Wafer yield influence factor analysis method and device, electronic equipment and storage medium

Abstract

The invention relates to a wafer yield influence factor analysis method and device, electronic equipment and a storage medium. The method comprises the steps that yield data and equipment data of batch wafers manufactured by wafer manufacturing equipment are acquired; according to the yield data of the batch wafers and the equipment data, determining a key chamber for generating low-yield wafers and a wafer set manufactured in the key chamber; according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values of the plurality of operation parameters when each wafer is manufactured, determining an influence factor analysis result of the wafer manufacturing equipment on the wafer yield, the influence factor analysis result comprises key operation parameters causing the low-yield wafer in the key chamber and parameter thresholds corresponding to the key operation parameters, and the parameter thresholds represent parameter value limits generating the low-yield wafer. Therefore, the key chamber and the key operation parameters which influence the yield can be quickly and accurately positioned, so that corresponding improvement measures can be formulated.

Description

Technical Field

[0001] The present disclosure relates to the field of semiconductor manufacturing, and in particular to a method and device for analyzing factors affecting wafer yield, an electronic device, and a storage medium. Background Art

[0002] In the wafer manufacturing process, wafer yield is an important indicator to measure production quality and efficiency. Slight deviations in each process step may lead to low product yield, high defect rate or abnormal wafer test parameters. Failure analysis is an important means for engineers to solve these problems. Through various correlation analysis methods, such as tool commonality analysis and application variance analysis (ANOVA), specific process steps and equipment (machines) that may cause abnormalities are identified.

[0003] However, the existing analysis methods are still not accurate enough to determine which equipment parameter abnormalities lead to a decrease in the overall wafer yield. And the fluctuation of equipment parameters often directly affects the wafer yield. Therefore, how to analyze and optimize the factors affecting the wafer yield in more detail to improve the wafer yield has become the focus of the current industry. Summary of the invention

[0004] In view of this, the present disclosure proposes a method and device for analyzing factors affecting wafer yield, an electronic device and a storage medium, which can combine the yield data and equipment data of batch wafers to quickly and accurately locate the key chambers and key operating parameters that affect the yield, thereby facilitating the formulation of corresponding improvement measures.

[0005] According to one aspect of the present disclosure, a method for analyzing factors affecting wafer yield is provided, comprising: obtaining yield data and equipment data of batch wafers manufactured by wafer manufacturing equipment, wherein the wafer manufacturing equipment comprises a plurality of chambers for manufacturing wafers, the yield data comprises the yield of each wafer in the batch wafers, the equipment data comprises the chamber in which each wafer in the batch wafers is manufactured and an operating parameter set of the chamber, the operating parameter set comprises parameter values ​​of a plurality of operating parameters when the wafers are manufactured in the chamber; according to the yield data and equipment data of the batch wafers, Determine a critical chamber that produces low-yield wafers and a wafer set manufactured in the critical chamber, wherein the low-yield wafers are wafers with a yield lower than a first threshold; determine an analysis result of factors affecting the wafer yield of the wafer manufacturing equipment based on the yield of each wafer in the wafer set manufactured in the critical chamber and parameter values ​​of multiple operating parameters when manufacturing each wafer, wherein the analysis result of factors affecting the wafer yield includes critical operating parameters in the critical chamber that cause low-yield wafers and parameter thresholds corresponding to the critical operating parameters, wherein the parameter thresholds represent parameter value limits that produce low-yield wafers.

[0006] In a possible implementation, the determining of the analysis result of the factors affecting the wafer yield of the wafer manufacturing equipment according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer includes: using a first analysis algorithm to determine a first analysis result according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, the first analysis result including a first operating parameter in the critical chamber that causes low-yield wafers and a parameter threshold value corresponding to the first operating parameter; using a second analysis algorithm to determine the first analysis result according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer. The first analysis result is used to determine the yield of the wafer and the parameter values ​​of multiple operating parameters when manufacturing each wafer, and the second analysis result includes the second operating parameter in the key chamber that causes the low-yield wafer and the degree of influence of the second operating parameter on the wafer yield; according to the first analysis result and the second analysis result, the analysis result of the influencing factors of the wafer manufacturing equipment on the wafer yield is determined; wherein the second operating parameter is the same or partially the same as the first operating parameter, and the analysis result of the influencing factors also includes the degree of influence of the key operating parameter in the key chamber that causes the low-yield wafer on the wafer yield and / or the result of sorting the key operating parameters according to the degree of influence.

[0007] In one possible implementation, the second analysis result is determined based on the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, including: determining the degree of influence of each of the multiple operating parameters on the wafer yield based on the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer; and determining the second operating parameter in the critical chamber that leads to low-yield wafers based on the degree of influence of each of the multiple operating parameters on the wafer yield.

[0008] In a possible implementation, the degree of influence of each of the multiple operating parameters on the wafer yield is determined according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of the multiple operating parameters when manufacturing each wafer, including: determining a first parameter group corresponding to a low-yield wafer and a second parameter group corresponding to a high-yield wafer according to the yield of each wafer in the wafer set manufactured in the critical chamber, wherein the high-yield wafer is a wafer with a yield higher than a second threshold, the second threshold is greater than the first threshold, and the first parameter group includes the yield of each low-yield wafer manufactured in the critical chamber. The first parameter group includes parameter values ​​of multiple operating parameters when manufacturing each high-yield wafer in the key chamber, and the second parameter group includes parameter values ​​of multiple operating parameters when manufacturing each high-yield wafer in the key chamber; by comparing and analyzing the first parameter group and the second parameter group, the parameter difference corresponding to each operating parameter in the multiple operating parameters is obtained, and the parameter difference characterizes the degree of difference between the parameter value of the operating parameter corresponding to the high-yield wafer and the parameter value of the operating parameter corresponding to the low-yield wafer; the parameter difference corresponding to each operating parameter in the multiple operating parameters is determined as the degree of influence of each operating parameter in the multiple operating parameters on the wafer yield.

[0009] In a possible implementation, the first analysis algorithm includes a decision tree algorithm, and the second analysis algorithm includes a T-detection algorithm.

[0010] In one possible implementation, the method also uses a decision tree algorithm to determine the key chamber that produces low-yield wafers and the wafer set manufactured in the key chamber based on the yield data and equipment data of the batch of wafers, and determines the analysis results of factors affecting the wafer yield of the wafer manufacturing equipment based on the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer.

[0011] In one possible implementation, the method further includes: generating optimization suggestions for key chambers and / or key operating parameters within key chambers in the wafer manufacturing equipment based on the analysis results of factors affecting wafer yield of the wafer manufacturing equipment; generating an analysis report based on the analysis results of the influencing factors and the optimization suggestions, and pushing the analysis report to relevant personnel, so that the relevant personnel can optimize the key chambers and / or key operating parameters within the key chambers in the wafer manufacturing equipment based on the analysis report with the goal of improving wafer yield.

[0012] According to another aspect of the present disclosure, a device for analyzing factors affecting wafer yield is provided, comprising: an acquisition module, for acquiring yield data and equipment data of batch wafers manufactured by wafer manufacturing equipment, wherein the wafer manufacturing equipment comprises a plurality of chambers for manufacturing wafers, the yield data comprises the yield of each wafer in the batch wafers, the equipment data comprises the chamber in which each wafer in the batch wafers is manufactured and an operating parameter set of the chamber, the operating parameter set comprises parameter values ​​of a plurality of operating parameters when the wafers are manufactured in the chamber; a first determination module, for determining the yield data and equipment data of the batch wafers according to the yield data and equipment data of the batch wafers; The invention discloses a method for determining a low-yield wafer by using a first determination module and a second determination module, and a method for determining a low-yield wafer by using a first determination module. The method comprises: providing data for determining a key chamber that produces low-yield wafers and a wafer set manufactured in the key chamber, wherein the low-yield wafers are wafers with a yield lower than a first threshold value; and a second determination module is used to determine an analysis result of factors affecting the wafer yield of the wafer manufacturing equipment according to the yield of each wafer in the wafer set manufactured in the key chamber and parameter values ​​of multiple operating parameters when manufacturing each wafer, wherein the analysis result of factors affecting the wafer yield includes key operating parameters in the key chamber that cause low-yield wafers and parameter thresholds corresponding to the key operating parameters, and the parameter thresholds represent parameter value limits for producing low-yield wafers.

[0013] According to another aspect of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0014] According to another aspect of the present disclosure, a non-volatile computer-readable storage medium is provided, on which computer program instructions are stored, wherein the computer program instructions implement the above method when executed by a processor.

[0015] According to another aspect of the present disclosure, a computer program product is provided, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0016] According to various aspects of the present disclosure, by acquiring the yield data and equipment data of the equipment manufacturing wafers, the key chamber that produces low-yield wafers is determined, and then based on the yield of the wafers manufactured in the key chamber and the parameter values ​​of the operating parameters, the key operating parameters and corresponding parameter thresholds that cause low-yield wafers in the key chamber can be determined, thereby achieving overall rapid and accurate positioning of the key chambers and key operating parameters and corresponding parameter thresholds that affect the yield, which is conducive to helping relevant personnel locate equipment problems in a timely manner and formulate corresponding improvement measures to effectively improve the yield of equipment manufacturing wafers on the production line.

[0017] Further features and aspects of the present disclosure will become apparent from the following detailed description of exemplary embodiments with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings, which are incorporated in and constitute a part of the specification, illustrate exemplary embodiments, features, and aspects of the disclosure and, together with the description, serve to explain the principles of the disclosure.

[0019] Figure 1 A flow chart of a method for analyzing factors affecting wafer yield according to an embodiment of the present disclosure is shown.

[0020] Figure 2 A tree-like visualization diagram of an influencing factor analysis result output by a decision tree algorithm according to an embodiment of the present disclosure is shown.

[0021] Figure 3 A block diagram of a device for analyzing factors affecting wafer yield according to an embodiment of the present disclosure is shown.

[0022] Figure 4 A block diagram of an electronic device 1900 according to an embodiment of the present disclosure is shown. DETAILED DESCRIPTION

[0023] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0024] The word “exemplary” is used exclusively herein to mean “serving as an example, example, or illustration.” Any embodiment described herein as “exemplary” is not necessarily to be construed as preferred or advantageous over other embodiments.

[0025] The term "and / or" herein is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the term "at least one" herein represents any combination of at least two of any one or more of a plurality of. For example, including at least one of A, B, and C can represent any one or more elements selected from the set consisting of A, B, and C. In the description of the present disclosure, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0026] It should be understood that the terms "first", "second", etc. in the claims, specifications and drawings of the present disclosure are used to distinguish different objects rather than to describe a specific order. The terms "include" and "comprise" used in the specifications and claims of the present disclosure indicate the presence of the described features, wholes, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or their collections.

[0027] In addition, in order to better illustrate the present disclosure, numerous specific details are given in the following specific embodiments. It should be understood by those skilled in the art that the present disclosure can also be implemented without certain specific details. In some examples, methods, means, components and circuits well known to those skilled in the art are not described in detail in order to highlight the main purpose of the present disclosure.

[0028] In practical applications, the wafer yield influencing factor analysis method of the embodiment of the present disclosure can be deployed on various terminal devices through software or hardware modification, and a rendering engine can be deployed on the terminal device. The terminal device involved in the embodiment of the present disclosure can refer to a device with a wireless connection function and / or a wired connection function. The wireless connection function refers to the ability to connect to other devices through wireless connection methods such as wifi and Bluetooth. The terminal device involved in the embodiment of the present disclosure can also communicate with other devices through a wired connection function. The terminal device involved in the embodiment of the present disclosure can be a touch screen, a non-touch screen, or a screen-free terminal device. The touch screen can be controlled by clicking and sliding on the display screen with a finger or a stylus. The non-touch screen device can be connected to an input device such as a mouse, a keyboard, a touch panel, and the terminal device is controlled by the input device. For example, the device without a screen can be a Bluetooth speaker without a screen. For example, the terminal device of the present application can include but is not limited to user equipment (UE), mobile devices, mobile terminals, handheld devices, tablet computers, laptops, PDAs, computing devices, etc.

[0029] The wafer yield influencing factor analysis method of the disclosed embodiment can also be deployed on a server, on which a rendering engine can be deployed, and the server can be located in the cloud or locally, and can be a physical device or a virtual device, such as a virtual machine, a container, etc., with a wireless communication function, wherein the wireless communication function can be set in the chip (system) or other parts or components of the server. It can refer to a device with a wireless connection function, and the wireless connection function refers to the ability to connect to other servers or terminal devices through wireless connection methods such as Wi-Fi and Bluetooth. The server involved in the disclosed embodiment can also have a wired connection for communication. For example, the server of the disclosed embodiment can be located in the cloud, communicate with the terminal device, receive the yield data and device data sent by the terminal device, and use the wafer yield influencing factor analysis method deployed on the server based on the above yield data and device data to determine the wafer yield influencing factor analysis results, and return them to the terminal device, so as to display the wafer yield influencing factor analysis results to the user in the terminal device.

[0030] Figure 1 FIG. 1 is a flow chart showing a method for analyzing factors affecting wafer yield according to an embodiment of the present disclosure. Figure 1 As shown, the method includes: step S11 to step S13.

[0031] In step S11, the yield data and equipment data of batch wafers manufactured by the wafer manufacturing equipment are obtained, wherein the wafer manufacturing equipment includes multiple chambers for manufacturing wafers, the yield data includes the yield of each wafer in the batch wafers, the equipment data includes the chamber where each wafer in the batch wafers is manufactured and the operating parameter set of the chamber, and the operating parameter set includes parameter values ​​of multiple operating parameters when manufacturing wafers in the chamber.

[0032] Among them, the wafer manufacturing equipment can be an equipment used to manufacture wafers. A wafer manufacturing equipment can include multiple chambers, each chamber can be used to manufacture at least one wafer, and the operating parameters can be the parameters used to manufacture wafers, such as temperature, pressure, content of various chemical reagents, density, etc. The types and quantities of operating parameters in the operating parameter set of the embodiment of the present disclosure are not limited.

[0033] In practical applications, yield data can come from the yield test results of the CP (Chip Probing) test site, including the classification information of high-yield wafers and low-yield wafers (that is, which are high-yield wafers and which are low-yield wafers). The CP test site can test the yield of each wafer; equipment data can be synchronously acquired through the FDC (Fault Detection and Classification) system, including the operating parameters of each chamber and the parameter values ​​of the operating parameters. The FDC system can record the parameter values ​​of the operating parameters in the chamber during the wafer manufacturing process in real time. It should be understood that the embodiments of the present disclosure do not limit the method for acquiring yield data and equipment data.

[0034] Among them, the yield data and equipment data of the batch wafers manufactured by the wafer manufacturing equipment within the cycle can be periodically obtained, or a custom trigger condition (such as when the number of low-yield wafers manufactured by the equipment exceeds a certain threshold) can be triggered to obtain the yield data and equipment data of the batch wafers manufactured by the equipment within a certain period to analyze the factors affecting the wafer yield, and the embodiments of the present disclosure are not limited to this. It should be understood that the embodiments of the present disclosure do not limit the number of wafers in the batch wafers.

[0035] Optionally, the yield data and equipment data of all wafers manufactured by the device within a certain period can be obtained, or the yield data and equipment data of some wafers manufactured by the device within a certain period can be obtained, and the partial data can include low-yield wafers with a yield lower than a first threshold and high-yield wafers with a yield higher than a second threshold, that is, the batch of wafers used in step S11 can include low-yield wafers and high-yield wafers; wherein, the first threshold is less than the second threshold, and technical personnel in this field can customize the first threshold and the second threshold according to actual needs. For example, the first threshold can be 70%, and the second threshold can be 90%, that is, the yield data and equipment data of wafers with a yield lower than 70% and wafers with a yield higher than 90% manufactured by the device can be obtained, and this is not limited to the embodiments of the present disclosure.

[0036] In actual applications, after obtaining the above-mentioned yield data and equipment data, the yield data can be associated with the equipment data, that is, the yield of the wafer can be associated with the chamber and the operating parameter set of the chamber in which the same wafer is manufactured, so as to obtain a unified data set to facilitate the subsequent analysis process; considering that there may be missing data in the yield data and the equipment data (such as the missing yield of a certain wafer, or the missing parameter value of a certain operating parameter, etc.), the missing data can be filled (such as, filled with the average value) or other data associated with the missing data can be directly eliminated, and, considering that there are many types of operating parameters in the equipment data and the numerical differences may be large, in order to facilitate the subsequent processing of the equipment data, the parameter values ​​of various operating parameters in each operating parameter set in the equipment data can also be normalized and other pre-processing operations can be performed, which are not limited to this embodiment of the present disclosure.

[0037] In step S12, based on the yield data of the batch wafers and the equipment data, the key chamber that produces low-yield wafers and the wafer set manufactured in the key chamber are determined, and the low-yield wafers are wafers with a yield lower than a first threshold.

[0038] It should be understood that the yield of each wafer in the batch of wafers and the chamber where each wafer is manufactured are known, wherein different chambers of the equipment can usually be numbered, thereby, the batch of wafers can be classified according to the chamber number, so that the wafers manufactured in each chamber and the corresponding yield of the wafers can be obtained, and then based on the first threshold for determining the low-yield wafer and the second threshold for determining the high-yield wafer, it can be determined whether each wafer manufactured in each chamber is a high-yield wafer or a low-yield wafer, and the key chamber that produces the low-yield wafer and the wafer set manufactured in the key chamber can be obtained. Alternatively, as described above, the batch of wafers can mainly include low-yield wafers and high-yield wafers, so in the above step S11, the low-yield wafers and the high-yield wafers can also be respectively classified and identified, thereby, in step S12, the key chamber that produces the low-yield wafer can also be determined based on the category identification for identifying the low-yield wafers and the high-yield wafers and the chamber number of the chamber to which each wafer belongs.

[0039] Considering that in actual situations, there are usually: chambers without low-yield wafers (such as all high-yield wafers), chambers without high-yield wafers (such as all low-yield wafers), and chambers with both high-yield wafers and low-yield wafers. For example, assuming that the batch of wafers currently analyzed has 80 wafers, of which 40 are high-yield wafers and 40 are low-yield wafers. The equipment has 3 chambers, marked as -P, -R, and -Q. By classifying the above 80 wafers according to the chamber, it may be obtained that the -P chamber contains 32 wafers, all of which are high-yield wafers (that is, there are no low-yield wafers); the -R chamber contains 28 wafers, of which 8 are high-yield wafers and 20 are low-yield wafers; the -Q chamber contains 20 wafers, all of which are low-yield wafers. Therefore, it is known that -R and -Q are the key chambers for producing low-yield wafers.

[0040] For chambers without low-yield wafers (such as all wafers in the -P chamber show high yield), it means that the chamber may not have process problems or the impact is small; for chambers without high-yield wafers (such as all wafers in the -Q chamber show low yield), it means that the chamber may have significant process problems and is a key chamber affecting the yield. This type of chamber should be inspected and dimensioned as a whole, and the process flow in the chamber should be optimized; but it is difficult to analyze separately which specific operating parameters in the chamber that will cause the wafer to have a low yield. Therefore, for key chambers that have both high-yield wafers and low-yield wafers (such as the -R chamber), the wafer collection manufactured by this type of key chamber that has both high-yield wafers and low-yield wafers (such as the -R chamber contains 28 wafers) can be used to further determine the impact of specific analysis operating parameters on wafer yield. Alternatively, if there are no chambers with both high-yield and low-yield wafers after classification, the effect of operating parameters on wafer yield can be analyzed by using the difference in parameter values ​​of operating parameters between chambers without low-yield wafers (such chambers without low-yield wafers can be understood as reference chambers) and key chambers without high-yield wafers.

[0041] In step S13, based on the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, the analysis results of the influencing factors of the wafer manufacturing equipment on the wafer yield are determined. The influencing factor analysis results include the key operating parameters in the critical chamber that lead to low-yield wafers and parameter thresholds corresponding to the key operating parameters. The parameter thresholds represent the parameter value limits that produce low-yield wafers.

[0042] As described above, the key chambers for producing low-yield wafers may include: chambers without high-yield wafers (i.e., all low-yield wafers), and / or chambers with both high-yield wafers and low-yield wafers. Among them, for the key chambers with both high-yield wafers and low-yield wafers, the parameter value difference between each operating parameter when producing high-yield wafers and each operating parameter when producing low-yield wafers in the key chamber can be analyzed to find the operating parameters with large parameter value differences (e.g., greater than a certain threshold) as the key operating parameters that lead to low-yield wafers. At the same time, it can also be found that when the key operating parameter is lower than a certain value or higher than a certain value, the wafer manufactured is a low-yield wafer, and the parameter threshold corresponding to the key operating parameter is obtained. Exemplarily, assuming that the operating parameters include temperature parameters and pressure parameters, for the 8 high-yield wafers and 20 low-yield wafers contained in the -R chamber, the parameter values ​​of the temperature parameters and the parameter values ​​of the pressure parameters corresponding to the 8 high-yield wafers contained in the -R chamber can be compared and analyzed with the parameter values ​​of the temperature parameters and the pressure values ​​of the pressure parameters corresponding to the 20 low-yield wafers, and the operating parameters with large parameter value differences (for example, greater than a certain threshold) are found as the key operating parameters that lead to low-yield wafers (for example, if the parameter values ​​corresponding to the temperature parameters are large, then the temperature parameter is the key operating parameter). At the same time, it can also be found that when the key operating parameter is lower than a certain value or higher than a certain value, the wafer manufactured is a low-yield wafer, and the parameter threshold corresponding to the key operating parameter is obtained (for example, when the temperature is higher than 35°C, the wafer produced is a low-yield wafer, and 35°C is the parameter threshold corresponding to the temperature parameter).

[0043] Among them, for the key chamber without high-yield wafers, for example, the parameter value differences of each operating parameter between the chamber without low-yield wafers and the key chamber without high-yield wafers can be calculated, and then the operating parameters with large parameter value differences (for example, greater than a certain threshold) between the two types of chambers can be found as the key operating parameters that lead to low-yield wafers. At the same time, it can also be found that the wafers manufactured when the key operating parameter is lower than a certain value or higher than a certain value are low-yield wafers, and the parameter threshold corresponding to the key operating parameter is obtained. By way of example, assuming that the operating parameters include temperature parameters and pressure parameters, the parameter values ​​of the temperature parameters and the parameter values ​​of the pressure parameters corresponding to the 32 wafers contained in the -P chamber can be compared and analyzed with the parameter values ​​of the temperature parameters and the pressure values ​​of the pressure parameters corresponding to the 20 wafers in the -Q chamber, and the operating parameters with large parameter value differences (for example, greater than a certain threshold) between the -Q chamber and the -P chamber can be found as the key operating parameters that lead to low-yield wafers, and the parameter threshold corresponding to the key operating parameter can be determined.

[0044] It should be understood that the key chambers with high-yield wafers and low-yield wafers can be used separately to analyze the implementation of the key operating parameters and corresponding parameter thresholds that affect the low-yield wafers, or the reference chamber without low-yield wafers and the key chamber without high-yield wafers can be used separately to analyze the implementation of the key operating parameters and corresponding parameter thresholds that affect the low-yield wafers. Of course, the analysis results of the above two implementations can also be used in combination to obtain the final analysis results of the influencing factors. For example, the intersection or union of the above two implementations can be taken to obtain the final analysis results of the influencing factors, and the embodiments of the present disclosure are not limited to this.

[0045] In a possible implementation, a decision tree algorithm can be used to implement the above step S12 to determine the key chamber that produces low-yield wafers and the wafer set manufactured in the key chamber according to the yield data and equipment data of the batch wafers, and the above step S13 determines the analysis results of the factors affecting the wafer yield of the wafer manufacturing equipment according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer. That is, a decision tree is used to analyze the key chambers through which low-yield wafers pass, the key operating parameters in the key chambers that cause low yields, and the parameter thresholds of the key operating parameters. In this way, the above steps S12 to S13 can be efficiently executed, and the above-mentioned influencing factor analysis results can be accurately obtained.

[0046] To facilitate understanding of the process of implementing the above steps S12 to S13 using the decision tree algorithm, the present disclosure first briefly introduces the basic principles of the decision tree algorithm. The decision tree algorithm includes: a splitting process, that is, the construction process of the decision tree starts from the root node, and the root node contains the entire data set (such as the data set generated by associating the yield data of the batch wafers and the equipment data obtained in step S11), and then the algorithm selects the splitting point according to the feature (attribute), the purpose is to divide the data set into two or more subsets, and the basis for the split is to select a feature and a certain threshold thereof (such as the number of the above chamber, the parameter threshold of the operating parameter), so that the data in the subset after the split is as "pure" as possible, that is, the target variable (such as the category label in the classification problem) is relatively concentrated; the splitting attribute (Feature Selection) mainly uses information gain (Information Gain), which is used to measure the information difference before and after the split (such as the difference in the chamber, the difference in the parameter value), specifically, the information gain can be calculated based on entropy (Entropy), and entropy is an indicator used to measure uncertainty; node splitting (Node Splitting), that is, splitting nodes into child nodes according to the selected features and thresholds, and the child nodes will continue to split until certain stopping conditions are met, such as reaching the maximum depth, too few samples in the node, or all data are pure (that is, there is only one category); Stopping Criteria, that is, the splitting of the decision tree will stop when one of the following conditions is met: reaching the preset tree depth (max depth), the number of samples in the child node after the split is less than a certain threshold (minsamples split), and the samples in the current node are already very "pure" and cannot be further effectively split. Among them, considering that the decision tree may be too complex, it is easy to cause overfitting. Pruning is the process of simplifying the generated decision tree. Pre-pruning can stop splitting during the tree generation process, and post-pruning can remove some unimportant branches after the tree is fully generated. The structure of a decision tree mainly includes the root node, which contains all the data and where the splitting begins; the internal nodes, which are each internal node representing the test condition of a feature; and the leaf nodes, which are the decision results (such as category labels or regression values).

[0047] Exemplarily, based on the above decision tree algorithm, it is assumed that the data set contains the chamber number (-P, -R, -Q) of the equipment, the operating parameter CONT_AE_FIELD and the yield category (G: high yield, B: low yield); wherein, the missing value can be filled with the mean, and the chamber (such as chamber ID) and the operating parameter CONT_AE_FIELD can be used as split attributes, based on which the decision tree algorithm can divide the wafers into multiple groups. For example: the first layer can be split according to the chamber ID (such as: chamber -P, -R, -Q), which is the first split point in the decision tree; the second layer can be further split inside each chamber using the operating parameter CONT_AE_FIELD, such as whether the operating parameter is less than a certain value (such as ≤26.987091), to continue to subdivide high-yield wafers and low-yield wafers. Through decision tree splitting, the key chambers and key operating parameter combinations that affect the yield can be analyzed, so that the performance of these wafers in different equipment chambers and the key influencing factors can be analyzed through the decision tree algorithm.

[0048] In practical applications, for example, the DecisionTreeClassifier tool can be used to build a decision tree model, and information gain can be selected as the splitting criterion, the maximum depth of the tree can be limited to 3 to avoid overfitting, and the text format of the output decision tree can be set to display the splitting process of the decision tree. The decision tree graph can also be drawn using the matplotlib tool for easy visual understanding, that is, the influencing factor analysis results output by the decision tree algorithm can be graphically visualized so that users can intuitively obtain the influencing factor analysis results of the wafer yield. For example, Figure 2 A tree-like visualization diagram of the influencing factor analysis results output by the decision tree algorithm is shown, such as Figure 2As shown, the root node of the decision tree has a total of 80 wafers (N=80), of which 40 are high-yield wafers and the other 40 are low-yield wafers. Green represents high-yield wafer c1 and red represents low-yield wafer c2. -P, -R, -Q are equipment chamber IDs, and CONT_AE_FIELD is an operating parameter; among them, based on the root node, according to the first-level factor condition (i.e., equipment chamber ID), it is divided into three intermediate nodes (i.e., chambers): -P, -R, -Q; among them, -P (green intermediate node) contains 32 wafers (N=32), all of which are high-yield wafers (c1), and there are no low-yield wafers (c2); -R (mixed color intermediate node) contains 28 wafers (N=28), of which 8 are high-yield wafers (c1) and 20 are low-yield wafers (c2:); -Q (red intermediate node) contains 20 wafers (N=20), all of which are low-yield wafers (c2). For chamber-R, according to the second-level factor conditions (i.e., the parameter value of the operating parameter), CONT_AE_FIELD is determined to be the key operating parameter, and according to the key operating parameter, it can be split into two leaf nodes, that is, under the path of chamber-R, the impact of the key operating parameter CONT_AE_FIELD on the low-yield wafers is further analyzed. It is analyzed that when CONT_AE_FIELD≤26.987091, all 20 wafers are low-yield wafers (c2), and when CONT_AE_FIELD>26.987091, all 8 wafers are high-yield wafers (c1). 26.987091 is the parameter threshold corresponding to the key operating parameter. It should be understood that for any other operating parameter, it can be determined whether it is a key operating parameter and the corresponding parameter threshold can be determined.

[0049] Understandable, through Figure 2 It can be seen intuitively that all wafers in the -P chamber show high yield, that is, high-yield wafers are mainly distributed in the -P chamber, and low-yield wafers are mainly distributed in the -Q chamber and the -R chamber. Among them, all wafers in the -Q chamber show low yield, indicating that there may be significant process problems in the chamber and it is the key chamber affecting the yield; and for the -R chamber, the -R chamber is further affected by the CONT_AE_FIELD parameter, that is, the operating parameter CONT_AE_FIELD obviously affects the yield, and when CONT_AE_FIELD≤26.987091, the wafer shows low yield, and when CONT_AE_FIELD>26.987091, the wafer shows high yield.

[0050] The decision tree algorithm does not require much data preprocessing, such as feature standardization, and can handle numerical and categorical features. The output can be explained graphically and is easy to understand. The output text of the decision tree can display the split decision based on the chamber ID and equipment parameters, helping to determine the key operating parameters that affect the yield. The decision tree graph shows the impact of different equipment chambers and operating parameters on the yield, and can intuitively see which chambers and parameters will lead to low yield. The visual display of this analysis process can help engineers quickly identify the reasons for the decline in yield and develop optimization strategies.

[0051] In practical applications, by determining the analysis results of factors affecting wafer yield, engineers can quickly identify the root cause of low yield problems and formulate targeted improvement measures, ultimately improving the overall efficiency and quality of wafer manufacturing. Therefore, after obtaining the analysis results of factors affecting wafer yield of wafer manufacturing equipment, the method may also include:

[0052] Generate optimization suggestions for key chambers and / or key operating parameters in key chambers in wafer manufacturing equipment based on the analysis results of factors affecting wafer yield of wafer manufacturing equipment;

[0053] Based on the analysis results of influencing factors and optimization suggestions, an analysis report is generated and pushed to relevant personnel so that they can optimize key chambers and / or key operating parameters in key chambers in wafer manufacturing equipment based on the analysis report with the goal of improving wafer yield.

[0054] For example, for the above Figure 2 The influencing factor analysis results shown, the generated optimization suggestions may include: 1. The setting value of the operating parameter CONT_AE_FIELD should be focused on and adjusted, especially to ensure that its value is higher than the parameter threshold 26.987091, in order to improve the yield. For example, the CONT_AE_FIELD parameter of the -R chamber can be specifically adjusted to be greater than 26.987091. 2. For chambers that show low yield (such as the -Q chamber), detailed key inspections and maintenance are required, and the process flow of the chamber is optimized. In practical applications, some suggestion templates can be set, and after obtaining the influencing factor analysis results, the influencing factor analysis results are combined with the corresponding suggestion templates to generate optimization suggestions; or, the large language model in the field of artificial intelligence can be used to realize the analysis results of the influencing factors of the wafer manufacturing equipment on the wafer yield, and generate optimization suggestions for key chambers in the wafer manufacturing equipment and / or key operating parameters in the key chambers, which are not limited to the embodiments of the present disclosure.

[0055] It should be understood that the analysis report may include the above-mentioned analysis results of the influencing factors and optimization suggestions. The embodiment of the present disclosure does not limit the style, layout and push method of the analysis report. For example, the analysis report can be pushed to relevant personnel through any push method such as email, short message or application, and the relevant personnel can be engineers for maintaining and managing wafer manufacturing equipment, so that engineers can timely optimize the process flow of key chambers and / or adjust the parameter values ​​of key operating parameters used in key chambers according to the analysis report. In actual production, the effect of optimization can also be verified, and further iterative optimization can be performed according to the verification results until the predetermined goal is achieved. For example, after optimization, the yield of wafers produced in the -R chamber is increased to more than 90%, the low yield problem of the -Q chamber is significantly improved, and the overall production yield is increased by about 15%, etc. The embodiment of the present disclosure does not limit this.

[0056] According to the method of the embodiment of the present disclosure, by acquiring the yield data and equipment data of the equipment manufacturing wafers, the key chamber that produces low-yield wafers is determined, and then based on the yield of the wafers manufactured in the key chamber and the parameter values ​​of the operating parameters, the key operating parameters and corresponding parameter thresholds that cause the low-yield wafers in the key chamber can be determined, so as to quickly and accurately locate the key chambers and key operating parameters and corresponding parameter thresholds that affect the yield, thereby helping relevant personnel to locate equipment problems in a timely manner and formulate corresponding improvement measures to effectively improve the yield of equipment manufacturing wafers on the production line.

[0057] As described above, a decision tree algorithm may be used to determine the analysis results of the factors affecting the wafer yield of wafer manufacturing equipment. Considering that only using the decision tree algorithm may make the analysis results of the factors affecting the wafer yield not comprehensive enough, for example, when multiple key operating parameters are determined, it is impossible to know the degree of influence (or priority) of each key operating parameter on the wafer yield, and it is impossible for engineers to know the order of checking each key operating parameter. For example, the higher the degree of influence of the key operating parameter, the more it should be checked first, and the lower the degree of influence of the key operating parameter, the later it can be checked. Therefore, in a possible implementation, the above step S13, according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, determines the analysis results of the factors affecting the wafer manufacturing equipment on the wafer yield, which may include:

[0058] Step S131, using a first analysis algorithm to determine a first analysis result according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, wherein the first analysis result includes a first operating parameter in the key chamber that causes a low-yield wafer and a parameter threshold corresponding to the first operating parameter;

[0059] Step S132, using a second analysis algorithm to determine a second analysis result according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, wherein the second analysis result includes a second operating parameter in the key chamber that causes a low-yield wafer and the degree of influence of the second operating parameter on the wafer yield;

[0060] Step S133, determining the analysis result of the factors affecting the wafer yield of the wafer manufacturing equipment according to the first analysis result and the second analysis result;

[0061] Among them, the second operating parameter is the same or partially the same as the first operating parameter, and the influencing factor analysis result also includes the degree of influence of the key operating parameters in the key chamber that cause low-yield wafers on the wafer yield and / or the results of sorting the key operating parameters according to the degree of influence.

[0062] In step S131, the first analysis algorithm may adopt a decision tree algorithm, that is, the implementation method of using the decision tree algorithm to determine the key operating parameters affecting the yield in the key chamber in the above step S13 may be referred to to achieve the determination of the first operating parameter in the key chamber that causes low-yield wafers and the parameter threshold value corresponding to the first operating parameter. That is, the decision tree algorithm may be used to implement the above steps S12 and S131 to obtain the first analysis result of the influencing factor analysis using the decision tree algorithm, which will not be elaborated here.

[0063] In step S132, the second analysis algorithm may adopt, for example, a T detection algorithm, or a machine learning algorithm such as a random forest algorithm or a support vector machine algorithm, to achieve determination of the second operating parameter in the critical chamber that causes low-yield wafers and the degree of influence of the second operating parameter on the wafer yield based on the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer. The embodiments of the present disclosure are not limited to this.

[0064] Optionally, the above step S132 determines the second analysis result according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, which may include:

[0065] Step S1321, determining the influence of each of the multiple operating parameters on the wafer yield according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of the multiple operating parameters when manufacturing each wafer;

[0066] Step S1322, determining a second operating parameter in the key chamber that causes low-yield wafers according to the degree of influence of each operating parameter among the multiple operating parameters on the wafer yield.

[0067] In step S1321, according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, determining the influence degree of each operating parameter in the multiple operating parameters on the wafer yield may include:

[0068] Step S13211, according to the yield of each wafer in the wafer set manufactured in the key chamber, determine a first parameter group corresponding to the low-yield wafer and a second parameter group corresponding to the high-yield wafer, the first parameter group including parameter values ​​of multiple operating parameters when each low-yield wafer is manufactured in the key chamber, and the second parameter group including parameter values ​​of multiple operating parameters when each high-yield wafer is manufactured in the key chamber;

[0069] Step S13212, by comparing and analyzing the first parameter group and the second parameter group, obtaining parameter differences corresponding to each of the multiple operating parameters, wherein the parameter differences represent the degree of difference between the parameter values ​​of the operating parameters corresponding to the high-yield wafer and the parameter values ​​of the operating parameters corresponding to the low-yield wafer;

[0070] Step S13213, determining the parameter difference corresponding to each of the multiple operating parameters as the influence degree of each of the multiple operating parameters on the wafer yield.

[0071] In step S13211, the critical chamber may be a chamber that has both high-yield wafers and low-yield wafers (such as an -R chamber). The high-yield wafers and low-yield wafers in the critical chamber are known, and the operating parameters of the wafers can be divided into two groups, namely, a first parameter group corresponding to the low-yield wafers and a second parameter group corresponding to the high-yield wafers. For example, assuming that the operating parameters include temperature parameters and pressure parameters, for the 8 high-yield wafers and 20 low-yield wafers in the -R chamber, the first parameter group corresponding to the low-yield wafers includes the parameter values ​​of the temperature parameters and the parameter values ​​of the pressure parameters corresponding to each of the 20 low-yield wafers, and the second parameter group corresponding to the high-yield wafers includes the parameter values ​​of the temperature parameters and the parameter values ​​of the pressure parameters corresponding to each of the 8 high-yield wafers.

[0072] In step S13212, for example, a T-test algorithm may be used to compare and analyze the first parameter group and the second parameter group. The T-test algorithm is an algorithm that can be used to determine whether there is a significant difference between the means of two groups of data. Specifically, for each operating parameter, the T-test algorithm shown in formula (1) may be used to calculate the parameter difference T corresponding to each operating parameter:

[0073]

[0074] in, represents the mean value of a parameter value of a certain operating parameter in the first parameter group (such as the mean value of the temperature parameter of the low-yield wafer), represents the mean value of the parameter value of the same operating parameter in the second parameter group (such as the mean value of the parameter value of the temperature parameter of the high-yield wafer), n1 represents the number of parameter values ​​of a certain operating parameter in the first parameter group (that is, the number of low-yield wafers corresponding to the first parameter group), n2 represents the number of parameter values ​​of the same operating parameter in the second parameter group (that is, the number of high-yield wafers corresponding to the second parameter group), represents the pooled variance, where Formula (2) can be used:

[0075]

[0076] in, represents the variance of the parameter value of a certain operating parameter in the first parameter group (such as the variance of the parameter value of the temperature parameter of the low-yield wafer), Represents the variance of parameter values ​​of the same operating parameter in the second parameter group (eg, the variance of parameter values ​​of temperature parameters of high-yield wafers).

[0077] It should be understood that the above-mentioned use of the T detection algorithm to calculate the parameter difference corresponding to the operating parameter is a possible implementation method provided by the public embodiment of the present invention. In fact, those skilled in the art may also adopt other known difference calculation methods in the art. For example, the difference or variance value or mean square error value between the means of the parameter values ​​of the same operating parameter in the first parameter group and the second parameter group may be calculated as the parameter difference corresponding to the operating parameter. Alternatively, other known machine learning algorithms in the art (such as random forest, support vector machine, etc.) may be used to determine the parameter difference corresponding to each operation, and the present embodiment of the present invention is not limited to this.

[0078] Among them, the greater the parameter difference of the operating parameter, the greater the impact of the operating parameter on the wafer yield, and the more likely the operating parameter is to cause the wafer to have a low yield. Therefore, the parameter difference corresponding to each of the multiple operating parameters can be determined as the impact of each of the multiple operating parameters on the wafer yield.

[0079] In step S1322, for example, based on the degree of influence of each operating parameter among the multiple operating parameters on the wafer yield, an operating parameter whose influence is greater than a certain threshold value can be selected as the second operating parameter that causes low-yield wafers; or, based on the degree of influence of each operating parameter among the multiple operating parameters on the wafer yield, the multiple operating parameters can be sorted (such as in descending order), and then based on the result of the descending order, the operating parameter ranked in the top m in terms of influence can be selected as the determined second operating parameter, and the second operating parameter is also an operating parameter with a significant difference, which is not limited to this embodiment of the present disclosure.

[0080] Optionally, the second operating parameter determined above can also be directly marked as a key operating parameter affecting the wafer yield, that is, the implementation method of the above steps S1321 to S1322 can also be directly referred to to determine the analysis results of the factors affecting the wafer yield of the wafer manufacturing equipment, that is, the second operating parameter that causes the low-yield wafer in the key chamber in the determined second analysis result can be used as the key operating parameter, and then according to the parameter value of the determined key operating parameter, the parameter threshold corresponding to the key operating parameter is determined, and the embodiment of the present disclosure is not limited to this. Exemplarily, for the 28 wafers in the above-R chamber, they can be divided into a first parameter group corresponding to 20 low-yield wafers and a second parameter group corresponding to 8 high-yield wafers, and then the parameter difference between the parameter values ​​of the two parameter groups can be compared by the T detection algorithm. If it is found that the parameter value of the temperature parameter is significantly different between the two parameter groups (that is, the parameter difference is large), the temperature parameter can be determined as the key operating parameter that causes the low-yield wafer.

[0081] As described above, step S12 may also determine a critical chamber without high-yield wafers (i.e., a critical chamber with all low-yield wafers). For this type of critical chamber without high-yield wafers, in step S13211, the parameter values ​​of multiple operating parameters corresponding to the low-yield wafers in this type of critical chamber can be directly used to form a first parameter group, and the parameter values ​​of multiple operating parameters corresponding to the high-yield wafers in a reference chamber without low-yield wafers (i.e., a reference chamber with all high-yield wafers) can be used to form a second parameter group, and then the above steps S13212 to S13213 are executed to obtain the degree of influence of each operating parameter on the wafer yield, and then the above step S1322 is executed to determine the second operating parameter in the critical chamber that causes the low-yield wafers, which will not be elaborated here.

[0082] In step S133, the first operating parameters included in the first analysis result and the second operating parameters included in the second analysis result may be the same or partially the same. Therefore, the intersection or union of the first operating parameters included in the first analysis result and the second operating parameters included in the second analysis result can be used as the key operating parameters in the critical chamber that cause low-yield wafers.

[0083] Among them, if the union of the first operating parameter and the second analysis result is used and the first operating parameter is partially identical to the second operating parameter, then for the part of the second operating parameter that is different from the first operating parameter (that is, the part of the second operating parameter for which the parameter threshold is not calculated), the parameter threshold corresponding to the part of the second operating parameter can be determined by referring to the above-mentioned implementation method of using the decision tree algorithm to determine the parameter threshold of the first operating parameter, and the parameter values ​​of the part of the second operating parameter on the high-yield wafer and the low-yield wafer respectively can be used. The embodiment of the present disclosure is not limited to this.

[0084] It should be understood that the degree of influence of each operating parameter on the wafer yield is known, and the degree of influence of the key operating parameters on the wafer yield is also known. At the same time, the results of sorting the key operating parameters according to the degree of influence (such as descending order) can be obtained. The influencing factor analysis results can also include the degree of influence of the key operating parameters in the key chamber that cause low-yield wafers on the wafer yield and / or the results of sorting the key operating parameters according to the degree of influence.

[0085] As described above, an analysis report can be generated based on the results of the influencing factor analysis, and the analysis report can be pushed to relevant personnel to optimize the key operating parameters in the key chamber. Therefore, the analysis report pushed to the relevant personnel can also include the degree of influence of the key operating parameters on the wafer yield and / or the results of sorting the key operating parameters according to the degree of influence. In other words, the key operating parameters can be sorted according to the degree of influence and provided to engineers to troubleshoot and optimize parameter problems based on the priority of the key operating parameters in the influencing program, which is equivalent to sorting the priority of the key operating parameters so that the key operating parameters with a higher degree of influence can be optimized first, which is conducive to timely improving the yield of equipment manufacturing wafers.

[0086] In actual applications, the analysis report may also include the degree of influence of each operating parameter among all operating parameters on the wafer yield and the results of sorting all operating parameters according to the degree of influence, and may highlight key operating parameters and the degree of influence of key operating parameters and parameter thresholds (for example, using different colors, fonts, or highlighting or bolding, etc.), so that users can view the degree of influence of all operating parameters and intuitively view information such as the degree of influence of key operating parameters and parameter thresholds, which is not limited to this embodiment of the present disclosure.

[0087] According to the method of the embodiment of the present disclosure, by integrating the CP site wafer yield data and the FDC system equipment data, combined with the decision tree algorithm, an efficient and accurate wafer yield influencing factor analysis method is proposed. Through this method, the key chambers and key performance parameters that affect the yield can be quickly located, and targeted optimization measures can be proposed, thereby significantly improving production efficiency and product quality.

[0088] According to the method of the embodiment of the present disclosure, by combining the wafer yield data (test data from the CP site) with the equipment data synchronized by the FDC system, the full process traceability and association of data is achieved. The key chambers and key operating parameters that affect the yield are quickly identified through the decision tree algorithm. Specific parameter optimization directions and threshold references (such as CONT_AE_FIELD>26.987091) can be provided.

[0089] According to the method of the embodiment of the present disclosure, the parameter data corresponding to the low-yield wafer and the high-yield wafer are grouped, and the parameters with significant differences are found using the geothermal analysis algorithm, so as to further clarify the key factors affecting the yield. After grouping all the parameter data of the key chamber found by the decision tree, the second analysis algorithm is used to perform a difference analysis on the two groups of data, and the operating parameters are sorted according to the difference significance value, so that engineers can check and optimize according to priority.

[0090] According to the method of the embodiment of the present disclosure, the analysis results can be pushed to relevant engineers in real time through relevant applications and email systems to ensure rapid response of optimization measures. Based on the data analysis results, the influencing factors can be directly located and optimized, avoiding the repeated trials in traditional methods and improving the optimization efficiency. It is not only applicable to the optimization of wafer yield, but can also be extended to other quality improvement scenarios in semiconductor manufacturing processes.

[0091] According to the method of the embodiment of the present disclosure, it is possible to more comprehensively understand and solve the problem of abnormal machine parameters, and to identify the problem of abnormal machine parameters by building an algorithm model. It is possible to learn the relationship between parameters and machine performance from a large amount of data, and combine domain expertise to accurately identify and effectively solve the problem of abnormal machines and their parameters.

[0092] According to the method of the embodiment of the present disclosure, a method for analyzing the relationship between wafer yield and machine chamber and machine parameters using a decision tree algorithm is implemented, and a technology for segmenting wafer data according to the equipment chamber ID and equipment operating parameters, as well as the quality of wafer yield is implemented. It is possible to identify abnormal machines that affect wafer yield while also identifying key operating parameters in key chambers. It is possible to propose specific suggestions for machine parameter optimization and chamber maintenance based on the results of the decision tree analysis. Software tools and algorithms can be developed to automate the above-mentioned decision tree analysis process. Visualization technology that intuitively displays the results of the decision tree analysis can be used. A method for providing process improvement decision support can be provided based on the results of the decision tree analysis.

[0093] According to the method of the embodiment of the present disclosure, using a decision tree algorithm to find key chambers and abnormal key operating parameters is an effective method to solve the yield reduction problem caused by abnormal operating parameters. By carefully selecting features, handling data imbalance problems, applying pruning technology, and performing model evaluation and optimization, an accurate and robust decision tree model can be constructed to provide strong support for the detection of machines and abnormal machine parameters.

[0094] According to the method of the embodiment of the present disclosure, the use of decision tree analysis can help engineers quickly lock in key influencing factors through conditional segmentation and optimize the process, for example: by analyzing equipment and process parameters to identify the root cause of the anomaly and improve the overall yield of the wafer. It is possible to accurately identify the key equipment chambers and parameters that affect the wafer yield, which is difficult to achieve through traditional analysis methods. By optimizing key operating parameters, the yield of the wafer can be directly improved, thereby increasing the overall output. By identifying and optimizing low-yield chambers (such as -O chambers), the scrap rate can be reduced, production costs can be reduced, and resource utilization can be improved.

[0095] According to the method of the embodiment of the present disclosure, a systematic method is provided to evaluate and optimize the process flow, especially for the maintenance and improvement of low-yield chambers, which helps to improve the efficiency and stability of the entire production line. It can provide data-based decision support for engineers and decision makers, making process optimization and troubleshooting more scientific and efficient. Through automated decision tree analysis tools, large amounts of data can be analyzed quickly, improving the efficiency of problem analysis and solving. It supports continuous process improvement, and adjusts and optimizes production parameters by continuously analyzing new data to achieve continuous quality improvement. Through intuitive data visualization technology, the transparency of the production process is enhanced, making it easier for relevant personnel to understand and monitor the production status.

[0096] Although the prior art can detect the mean difference between different groups (for example, normal machines and abnormal machines), thereby identifying abnormal machines. However, this method only provides a macroscopic perspective and cannot go deep into the specific parameter level of the machine. The results usually cannot directly point out which specific parameters cause the abnormality of the machine. This means that although the abnormal machine can be identified, it is impossible to determine which parameter abnormalities lead to a decrease in overall performance. The method provided by the embodiment of the present disclosure uses a decision tree to analyze the chamber through which the low-yield wafer passes and the operating parameters in the chamber that cause the low yield, which can go deep into the specific parameter level and identify the specific factors that affect the yield. In addition, an intuitive tree diagram is provided, which is easy to understand and explain, so that non-professionals can also grasp the analysis results.

[0097] According to the method of the embodiment of the present disclosure, an innovation in the common analysis method of equipment and chambers is achieved, a method of splitting samples under multi-layer factor conditions is adopted, and a specific description is given of how to group according to different equipment chamber IDs and equipment parameters, so as to accurately identify equipment or process steps that may lead to low yield.

[0098] According to the method of the embodiment of the present disclosure, the decision tree algorithm is specifically used for failure analysis in wafer manufacturing, rather than the general application of the decision tree algorithm. In particular, the split nodes (chamber ID or operating parameters) and discrimination criteria selected in the decision tree algorithm reflect the particularity of the application of the decision tree algorithm in the semiconductor process flow. That is, it innovatively realizes the decision criteria of using split nodes to maximize the distinction between high-yield and low-yield wafers, and a unique technical path to gradually narrow the scope of abnormal root causes through these splitting processes. In other words, the influencing factor analysis implemented by the decision tree algorithm in the embodiment of the present disclosure can have obvious advantages in identifying abnormal machines and specific parameter problems of the machines, and can provide more in-depth and detailed analysis results, which helps to fundamentally solve the problem of yield decline.

[0099] Figure 3 A block diagram of a wafer yield influencing factor analysis device according to an embodiment of the present disclosure is shown. Figure 3 As shown, the device comprises:

[0100] An acquisition module 301 is used to acquire yield data and equipment data of batch wafers manufactured by a wafer manufacturing device, wherein the wafer manufacturing device includes a plurality of chambers for manufacturing wafers, the yield data includes the yield of each wafer in the batch wafers, the equipment data includes the chamber where each wafer in the batch wafers is manufactured and an operating parameter set of the chamber, and the operating parameter set includes parameter values ​​of a plurality of operating parameters when manufacturing wafers in the chamber;

[0101] A first determination module 302 is used to determine a key chamber that produces low-yield wafers and a wafer set manufactured in the key chamber according to the yield data and equipment data of the batch of wafers, wherein the low-yield wafers are wafers with a yield lower than a first threshold;

[0102] The second determination module 303 is used to determine the analysis results of the influencing factors of the wafer manufacturing equipment on the wafer yield based on the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer. The influencing factor analysis results include the key operating parameters in the key chamber that lead to low-yield wafers and parameter thresholds corresponding to the key operating parameters, and the parameter thresholds represent the parameter value limits that produce low-yield wafers.

[0103] In a possible implementation, the determining of the analysis result of the factors affecting the wafer yield of the wafer manufacturing equipment according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer includes: using a first analysis algorithm to determine a first analysis result according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, the first analysis result including a first operating parameter in the critical chamber that causes low-yield wafers and a parameter threshold value corresponding to the first operating parameter; using a second analysis algorithm to determine the first analysis result according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer. The first analysis result is used to determine the yield of the wafer and the parameter values ​​of multiple operating parameters when manufacturing each wafer, and the second analysis result includes the second operating parameter in the key chamber that causes the low-yield wafer and the degree of influence of the second operating parameter on the wafer yield; according to the first analysis result and the second analysis result, the analysis result of the influencing factors of the wafer manufacturing equipment on the wafer yield is determined; wherein the second operating parameter is the same or partially the same as the first operating parameter, and the analysis result of the influencing factors also includes the degree of influence of the key operating parameter in the key chamber that causes the low-yield wafer on the wafer yield and / or the result of sorting the key operating parameters according to the degree of influence.

[0104] In one possible implementation, the second analysis result is determined based on the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, including: determining the degree of influence of each of the multiple operating parameters on the wafer yield based on the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer; and determining the second operating parameter in the critical chamber that leads to low-yield wafers based on the degree of influence of each of the multiple operating parameters on the wafer yield.

[0105] In a possible implementation, the degree of influence of each of the multiple operating parameters on the wafer yield is determined according to the yield of each wafer in the wafer set manufactured in the critical chamber and the parameter values ​​of the multiple operating parameters when manufacturing each wafer, including: determining a first parameter group corresponding to a low-yield wafer and a second parameter group corresponding to a high-yield wafer according to the yield of each wafer in the wafer set manufactured in the critical chamber, wherein the high-yield wafer is a wafer with a yield higher than a second threshold, the second threshold is greater than the first threshold, and the first parameter group includes the yield of each low-yield wafer manufactured in the critical chamber. The first parameter group includes parameter values ​​of multiple operating parameters when manufacturing each high-yield wafer in the key chamber, and the second parameter group includes parameter values ​​of multiple operating parameters when manufacturing each high-yield wafer in the key chamber; by comparing and analyzing the first parameter group and the second parameter group, the parameter difference corresponding to each operating parameter in the multiple operating parameters is obtained, and the parameter difference characterizes the degree of difference between the parameter value of the operating parameter corresponding to the high-yield wafer and the parameter value of the operating parameter corresponding to the low-yield wafer; the parameter difference corresponding to each operating parameter in the multiple operating parameters is determined as the degree of influence of each operating parameter in the multiple operating parameters on the wafer yield.

[0106] In a possible implementation, the first analysis algorithm includes a decision tree algorithm, and the second analysis algorithm includes a T-detection algorithm.

[0107] In a possible implementation, the device also uses a decision tree algorithm to determine the key chamber that produces low-yield wafers and the wafer set manufactured in the key chamber according to the yield data and equipment data of the batch of wafers, and, according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, determine the analysis results of the factors affecting the wafer yield of the wafer manufacturing equipment.

[0108] In one possible implementation, the device also includes: a generation module, which is used to generate optimization suggestions for key chambers and / or key operating parameters in key chambers in the wafer manufacturing equipment based on the analysis results of factors affecting wafer yield of the wafer manufacturing equipment; a push module, which is used to generate an analysis report based on the analysis results of the influencing factors and the optimization suggestions, and push the analysis report to relevant personnel, so that the relevant personnel can optimize the key chambers and / or key operating parameters in the key chambers in the wafer manufacturing equipment based on the analysis report with the goal of improving wafer yield.

[0109] According to the device of the embodiment of the present disclosure, by acquiring the yield data and equipment data of the equipment manufacturing wafers, the key chamber that produces low-yield wafers is determined, and then based on the yield of the wafers manufactured in the key chamber and the parameter values ​​of the operating parameters, the key operating parameters and corresponding parameter thresholds that cause the low-yield wafers in the key chamber can be determined, thereby achieving overall rapid and accurate positioning of the key chambers and key operating parameters and corresponding parameter thresholds that affect the yield, which is conducive to helping relevant personnel locate equipment problems in a timely manner, so as to effectively improve the yield of equipment manufacturing wafers on the production line.

[0110] In some embodiments, the functions or modules included in the device provided by the embodiments of the present disclosure can be used to execute the method described in the above method embodiments. The specific implementation can refer to the description of the above method embodiments, and for the sake of brevity, it will not be repeated here.

[0111] The embodiment of the present disclosure also provides a computer-readable storage medium on which computer program instructions are stored, and the computer program instructions implement the above method when executed by a processor. The computer-readable storage medium can be a volatile or non-volatile computer-readable storage medium.

[0112] An embodiment of the present disclosure further proposes an electronic device, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to implement the above method when executing the instructions stored in the memory.

[0113] The embodiments of the present disclosure also provide a computer program product, including a computer-readable code, or a non-volatile computer-readable storage medium carrying the computer-readable code. When the computer-readable code runs in a processor of an electronic device, the processor in the electronic device executes the above method.

[0114] Figure 4 1 is a block diagram of an electronic device 1900 according to an embodiment of the present disclosure. For example, the electronic device 1900 may be provided as a server or a terminal device. Figure 4 , the electronic device 1900 includes a processing component 1922, which further includes one or more processors, and a memory resource represented by a memory 1932 for storing instructions executable by the processing component 1922, such as an application. The application stored in the memory 1932 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 1922 is configured to execute instructions to perform the above method.

[0115] The electronic device 1900 may also include a power supply component 1926 configured to perform power management of the electronic device 1900, a wired or wireless network interface 1950 configured to connect the electronic device 1900 to a network, and an input / output interface 1958 (I / O interface). The electronic device 1900 may operate based on an operating system stored in the memory 1932, such as Windows Server 2003. TM , Mac OS X TM , Unix TM ,Linux TM , FreeBSD TM or similar.

[0116] In an exemplary embodiment, a non-volatile computer-readable storage medium is also provided, such as a memory 1932 including computer program instructions, which can be executed by the processing component 1922 of the electronic device 1900 to perform the above method.

[0117] The present disclosure may be a system, a method and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for causing a processor to implement various aspects of the present disclosure.

[0118] A computer-readable storage medium may be a tangible device that can hold and store instructions used by an instruction execution device. A computer-readable storage medium may be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the foregoing. More specific examples of computer-readable storage media (a non-exhaustive list) include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disk read-only memory (CD-ROM), a digital versatile disk (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punch card or a raised structure in a groove on which instructions are stored, and any suitable combination of the foregoing. As used herein, a computer-readable storage medium is not to be interpreted as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a fiber optic cable), or an electrical signal transmitted through a wire.

[0119] The computer-readable program instructions described herein can be downloaded from a computer-readable storage medium to each computing / processing device, or downloaded to an external computer or external storage device via a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmissions, wireless transmissions, routers, firewalls, switches, gateway computers, and / or edge servers. The network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in the computer-readable storage medium in each computing / processing device.

[0120] The computer program instructions for performing the operation of the present disclosure may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages, such as Smalltalk, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. Computer-readable program instructions may be executed completely on a user's computer, partially on a user's computer, as an independent software package, partially on a user's computer, partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., using an Internet service provider to connect via the Internet). In some embodiments, an electronic circuit, such as a programmable logic circuit, a field programmable gate array (FPGA), or a programmable logic array (PLA), may be customized by utilizing the state information of the computer-readable program instructions, and the electronic circuit may execute the computer-readable program instructions, thereby realizing various aspects of the present disclosure.

[0121] Various aspects of the present disclosure are described herein with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0122] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, thereby producing a machine, so that when these instructions are executed by the processor of the computer or other programmable data processing device, a device that implements the functions / actions specified in one or more boxes in the flowchart and / or block diagram is generated. These computer-readable program instructions can also be stored in a computer-readable storage medium, and these instructions cause the computer, programmable data processing device, and / or other equipment to work in a specific manner, so that the computer-readable medium storing the instructions includes a manufactured product, which includes instructions for implementing various aspects of the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0123] Computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operating steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby causing the instructions executed on the computer, other programmable data processing apparatus, or other device to implement the functions / actions specified in one or more boxes in the flowchart and / or block diagram.

[0124] The flow chart and block diagram in the accompanying drawings show the possible architecture, function and operation of the system, method and computer program product according to multiple embodiments of the present disclosure. In this regard, each square box in the flow chart or block diagram can represent a part of a module, program segment or instruction, and a part of the module, program segment or instruction includes one or more executable instructions for realizing the specified logical function. In some alternative implementations, the function marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two continuous square boxes can actually be executed substantially in parallel, and they can sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs the specified function or action, or can be implemented with a combination of special hardware and computer instructions.

[0125] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or technical improvements in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A method for analyzing factors affecting wafer yield, characterized in that: include: Obtaining yield data and equipment data of batch wafers manufactured by a wafer manufacturing device, wherein the wafer manufacturing device includes a plurality of chambers for manufacturing wafers, the yield data includes the yield of each wafer in the batch wafers, the equipment data includes the chamber where each wafer in the batch wafers is manufactured and an operating parameter set of the chamber, and the operating parameter set includes parameter values ​​of a plurality of operating parameters when the wafers are manufactured in the chamber; Determine, according to the yield data and equipment data of the batch of wafers, a key chamber that produces low-yield wafers and a wafer set manufactured in the key chamber, wherein the low-yield wafers are wafers with a yield lower than a first threshold; Based on the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer, the analysis results of the factors affecting the wafer yield of the wafer manufacturing equipment are determined. The analysis results of the influencing factors include the key operating parameters in the key chamber that lead to low-yield wafers and parameter thresholds corresponding to the key operating parameters. The parameter thresholds represent the parameter value limits that produce low-yield wafers.

2. The method according to claim 1, characterized in that The method of determining the analysis result of the factors affecting the wafer yield of the wafer manufacturing equipment according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer includes: Determine a first analysis result using a first analysis algorithm according to the yield of each wafer in the wafer set manufactured in the critical chamber and parameter values ​​of multiple operating parameters when manufacturing each wafer, wherein the first analysis result includes a first operating parameter in the critical chamber that causes low-yield wafers and a parameter threshold corresponding to the first operating parameter; Determine a second analysis result using a second analysis algorithm according to the yield of each wafer in the wafer set manufactured in the critical chamber and parameter values ​​of multiple operating parameters when manufacturing each wafer, wherein the second analysis result includes a second operating parameter in the critical chamber that causes low-yield wafers and the degree of influence of the second operating parameter on the wafer yield; Determine, based on the first analysis result and the second analysis result, an analysis result of factors affecting wafer yield of the wafer manufacturing equipment; Among them, the second operating parameter is the same or partially the same as the first operating parameter, and the influencing factor analysis result also includes the degree of influence of the key operating parameters in the key chamber that cause low-yield wafers on the wafer yield and / or the result of sorting the key operating parameters according to the degree of influence.

3. The method according to claim 2, characterized in that The determining of the second analysis result according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer includes: Determining the influence of each of the multiple operating parameters on the wafer yield according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer; According to the influence degree of each operating parameter in the plurality of operating parameters on the wafer yield, a second operating parameter in the key chamber that causes low-yield wafers is determined.

4. The method according to claim 3, characterized in that The step of determining the influence of each of the plurality of operating parameters on the wafer yield according to the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of the plurality of operating parameters when manufacturing each wafer comprises: According to the yield of each wafer in the wafer set manufactured in the key chamber, determine a first parameter group corresponding to the low-yield wafer and a second parameter group corresponding to the high-yield wafer, wherein the high-yield wafer is a wafer with a yield higher than a second threshold, the second threshold is greater than the first threshold, the first parameter group includes parameter values ​​of multiple operating parameters when each low-yield wafer is manufactured in the key chamber, and the second parameter group includes parameter values ​​of multiple operating parameters when each high-yield wafer is manufactured in the key chamber; By comparing and analyzing the first parameter group and the second parameter group, a parameter difference corresponding to each operating parameter in the plurality of operating parameters is obtained, wherein the parameter difference represents a degree of difference between a parameter value of the operating parameter corresponding to the high-yield wafer and a parameter value of the operating parameter corresponding to the low-yield wafer; The parameter difference corresponding to each of the multiple operating parameters is determined as the influence degree of each of the multiple operating parameters on the wafer yield.

5. The method according to claim 2, characterized in that: The first analysis algorithm includes a decision tree algorithm, and the second analysis algorithm includes a T-detection algorithm.

6. The method according to claim 1, characterized in that The method also uses a decision tree algorithm to determine the key chamber that produces low-yield wafers and the wafer set manufactured in the key chamber based on the yield data and equipment data of the batch of wafers, and determines the analysis results of the factors affecting the wafer yield of the wafer manufacturing equipment based on the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer.

7. The method according to any one of claims 1 to 6, characterized in that: The method further comprises: Generating optimization suggestions for key chambers and / or key operating parameters in key chambers in the wafer manufacturing equipment according to the analysis results of the factors affecting wafer yield of the wafer manufacturing equipment; Based on the analysis results of the influencing factors and the optimization suggestions, an analysis report is generated and pushed to relevant personnel so that the relevant personnel can optimize the key chambers and / or key operating parameters in the key chambers in the wafer manufacturing equipment according to the analysis report with the goal of improving wafer yield.

8. A wafer yield influencing factor analysis device, characterized in that: include: An acquisition module, used for acquiring yield data and equipment data of batch wafers manufactured by a wafer manufacturing device, wherein the wafer manufacturing device includes a plurality of chambers for manufacturing wafers, the yield data includes the yield of each wafer in the batch wafers, the equipment data includes the chamber where each wafer in the batch wafers is manufactured and an operating parameter set of the chamber, and the operating parameter set includes parameter values ​​of a plurality of operating parameters when the wafers are manufactured in the chamber; A first determination module is used to determine a key chamber that produces low-yield wafers and a wafer set manufactured in the key chamber according to the yield data and equipment data of the batch of wafers, wherein the low-yield wafers are wafers with a yield lower than a first threshold; The second determination module is used to determine the analysis results of the influencing factors of the wafer manufacturing equipment on the wafer yield based on the yield of each wafer in the wafer set manufactured in the key chamber and the parameter values ​​of multiple operating parameters when manufacturing each wafer. The influencing factor analysis results include the key operating parameters in the key chamber that lead to low-yield wafers and parameter thresholds corresponding to the key operating parameters, and the parameter thresholds represent the parameter value limits that produce low-yield wafers.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to implement the method described in any one of claims 1 to 7 when executing the instructions stored in the memory.

10. A non-volatile computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images