted first quantity of quality data as the quality data matching the environmental data.

[0011] Optionally, the monitoring frequencies of multiple environmental parameters are not exactly the same, and the monitoring frequency of the first environmental parameter is the lowest. Monitor the first environmental parameter to obtain first environmental data;

[0012] Extracting a first quantity of quality data with the closest monitoring time interval to the environmental data includes: extracting the first quantity of quality data with the closest monitoring time interval to the first environmental data.

[0013] Optionally, multiple environmental parameters include the first environmental parameter and a second environmental parameter with a monitoring frequency higher than that of the first environmental parameter. Monitor the second environmental parameter to obtain second environmental data;

[0014] The product quality monitoring method further includes: extracting a second quantity of second environmental data with the closest monitoring time interval to the first environmental data, and determining the mean value of the extracted second quantity of second environmental data as the second environmental data matching the first environmental data.

[0015] Optionally, extracting the first quantity of quality data with the closest monitoring time interval to the first environmental data includes: extracting quality data with a monitoring time interval not greater than a first duration from the first initial duration, and the first duration gradually increases from the first initial duration until the first quantity of quality data is extracted or increases to a first duration threshold when the first quantity of quality data is not extracted;

[0016] Extracting a second quantity of second environmental data with the closest monitoring time interval to the first environmental data includes: extracting second environmental data with a monitoring time interval not greater than a second duration from the second initial duration, and the second duration gradually increases from the second initial duration until the second quantity of second environmental data is extracted or increases to a second duration threshold when the second quantity of second environmental data is not extracted;

[0017] The first initial duration and the first duration threshold are determined according to the monitoring frequency of the quality parameter and are each negatively correlated with the quality parameter monitoring frequency. The second initial duration and the second duration threshold are determined according to the monitoring frequency of the second environmental parameter and are each negatively correlated with the second environmental parameter monitoring frequency.

[0018] Optionally, the first quantity is determined according to the total amount of quality data obtained by monitoring the quality parameter and there is a positive correlation between the two;

[0019] The second quantity is determined according to the total amount of second environmental data obtained by monitoring the second environmental parameter, and there is a positive correlation between the two.

[0020] Optionally, the product quality monitoring method further includes:

[0021] Determining whether the total amount of first environmental data obtained by monitoring the first environmental parameter is not less than a sample quantity threshold;

[0022] When the total amount of the monitored first environmental data is not less than the sample quantity threshold, extracting the first quantity of quality data whose monitoring time interval is closest to the monitoring time of the first environmental data, and extracting the second quantity of second environmental data whose monitoring time interval is closest to the monitoring time of the first environmental data.

[0023] Optionally, when the total amount of the monitored first environmental data is less than the sample quantity threshold, the product quality monitoring method further includes performing the following steps:

[0024] Extracting the first quantity of quality data and the second quantity of second environmental data whose monitoring time intervals are closest to the monitoring time of the first environmental data within the time period before the monitoring time of the first environmental data, so as to obtain a first set of quality data and a first set of second environmental data corresponding to the first environmental data;

[0025] Extracting the first quantity of quality data and the second quantity of second environmental data whose monitoring time intervals are closest to the monitoring time of the first environmental data within the time period after the monitoring time of the first environmental data, so as to obtain a second set of quality data and a second set of second environmental data corresponding to the first environmental data;

[0026] Taking the mean values of the first set of quality data and the first set of second environmental data corresponding to the first environmental data and the first environmental data as a set of matched environmental data and quality data, and taking the mean values of the second set of quality data and the second set of second environmental data corresponding to the first environmental data and the first environmental data as another set of matched environmental data and quality data.

[0027] Optionally, the multiple environmental parameters include parameters characterizing environmental characteristics and the waiting time between different process steps in the product manufacturing process.

[0028] According to a second aspect of the present invention, there is provided a product quality monitoring system for a semiconductor manufacturing factory, including: a processor, a memory, and a computer program stored on the memory and executable on the processor, where when the computer program is executed by the processor, it implements any one of the product quality monitoring methods described in the first aspect.

[0029] The unexpected technical effect of this application is:

[0030] The product quality monitoring method for a semiconductor manufacturing factory provided by this application includes: obtaining target data, where the target data includes environmental data obtained by monitoring various environmental parameters of the semiconductor manufacturing factory and quality data obtained by monitoring the quality parameters of the products manufactured by the semiconductor manufacturing factory; performing partial correlation analysis based on the environmental data and the quality data to determine key environmental parameters related to the quality parameters from among the various environmental parameters; fitting a regression equation between the key environmental parameters and the quality parameters based on the environmental data and the quality data; and predicting the quality parameters according to the regression equation and / or controlling the quality parameters by adjusting the key environmental parameters. Therefore, this application accurately determines the combined influence of various environmental parameters on the quality parameters through partial correlation analysis and fitting a regression equation based on big data, thereby enabling accurate monitoring of the quality of the products manufactured by the semiconductor manufacturing factory.

[0031] Further, the monitoring frequency of the environmental parameters is lower than that of the quality parameters, and the matched environmental data and quality data are used for partial correlation analysis and fitting the regression equation. The product quality monitoring method provided by this application further includes: extracting the first quantity of quality data with the closest monitoring time interval to the monitoring time of the environmental data, and determining the mean value of the extracted first quantity of quality data as the quality data matched with the environmental data, thereby solving the technical problem of the inability to match the environmental data and the quality data caused by the low monitoring frequency of the environmental parameters. In addition, the determined quality data matched with the environmental data is relatively reasonable, so that the analysis of the combined influence of various environmental parameters on the quality parameters can be more accurate.

[0032] Further, the various environmental parameters include a first environmental parameter and a second environmental parameter with a monitoring frequency higher than that of the first environmental parameter. Second environmental data is obtained by monitoring the second environmental parameter. The product quality monitoring method provided by this application further includes: extracting the second quantity of second environmental data with the closest monitoring time interval to the monitoring time of the first environmental data, and determining the mean value of the extracted second quantity of second environmental data as the second environmental data matched with the first environmental data, thereby solving the technical problem of difficult matching caused by different monitoring frequencies of the environmental parameters. Description of the Drawings

[0033] Through the following description of the embodiments of this application with reference to the drawings, the above and other objects, features, and advantages of this application will become clearer. In the drawings:

[0034] Figure 1 Shows the environmental data obtained by monitoring two exemplary environmental parameters respectively;

[0035] Figure 2 Shows the relationships between two exemplary environmental parameters and the quality data respectively;

[0036] Figure 3 A flowchart showing a product quality monitoring method according to an embodiment of the present application;

[0037] Figure 4 A schematic diagram showing a regression equation fitted according to an embodiment of the present application in a three-dimensional coordinate system;

[0038] Figure 5 A schematic diagram showing an exemplary determination of quality data matching environmental data according to the present application;

[0039] Figure 6 A schematic diagram showing an exemplary determination of quality data matching first environmental data and second environmental data according to the present application;

[0040] Figure 7 A structural block diagram showing a product quality monitoring system according to an embodiment of the present application.

[0041] Explanation of reference numerals: 1300 - Product quality monitoring system; 1310 - Memory; 1320 - Processor; 1330 - Power supply component; 1340 - Network interface; 1350 - Input / output interface. Detailed implementation manners

[0042] To facilitate the understanding of the present application, the present application will be described more comprehensively below with reference to the relevant drawings. The preferred embodiments of the present application are given in the drawings, but the present application can be implemented in different forms and is not limited to the embodiments described herein. The purpose of providing these embodiments is to make the understanding of the disclosure content of the present application more thorough and comprehensive.

[0043] In the semiconductor field, the environmental parameters of a semiconductor manufacturing factory refer to a series of environmental parameters related to production in the semiconductor manufacturing factory. The following are some common environmental parameters:

[0044] 1) Temperature and humidity, which will affect the material properties, chemical reaction rate, and stability of manufacturing equipment to a certain extent;

[0045] 2) Cleanroom class, which is a standard for measuring the number of particles in the air. For example, ISO Class 4 requires less than 352 particles greater than or equal to 0.5 microns per cubic meter. Emphasizing the cleanroom class is to prevent the performance of the products manufactured in the semiconductor manufacturing factory from being affected by pollutants in the air;

[0046] 3) Chemical purity, such as the purity of fluorine gas and chlorine gas in a semiconductor manufacturing factory. Generally, the chemicals used in semiconductor manufacturing must have extremely high purity to avoid the performance of the products manufactured in the semiconductor manufacturing factory being affected by impurities in the chemicals;

[0047] 4) The air pressure inside the factory and the electromagnetic interference level, which may affect the stability of manufacturing equipment such as ion implanters and the performance of products manufactured in semiconductor manufacturing plants.

[0048] The environmental parameters listed above are all parameters characterizing the environmental characteristics, but it should be understood that this is only a part of the parameters characterizing the environmental characteristics and does not represent a limitation on all types of parameters characterizing the environmental characteristics.

[0049] In semiconductor manufacturing, semiconductor devices are usually produced in batches (lots). If the production of semiconductor devices involves multiple process steps, a batch of intermediate structures manufactured in the previous process step needs to enter the next process step in sequence. Therefore, there is a waiting stage for an intermediate structure between different process steps. The duration of the waiting stage is the waiting time (Queue time, abbreviated as Q-Time). In the embodiments of the present application, the environmental parameters may further include the waiting time between different process steps during the product manufacturing process. This is because the intermediate structures in the semiconductor manufacturing process will be exposed to the environment of the semiconductor manufacturing plant during the waiting stage between different processes. The magnitude of the waiting time may affect different degrees of changes in the performance of the finally manufactured products. Therefore, taking the waiting time between different process steps during the product manufacturing process as an environmental parameter to analyze the factors affecting product quality will make the analysis results more accurate.

[0050] For different semiconductor devices, the environmental parameters affecting product quality may be different. Therefore, both the inspection party and the quality party hope to be able to trace and monitor the impact of environmental parameter fluctuations on quality parameters. The quality parameters mentioned here refer to the parameters characterizing the quality of products manufactured in semiconductor manufacturing plants, which can be the number of defective semiconductor devices in semiconductor devices produced in batches or the yield rate of semiconductor devices.

[0051] Currently, there are mainly two analysis schemes for the environmental parameters of semiconductor manufacturing plants. One is for the situation where the environmental data obtained by monitoring the environmental parameters of the semiconductor manufacturing plant is abnormal, and the other is for the situation where the quality data obtained by monitoring the quality parameters of the products manufactured in the semiconductor manufacturing plant is abnormal.

[0052] Specifically, the former analysis scheme mainly uses an SPC (Statistical Process Control) system to monitor the fluctuations of environmental parameters and issues an SPC alarm when the fluctuations of the environmental parameters cause the corresponding environmental data obtained by monitoring to be outside the preset range. For example, Figure 1In the (a) figure, the environmental parameter of temperature (Tem for short) is monitored at different times (Time), and when the monitored temperature data is less than 22.2 °C or greater than 23.8 °C, an SPC alarm is issued in a timely manner. The temperature data A1, A2, and A3 shown in the (a) figure are the temperature data for which the alarm is issued; for another example, Figure 1 In the (b) figure, the environmental parameter of relative humidity (RH for short) is monitored at different times, and when the monitored relative humidity data is less than 40% or greater than 46%, an SPC alarm is issued in a timely manner. The relative humidity data B1 and B2 shown in the (b) figure are the relative humidity data for which the alarm is issued. Figure 1 The abscissa of each of the (a) figure and the (b) figure represents time. Among them, the abscissa of the (a) figure marks some monitoring times, but it should be noted that the temperature is not monitored at a constant interval; the abscissa of the (b) figure does not mark the monitoring times of relative humidity, and the relative humidity data shown in the (b) figure is monitored at a frequency of twice a week. The purpose of the SPC alarm is to timely identify and respond to abnormal situations in the semiconductor manufacturing process, and prevent the occurrence and spread of product defects by sending warning messages. In the previous analysis scheme, after the SPC alarm, based on the alarm information, the fluctuation reasons of the environmental parameters are analyzed by adding test steps, and then improvement schemes are proposed according to the analyzed fluctuation reasons to ensure that the environmental parameters return to the preset range, and experience is also summarized and measures are taken to prevent the fluctuation of the environmental parameters. This analysis scheme does not conduct a correlation analysis between the environmental parameters and the product quality parameters, and it is not clear whether the fluctuation of the environmental parameters has an impact on the product quality and what kind of impact it has during the whole process, and there is a lack of an early warning mechanism.

[0053] In the latter analysis scheme, when it is determined that the abnormality of the quality data is caused by the environment of the semiconductor manufacturing factory in the case of abnormal quality data, the environmental data and the quality data are analyzed by adding test steps to determine the environmental parameters that cause the abnormality of the quality data, and then the determined environmental parameters are adjusted so that the environment of the semiconductor manufacturing factory is improved in a manner that meets the requirements of Quality Assessment (QA) until it is confirmed that the product quality returns to normal. The abnormality of the quality data means that the quality data is outside the preset range. For example, the number of defective semiconductor devices in a batch of semiconductor devices produced is greater than the defect quantity threshold. This analysis scheme requires manual collation of environmental data and quality data for analysis, with low efficiency; and the analysis method is single, lacking the technology to analyze the interaction of multiple environmental parameters.

[0054] Currently, there are frequent cases where environmental anomalies affect product quality. Figure 2The relevant data in a case are shown below. Among them, in Figure (a), the number Q of defective semiconductor devices in semiconductor devices produced in batches is indicated by a plurality of black dots in a two-dimensional coordinate system def The relationship with a parameter Environment characterizing the environmental characteristics. The number Q is indicated in the figure def As the parameter Environment increases basically at the slope shown by the dashed line, but one value of the parameter Environment corresponds to multiple values of the number Q def Therefore, the number Q def is not uniquely determined by the parameter Environment; in Figure (b), the number Q is indicated by a plurality of black dots in a two-dimensional coordinate system def The relationship with the waiting duration Q-Time. Similarly, the number Q is indicated in the figure def As the waiting duration Q-Time increases basically at the slope shown by the dashed line, but one value of the waiting duration Q-Time corresponds to multiple values of the number Q def Therefore, the number Q def is not uniquely determined by the waiting duration Q-Time. Therefore, based on Figure 2 the case shown above, it can be seen that it is of great significance to analyze the interaction of multiple environmental parameters.

[0055] Although the latter analysis scheme above analyzes the influence of environmental parameters on product quality, due to the inability to analyze the interaction of multiple environmental parameters, there is a technical problem of inaccurate analysis for cases where the interaction of multiple environmental parameters jointly affects product quality. Therefore, based on the analysis results, it is impossible to accurately predict product quality based on environmental parameters, nor can the product quality be accurately controlled by adjusting environmental parameters.

[0056] In view of this, an embodiment of the present application provides a product quality monitoring method for a semiconductor manufacturing factory. This product quality monitoring method performs partial correlation analysis based on environmental data and quality data to determine key environmental parameters related to the quality parameters of the product from multiple environmental parameters, and then fits a regression equation between the key environmental parameters and the quality parameters based on the environmental data and quality data. Thus, rapid and accurate analysis can be performed in the case of abnormal environmental data or abnormal quality data according to the regression equation, and finally, the accurate monitoring of the product quality manufactured by the semiconductor manufacturing factory can be realized.

[0057] Figure 3 The flowchart of the product quality monitoring method for a semiconductor manufacturing factory provided by the embodiment of the present application is shown. As Figure 3 shown, this product quality monitoring method includes:

[0058] Step S110: Obtain target data, where the target data includes environmental data obtained by monitoring various environmental parameters of a semiconductor manufacturing factory and quality data obtained by monitoring the quality parameters of the products manufactured by the semiconductor manufacturing factory.

[0059] Step S120: Conduct partial correlation analysis based on the environmental data and the quality data to determine the key environmental parameters related to the quality parameters from various environmental parameters.

[0060] Step S130: Fit a regression equation between the key environmental parameters and the quality parameters based on the environmental data and the quality data.

[0061] Step S140: Predict the quality parameters according to the regression equation and / or control the quality parameters by adjusting the key environmental parameters.

[0062] It should be noted that the prediction of the quality parameters according to the regression equation usually targets the situation where the environmental parameters fluctuate. That is, when the environmental parameters fluctuate, the actual values of the environmental parameters are obtained in a timely manner, and whether they affect the quality parameters is analyzed according to the regression equation, and what kind of impact is caused on the quality parameters in the case of affecting the quality parameters. This belongs to the process of tracing the cause to the result, which can give early warnings and thus help eliminate potential hazards in a timely manner. The control of the quality parameters by adjusting the key environmental parameters according to the regression equation usually targets the situation where the quality parameters fluctuate. That is, when the quality parameters fluctuate and the quality data is abnormal, the key environmental parameters are adjusted to ensure that the quality of the manufactured products meets the requirements. This process traces the cause and effect, and improves the quality of subsequent products by timely solving the problems that cause the abnormal quality data.

[0063] In an example where a parameter Environment and a waiting duration Q-Time interact to jointly affect a quantity Q def The expression of the correlation coefficient matrix Coe calculated by partial correlation analysis is shown in the following formula (1). Among them, the value in the i-th row and j-th column represents the correlation coefficient between the i-th parameter and the j-th parameter. The first parameter is the parameter Environment, the second parameter is the waiting duration Q-Time, and the third parameter is the quantity Q def ; In addition, through partial correlation analysis, the first-order partial correlation coefficient between the parameter Environment and the quantity Q def is 0.5860846986923319, and the first-order partial correlation coefficient between the waiting duration Q-Time and the quantity Q def is 0.473309053694991.

[0064] Coe = (1)

[0065] It should be noted that the correlation coefficient reflects the total correlation between two variables without controlling other variables, including direct and indirect relationships; the first-order partial correlation coefficient reflects only the direct relationship between two variables by controlling other variables. The value ranges of the correlation coefficient and the first-order partial correlation coefficient are both between -1 and 1. Among them, -1 indicates a perfect negative correlation, 1 indicates a perfect positive correlation, and 0 indicates no correlation.

[0066] Combining the above formula (1) with the calculated first-order partial correlation coefficient can determine that the parameter Environment is related to the quantity Q as a quality parameter def and there are direct and indirect relationships between them, and the waiting time Q-Time is related to the quantity Q as a quality parameter def and there are also direct and indirect relationships between them. Since the parameter Environment and the waiting time Q-Time are respectively related to the quantity Q def therefore, both the parameter Environment and the waiting time Q-Time are key environmental parameters related to the quantity Q def In this application, the fact that the key environmental parameter is related to the quality parameter means that a change in the value of the key environmental parameter will cause a change in the quality parameter.

[0067] For the example representing the correlation coefficient matrix Coe by the above formula (1), next, taking the quantity Q def as the dependent variable, the parameter Environment as one independent variable, and the waiting time Q-Time as another independent variable, a regression equation as shown in the following formula (2) is fitted by the polynomial regression algorithm.

[0068] Q def = 0.729 - 23.823×Environment + 0.303×Q-Time + 279.603×Environment 2 + 4.632×(Environment×Q-Time) - 0.003×Q-Time 2 (2)

[0069] For Figure 2 the case shown, the interaction between the parameter Environment and the waiting time Q-Time jointly affects the quantity Q def , and the fitted regression equation is represented as a surface as shown in Figure 4 in the three-dimensional coordinate system. Since Figure 4 a set of values of the parameter Environment and the waiting time Q-Time in defThis means that the fitted regression equation accurately represents the interaction between the parameter Environment and the waiting time Q-Time and the quantity Q def impact.

[0070] It should be understood that the regression equation shown in formula (2) above can only analyze the parameters Environment and the waiting time Q-Time and the quantity Q def Therefore, the regression equation can only be used for the case where the parameter Environment and the waiting time Q-Time fluctuate. def predictions, and for the quantity Q def In the event of an abnormality, determine how the parameter Environment and the waiting time Q-Time need to be adjusted. Based on this, the various environmental parameters described in step S110 are not necessarily all environmental parameters of a semiconductor manufacturing plant. In other words, the various environmental parameters described in step S110 may be some environmental parameters that are prone to fluctuations, so that the purpose of simplifying the monitoring calculation cost is achieved by reducing the number of environmental parameters. For non-fluctuating environmental parameters, even if these environmental parameters will affect the quality parameters when they fluctuate, the impact of taking a certain constant value on the quality parameters in a non-fluctuating scenario can be fitted to the constant term of the regression equation. In practice, the various environmental parameters in step S110 can be set by the user, and the monitoring data obtained by monitoring the environmental parameters can be stored in a database, and the environmental data corresponding to the required environmental parameters can be directly obtained from the database when the product quality monitoring system executes the product quality monitoring method.

[0071] The execution result of the above-mentioned step S140 can be to generate prediction information when predicting the quality parameters and further output more intuitive prediction information in the form of an analysis report, and the prediction information includes the value of the quality parameters; it can also be to generate control information when controlling the quality parameters, and the control information includes the value of the increase or decrease of the key environmental parameters. The control information can be directly output to the control device of the key environmental parameters so that the control device can quickly adjust the key environmental parameters. The control information can also be output in the form of an analysis report to inform the user how to adjust the key environmental parameters.

[0072] Due to insufficient monitoring machines or sampling manpower, the monitoring frequency of environmental parameters is usually low. For example, the monitoring frequency of temperature and humidity is twice a week respectively, and the monitoring frequency of indoor total volatile organic compounds (Total Volatile Organic Compounds, abbreviated as TVOC) is once a week. Quality parameters are usually statistically analyzed after a batch of products are produced. Therefore, the monitoring frequency of environmental parameters is lower than that of quality parameters. This may result in quality data being monitored at a certain moment while there is no monitored environmental data. As a result, there are difficulties in matching environmental data and quality data due to the sparsity of environmental data caused by the low monitoring frequency of environmental parameters. Both partial correlation analysis and fitting regression equations require matching environmental data and quality data. In response to this, an optional embodiment uses the KNN (K-Nearest Neighbors) algorithm to solve the technical problem that environmental data and quality data cannot be matched at the monitoring moment and thus cannot be analyzed. Specifically, the above product quality monitoring method further includes: extracting the first quantity of quality data with the closest monitoring time interval to the environmental data, and determining the mean value of the extracted first quantity of quality data as the quality data matching the environmental data. In a case where the environmental parameters fluctuate slightly, the mean value of the above-extracted first quantity of quality data can avoid the disturbance caused by factors other than such environmental parameters to the quality data; in a case where the environmental parameters fluctuate greatly, the mean value of the first quantity of quality data extracted for a certain environmental data can be regarded as the mean value of multiple quality data caused by multiple environmental data fluctuating around the environmental data, and thus is closer to the quality data caused by the environmental data. The method provided in the embodiments of the present application for determining the quality data matching the environmental data is relatively reasonable, and thus can make the analysis of the joint influence of multiple environmental parameters on quality parameters more accurate.

[0073] Figure 5 Shown is a schematic diagram of an exemplary determination of quality data matching environmental data. Among them, the environmental data is the data obtained by monitoring a parameter Environment representing environmental characteristics and is marked by black dots in the figure, and the quality data is the number Q of defective semiconductor devices in the semiconductor devices produced in batches and is marked by black triangles in the figure. def The data obtained and is marked by black triangles in the figure. Figure 5 It is shown that a total of five environmental data were monitored from zero o'clock on September 3, 2023 to zero o'clock on September 12, 2023 as shown on the horizontal axis. Each dotted box in the figure has an environmental data marked by a black dot, and there is also one or more dotted boxes within each dotted box. The quality data marked by black triangles within the dotted boxes is the first quantity of quality data extracted for the environmental data within the same dotted box.

[0074] Since different types of environmental parameters in a semiconductor manufacturing plant often involve different monitoring layouts and detection points, the detection frequencies of different types of environmental parameters may be different. For an example where the monitoring frequencies of multiple environmental parameters are not exactly the same, if the monitoring frequency of the first environmental parameter among the multiple environmental parameters is the lowest and the first environmental data is obtained by monitoring the first environmental parameter, then the above-mentioned extraction of the first quantity of quality data with the closest time interval to the monitoring time of the environmental data may include: extracting the first quantity of quality data with the closest time interval to the monitoring time of the first environmental data, that is, matching the environmental data with the quality data based on the first environmental data.

[0075] The multiple environmental parameters include the above-mentioned first environmental parameter and a second environmental parameter with a monitoring frequency higher than that of the first environmental parameter, and the second environmental data is obtained by monitoring the second environmental parameter. It should be understood that in the embodiments of the present application, the second environmental parameter may be one or more. The product quality monitoring method provided by the embodiments of the present application may further include: extracting the second quantity of second environmental data with the closest time interval to the monitoring time of the first environmental data, and determining the mean value of the extracted second quantity of second environmental data as the second environmental data matched with the first environmental data, thereby solving the technical problem of difficult matching caused by different monitoring frequencies of each environmental parameter for an example where the monitoring frequencies of multiple environmental parameters are not exactly the same by using the KNN algorithm again.

[0076] The above-mentioned extraction of the first quantity of quality data with the closest time interval to the monitoring time of the first environmental data may include: extracting the quality data with a time interval not greater than the first duration from the monitoring time of the first environmental data; the above-mentioned extraction of the second quantity of second environmental data with the closest time interval to the monitoring time of the first environmental data may include: extracting the second environmental data with a time interval not greater than the second duration from the monitoring time of the first environmental data.

[0077] If the time when the first environmental data is detected is denoted as Time2, and the time when the quality data or the second environmental data is detected is denoted as Time1, then the extracted quality data and the second environmental data need to satisfy the relationship shown in the following formula (3). Among them, when Time1 represents the time when the quality data is detected, Time0 is the first duration. The first duration gradually increases from the first initial duration until the first quantity of quality data is extracted, or increases to the first duration threshold when the first quantity of quality data is not extracted. In this way, by dynamically adjusting the first duration, the extracted quality data can be made as much as possible the quality data with the closest monitoring time interval to the first environmental data among the unextracted quality data. When Time1 represents the time when the second environmental data is detected, Time0 is the second duration. The above-mentioned second duration gradually increases from the second initial duration until the second quantity of the second environmental data is extracted, or increases to the second duration threshold when the second quantity of the second environmental data is not extracted. In this way, by dynamically adjusting the second duration, the extracted second environmental data can be made as much as possible the second environmental data with the closest monitoring time interval to the first environmental data among the unextracted second environmental data.

[0078] |Time2 - Time1| ≤ Time0 (3)

[0079] The above-mentioned first initial duration and the first duration threshold are determined according to the monitoring frequency of the quality parameter and are negatively correlated with the monitoring frequency of the quality parameter respectively, that is, the higher the monitoring frequency of the quality parameter, the smaller the first initial duration and the first duration threshold. The reason why the higher the monitoring frequency of the quality parameter, the smaller the first initial duration is as follows: If the first initial duration is less than the duration set according to the monitoring frequency of the quality parameter, then it is necessary to increase the first duration multiple times to query the quality data, and the efficiency of extracting the first quantity of quality is low; If the first initial duration is greater than the duration set according to the monitoring frequency of the quality parameter, then it is very likely that the total amount of quality data with a monitoring time interval not greater than the first initial duration from the first environmental data has already been greater than the first quantity, thus it is impossible to ensure that the first quantity of quality data with the closest monitoring time interval to the first environmental data is extracted. The reason why the higher the monitoring frequency of the quality parameter, the smaller the first duration threshold is as follows: If the first duration threshold is less than the duration set according to the monitoring frequency of the quality parameter, then it may be possible to extract only less than the first quantity of quality data; If the first duration threshold is greater than the duration set according to the monitoring frequency of the quality parameter, then when the adjustment step of the first duration is slightly larger, it may make the extracted quality data not the quality data with the closest monitoring time interval to the first environmental data among the unextracted quality data.

[0080] The above-mentioned second initial duration and second duration threshold are determined according to the monitoring frequency of the second environmental parameter and are each negatively correlated with the monitoring frequency of the second environmental parameter. Such a setting is conducive to efficiently extracting the second quantity of second environmental data. For the specific reasons, reference can be made to the relevant descriptions of the quality data above for understanding, and details will not be elaborated here.

[0081] The above-mentioned first quantity can be determined according to the total amount of quality data obtained from monitoring quality parameters, and there is a positive correlation between the two. The second quantity can be determined according to the total amount of second environmental data obtained from monitoring the second environmental parameter, and there is a positive correlation between the two. It should be understood that a large total amount of quality data obtained from monitoring quality parameters within the same time period indicates a high monitoring frequency of the quality parameter. Similarly, a large total amount of second environmental data obtained from monitoring the second environmental parameter within the same time period indicates a high monitoring frequency of the second environmental parameter. Therefore, the method of determining the first quantity and the second quantity here further considers the monitoring frequencies of the quality parameter and the second environmental parameter. Combining with the determination methods of the above-mentioned first initial duration and first duration threshold and the determination methods of the second initial duration and second duration threshold, it is not necessary to set large first duration threshold and second duration threshold in order to extract the first quantity of quality data and the second quantity of second environmental data. This is because when the first duration threshold and the second duration threshold are set too large, quality data and second environmental data with too large a monitoring time interval from the first environmental data will be extracted. Quality data with too large a monitoring time interval from the first environmental data is likely to have no correlation with the first environmental data. In addition, second environmental data with too large a monitoring time interval from the first environmental data is also likely to have no correlation with the first environmental data in terms of the impact on the quality data.

[0082] It should be understood that the first quantity and the second quantity can each be regarded as the K value in the KNN algorithm. The process of determining the first quantity and the second quantity above is the process of dynamically adjusting the K value according to the sample quantity.

[0083] In some examples, the product quality monitoring method provided by the embodiments of the present application may further include: determining whether the total amount of the first environmental data obtained by monitoring the first environmental parameter is not less than the sample quantity threshold; when the total amount of the monitored first environmental data is not less than the sample quantity threshold, performing the step of extracting the first quantity of quality data with the closest monitoring time interval to the monitoring time of the first environmental data, and performing the step of extracting the second quantity of second environmental data with the closest monitoring time interval to the monitoring time of the first environmental data.

[0084] Specifically, the above sample size threshold can be a preset value, which is used to measure whether the sample quantity is insufficient during the process of determining the matching quality data and the matching second environmental data of the first environmental data. If the total amount of the first environmental data is less than the sample size threshold, it indicates that there is a problem of insufficient sample quantity.

[0085] Furthermore, the product quality monitoring method provided by the embodiments of the present application may further include performing the following steps when the total amount of the monitored first environmental data is less than the sample size threshold: extracting the first quantity of quality data and the second quantity of second environmental data with the closest time interval to the monitoring time of the first environmental data within the time period before the monitoring time of the first environmental data, so as to obtain the first group of quality data and the first group of second environmental data corresponding to the first environmental data; extracting the first quantity of quality data and the second quantity of second environmental data with the closest time interval to the monitoring time of the first environmental data within the time period after the monitoring time of the first environmental data, so as to obtain the second group of quality data and the second group of second environmental data corresponding to the first environmental data; taking the mean values of the first group of quality data and the first group of second environmental data corresponding to the first environmental data and the first environmental data as a group of matching environmental data and quality data, and taking the mean values of the second group of quality data and the second group of second environmental data corresponding to the first environmental data and the first environmental data as another group of matching environmental data and quality data.

[0086] It should be noted that, in order to better extract the above first quantity of quality data within the time periods before and after the monitoring time of the first environmental data, the quality data can be extracted respectively within the first time period before and after the monitoring time of the first environmental data according to the above relevant description; similarly, in order to better extract the above second quantity of second environmental data within the time periods before and after the monitoring time of the first environmental data, the second environmental data can be extracted respectively within the second time period before and after the monitoring time of the first environmental data according to the above relevant description.

[0087] Figure 6Shown is a schematic diagram of an exemplary determination of quality data and second environmental data that match first environmental data. Here, the horizontal axis represents time, and the vertical axis represents the specific value of each data. Environmental data 1 is marked by black dots in the figure, environmental data 2 is marked by black triangles in the figure, and quality data is marked by black diamonds in the figure. Environmental data 1 serves as the first environmental data. In this example, the first quantity is 5, the second quantity is 3, the total amount of environmental data 1 is 3, and the sample size threshold is, for example, 5. Therefore, 5 quality data are respectively extracted within the first time period before and after the monitoring moment of each environmental data 1, and 3 environmental data 2 are respectively extracted within the second time period before and after the monitoring moment of each environmental data 1. Here, the first time period threshold and the second time period threshold are both, for example, 12 hours, and the time span of the dashed box in the figure is 12 hours. As Figure 6 shown, each environmental data 1 is adjacent to two dashed boxes and thus corresponds to two dashed boxes. There are a solid box and a dotted box within each dashed box. Among them, the quality data marked by black diamonds within the solid box are the first quantity of quality data extracted for the environmental data 1 corresponding to the dashed box where the solid box is located. And the quality data extracted for environmental data 1 include the first group of quality data located within the solid box before the monitoring moment of this environmental data 1 and the second group of quality data located within the solid box after the monitoring moment of this environmental data 1. The environmental data 2 marked by triangles within the dotted box are the second quantity of environmental data 2 extracted for the environmental data 1 corresponding to the dashed box where the dotted box is located. And the environmental data 2 extracted for environmental data 1 include the first group of environmental data 2 located within the dotted box before the monitoring moment of this environmental data 1 and the second group of environmental data 2 located within the dotted box after the monitoring moment of this environmental data 1.

[0088] Refer to Figure 6 , the mean values of the first group of quality data and the first group of environmental data 2 corresponding to one environmental data 1, together with this environmental data 1, serve as a set of matched environmental data and quality data, thus forming a sample for performing the partial correlation analysis in step S120 and the fitting regression equation in step S130. The mean values of the second group of quality data and the second group of environmental data 2 corresponding to the same environmental data 1, together with this environmental data 1, serve as another set of matched environmental data and quality data, thus forming a sample for the partial correlation analysis in step S120 and the fitting regression equation in step S130. It can be seen that: the same environmental data 1 can form two samples, achieving an expansion of the sample quantity. It should be noted that the two samples formed by the same environmental data 1 are of great significance for analyzing the correlation between the second environmental parameter and the quality parameter when the value of the first environmental parameter remains unchanged.

[0089] It should be noted that the first quantity and the second quantity, the first initial duration and the first duration threshold, and the second initial duration and the second duration threshold determined according to the embodiments of the present application can ensure that the required first quantity of quality data and the second quantity of second environmental data are extracted during the execution of the product quality monitoring method as much as possible. However, during the process of expanding the sample quantity, it may be impossible to extract twice the first quantity of quality data or twice the second quantity of second environmental data. For example, Figure 6 as shown, only two environmental data 2 are extracted within 12 hours after the monitoring time of the latest monitored environmental data 1. In the embodiments of the present application, for the situation where it is impossible to extract twice the first quantity of quality data or twice the second quantity of second environmental data, as long as the quality data and the second environmental data are extracted, the execution is allowed to continue. That is, as long as the average value of the extractable quality data is used as the matching quality data of the corresponding first environmental data, and similarly, as long as the average value of the extractable second environmental data is used as the matching second environmental data of the corresponding first environmental data.

[0090] The product quality monitoring method provided by the embodiments of the present application can also analyze a semiconductor manufacturing factory with only a single environmental parameter fluctuation. Specifically, the function relationship between the single environmental parameter and the quality parameter is fitted through the environmental data obtained by monitoring the single environmental parameter and the quality data obtained by monitoring the product quality parameter, and the quality data matching the monitored environmental data can be determined through the above relevant content.

[0091] Corresponding to the product quality monitoring method for a semiconductor manufacturing factory provided in the above embodiments, another embodiment of the present application provides a product quality monitoring system for a semiconductor manufacturing factory, as Figure 7 shown. The product quality monitoring system 1300 includes: a memory 1310, a processor 1320, and a program stored on the memory 1310 and executable on the processor 1320. When the program is executed by the processor 1320, it can implement each process of the above product quality monitoring method in each embodiment and achieve the same technical effect. In some examples, the product quality monitoring system 1300 may further include auxiliary sub-devices such as a power supply component 1330, a network interface 1340, and an input / output interface 1350.

[0092] The product quality monitoring system provided by the embodiments of the present application belongs to an intelligent monitoring system, which can perform correlation analysis on various environmental parameters and quality parameters, so as to explore the true relationship between the environment of a semiconductor manufacturing factory and the quality of the manufactured products through multi-angle analysis; in addition, it can support single-factor analysis and multi-factor interaction analysis, so it allows users to flexibly input relevant data of a single environmental parameter or multiple environmental parameters according to actual needs for analysis, so as to achieve corresponding single-factor monitoring or multi-factor monitoring, which is of great significance for accurately and efficiently monitoring the quality of products manufactured in a semiconductor manufacturing factory.

[0093] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by the execution of a computer program. For this reason, another embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it can implement each process of the above product quality monitoring method embodiments and can achieve the same technical effect. Among them, the computer-readable storage medium is various media that can store program codes, such as a mobile hard disk, a read-only memory (ROM for short), a random access memory (RAM for short), a magnetic disk, or an optical disc.

[0094] Finally, it should be noted that the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance. According to the embodiments of the present application as described above, these embodiments do not describe all the details in detail, nor do they limit the application to the specific embodiments described. Obviously, many modifications and changes can be made according to the above description. The present specification selects and specifically describes these embodiments to better explain the principle and practical application of the present application, so that those skilled in the art can make good use of the present application and its modifications based on the present application. The present application is only limited by the claims and their full scope and equivalents.

Claims

1. A product quality monitoring method for a semiconductor manufacturing factory, comprising: Obtaining target data, where the target data includes environmental data obtained by monitoring various environmental parameters of the semiconductor manufacturing factory and quality data obtained by monitoring the quality parameters of the products manufactured by the semiconductor manufacturing factory; Performing partial correlation analysis based on the environmental data and the quality data to determine key environmental parameters related to the quality parameters from the various environmental parameters; Fitting a regression equation between the key environmental parameters and the quality parameters based on the environmental data and the quality data; Predicting the quality parameters according to the regression equation and / or controlling the quality parameters by adjusting the key environmental parameters, wherein the monitoring frequency of the environmental parameters is lower than the monitoring frequency of the quality parameters, and the matched environmental data and quality data are used for the partial correlation analysis and fitting the regression equation; the monitoring frequencies of the various environmental parameters are not completely the same and the monitoring frequency of the first environmental parameter is the lowest, and the first environmental data is obtained by monitoring the first environmental parameter; The product quality monitoring method further includes: extracting the first quantity of quality data with the closest monitoring time interval to the environmental data, and determining the mean value of the extracted first quantity of quality data as the quality data matched with the environmental data; extracting the first quantity of quality data with the closest monitoring time interval to the environmental data includes: extracting the first quantity of quality data with the closest monitoring time interval to the first environmental data.

2. The product quality monitoring method according to claim 1, wherein, The various environmental parameters include the first environmental parameter and a second environmental parameter with a monitoring frequency higher than that of the first environmental parameter, and the second environmental data is obtained by monitoring the second environmental parameter; The product quality monitoring method further includes: extracting the second quantity of second environmental data with the closest monitoring time interval to the first environmental data, and determining the mean value of the extracted second quantity of second environmental data as the second environmental data matched with the first environmental data.

3. The product quality monitoring method according to claim 2, wherein, Extracting the first quantity of quality data with the closest monitoring time interval to the first environmental data includes: extracting the quality data with a monitoring time interval not greater than the first duration from the first environmental data, and the first duration gradually increases from the first initial duration until the first quantity of quality data is extracted or increases to the first duration threshold when the first quantity of quality data is not extracted; Extracting the second quantity of second environmental data with the closest monitoring time interval to the first environmental data includes: extracting the second environmental data with a monitoring time interval not greater than the second duration from the first environmental data, and the second duration gradually increases from the second initial duration until the second quantity of second environmental data is extracted or increases to the second duration threshold when the second quantity of second environmental data is not extracted; The first initial duration and the first duration threshold are determined according to the monitoring frequency of the quality parameter and are each negatively correlated with the quality parameter monitoring frequency. The second initial duration and the second duration threshold are determined according to the monitoring frequency of the second environmental parameter and are each negatively correlated with the second environmental parameter monitoring frequency.

4. The product quality monitoring method according to claim 3, wherein The first quantity is determined according to the total amount of quality data obtained by monitoring the quality parameter, and there is a positive correlation between the two; The second quantity is determined according to the total amount of the second environmental data obtained by monitoring the second environmental parameter, and there is a positive correlation between the two.

5. The product quality monitoring method according to claim 2, further comprising: Judging whether the total amount of the first environmental data obtained by monitoring the first environmental parameter is not less than the sample size threshold; When the total amount of the monitored first environmental data is not less than the sample size threshold, extracting the first quantity of quality data with the closest monitoring time interval to the monitoring time of the first environmental data, and extracting the second quantity of the second environmental data with the closest monitoring time interval to the monitoring time of the first environmental data.

6. The product quality monitoring method according to claim 5, further comprising performing the following steps when the total amount of the monitored first environmental data is less than the sample size threshold: Extracting the first quantity of quality data and the second quantity of the second environmental data with the closest monitoring time interval to the monitoring time of the first environmental data within the period before the monitoring time of the first environmental data, so as to obtain the first set of quality data and the first set of the second environmental data corresponding to the first environmental data; Extracting the first quantity of quality data and the second quantity of the second environmental data with the closest monitoring time interval to the monitoring time of the first environmental data within the period after the monitoring time of the first environmental data, so as to obtain the second set of quality data and the second set of the second environmental data corresponding to the first environmental data; Taking the mean values of the first set of quality data and the first set of the second environmental data corresponding to the first environmental data and the first environmental data as a set of matching environmental data and quality data, and taking the mean values of the second set of quality data and the second set of the second environmental data corresponding to the first environmental data and the first environmental data as another set of matching environmental data and quality data.

7. The product quality monitoring method according to claim 1, wherein, The multiple environmental parameters include parameters characterizing environmental characteristics and waiting durations between different process steps in the product manufacturing process.

8. A product quality monitoring system for a semiconductor manufacturing plant, comprising: A processor, a memory, and a computer program stored on the memory and executable on the processor, where when the computer program is executed by the processor, it implements the product quality monitoring method according to any one of claims 1-7.

Images