A method and device for evaluating the processing sequence of equipment failures based on risk assessment

Abstract

The present invention relates to a method for evaluating the processing sequence of equipment failures based on risk assessment, comprising: obtaining a first wafer sample, and obtaining wafer parameter information and fault information of the first wafer sample based on the first wafer sample, and the fault information includes: information of the equipment where the fault occurs, and the actual waiting time of the equipment failure; determining a first weight of the equipment failure based on the wafer parameter information, the equipment information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data; determining an equivalent waiting time of the equipment failure based on the first weight and the actual waiting time. Correspondingly, the present invention also provides an evaluation device. The evaluation method and device provided by the present invention can improve the equivalent efficiency of fault processing.

Description

Technical Field

[0001] The present invention relates to the field of semiconductor manufacturing, and in particular to a method and device for evaluating the processing sequence of equipment failures based on risk assessment. Background Art

[0002] With the development of semiconductor device technology, more and more processes are used to manufacture semiconductor devices, and each process has a certain degree of complexity. Each process flow may produce some unexpected structures in the processing of wafers. Among them, those that cause the circuits on the chip to fail to work properly are called wafer defects.

[0003] In the chip manufacturing process, in order to ensure the quality of chip products, it is necessary to add measurement processes between production processes. For example, the measurement process includes the measurement of size and electrical properties, as well as the scanning detection of defects on the chip. The existing conventional equipment supervision steps are divided into: testing the sampled wafer samples, identifying the wafer samples whose difference from the standard wafer exceeds a certain threshold, and notifying the problem handling system for manual judgment, and finally manually analyzing and handling the problems or faults found. Since the production line of chip production works 24 hours a day, when the engineer finds the cause of the problem, the relevant equipment or production line will be locked for shutdown inspection to ensure that subsequent products are not affected. However, before the engineer actually starts the analysis, it is impossible to know the specific situation of each included problem in advance, so the engineer can generally only handle the problem in chronological order (FIFO). The severity and degree of harm of different problems or faults are different. Handling them in chronological order often leads to too long waiting time for serious problems, resulting in the expansion of final losses. Summary of the invention

[0004] In view of the above technical problems, the object of the present invention is to provide a method for evaluating the processing sequence of equipment failures based on risk assessment, comprising:

[0005] Acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where a fault occurs, and an actual waiting time of the device fault;

[0006] Determine a first weight of a device failure based on the wafer parameter information, the device information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data;

[0007] An equivalent waiting time of the device failure is determined based on the first weight and the actual waiting time.

[0008] In some embodiments, the calculation model for determining the first weight is:

[0009] wi =R1N1+R2N2+......+R n N n

[0010] Among them, w i is the first weight, R1, R2, ..., R n is the second weight, N1, N2, ..., N n is a sample parameter of the first wafer sample, the sample parameter including: wafer parameter information and reference data, and n is a natural number greater than or equal to 1 (ie, the number of equipment failures).

[0011] Further, in some embodiments, the calculation model for determining the first weight is:

[0012] w i =R1N1+R2N2+R3N3+R4N4+R5N5+R6N6+R7N7

[0013] Among them, w i is the first weight, R1, R2, R3, R4, R5, R6, and R7 are the second weights, N1 is the degree of deviation between the total number of defects of the first wafer sample after scanning at the first site and the average number of defects scanned by the historical wafer samples of the first site in the first historical period, N2 is the standard value based on the defects scanned by the first wafer sample, N3 is the number of special elements in the first wafer sample, N4 is the number of times the first wafer sample is processed by the key production equipment ID pre-defined by the user, N5 is the remaining waiting time of the first wafer sample, N6 is the production priority of the first wafer sample, and N7 is the number of production failures that have occurred at the first site in the first historical period.

[0014] In some embodiments, the calculation model of the equivalent waiting time is:

[0015] T=w i T i

[0016] Where T is the equivalent waiting time of the fault, w i The first weight of the fault, T i is the actual waiting time for the failure.

[0017] In some embodiments, the steps include:

[0018] The device failures are prioritized based on the equivalent waiting times.

[0019] A second aspect of the present invention is to provide a device for evaluating the processing sequence of equipment failures based on risk assessment, comprising:

[0020] An information acquisition module, used to acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where a fault occurs, and an actual waiting time of the device fault;

[0021] A fault weight determination module, configured to determine a first weight of a device fault based on the wafer parameter information, the device information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data;

[0022] An equivalent waiting time determination module is used to determine an equivalent waiting time of the device failure based on the first weight and the actual waiting time.

[0023] In some embodiments, the fault weight determination module determines the calculation model of the first weight as:

[0024] w i =R1N1+R2N2+......+R n N n

[0025] Among them, w i is the first weight, R1, R2, ..., R n is the second weight, N1, N2, ..., N n is a sample parameter of a first wafer sample, the sample parameter including: wafer parameter information and reference data, and n is a natural number greater than or equal to 1.

[0026] In some embodiments, the calculation model for determining the first weight is:

[0027] w i =R1N1+R2N2+R3N3+R4N4+R5N5+R6N6+R7N7

[0028] Among them, w i is the first weight, R1, R2, R3, R4, R5, R6, and R7 are the second weights, N1 is the degree of deviation between the total number of defects of the first wafer sample after scanning at the first site and the average number of defects scanned by the historical wafer samples of the first site in the first historical period, N2 is the standard value based on the defects scanned by the first wafer sample, N3 is the number of special elements in the first wafer sample, N4 is the number of times the first wafer sample is processed by the key production equipment ID pre-defined by the user, N5 is the remaining waiting time of the first wafer sample, N6 is the production priority of the first wafer sample, and N7 is the number of production failures that have occurred at the first site in the first historical period.

[0029] In some embodiments, the calculation model used by the equivalent waiting time determination module to determine the equivalent waiting time is:

[0030] T=w i T i

[0031] Where T is the equivalent waiting time of the fault, w i The first weight of the fault, T i is the actual waiting time for the failure.

[0032] In some embodiments, the apparatus further comprises:

[0033] A fault sorting module is used to prioritize the device faults based on the equivalent waiting time.

[0034] The third aspect of the present invention is to provide another method for evaluating the processing sequence of equipment failures based on risk assessment, the method comprising the steps of:

[0035] Acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where the fault occurs, and an actual occurrence time of the corresponding device fault;

[0036] Sort the currently acquired device failures at least twice (for example, sort multiple device failures randomly), and determine the estimated waiting time T of the corresponding device failure under each sorting scheme based on the estimated processing time and the actual occurrence time of each device failure i ';

[0037] Determine a first weight w of a corresponding device failure based on the wafer parameter information, the device information and pre-acquired reference data i , wherein the reference data includes: relevant data and historical data;

[0038] Based on the first weight w i and the estimated waiting time T i 'Determine the equivalent total waiting time T1 of each device failure in each sequencing scheme;

[0039] The preferred sorting scheme is determined based on the equivalent total waiting time T1 of different sorting schemes.

[0040] Furthermore, in some embodiments, the calculation model for determining the equivalent waiting time is:

[0041]

[0042] T1 is the equivalent waiting time, w i is the first weight, T i 'Estimated waiting time.

[0043] In some embodiments, the calculation model of the first weight is:

[0044] w i =R1N1+R2N2+......+R n N n

[0045] Among them, w i is the first weight, R1, R2, ..., R n is the second weight, N1, R2, ..., N n is a relative value of a sample parameter of a first wafer sample, where the sample parameter includes: wafer parameter information and reference data, and n is a natural number greater than or equal to 1.

[0046] Preferably, in some embodiments, the calculation model for determining the first weight is:

[0047] w i =R1N1+R2N2+R3N3+R4N4+R5N5+R6N6+R7N7

[0048] Among them, w i is the first weight, R1, R2, R3, R4, R5, R6, and R7 are the second weights, N1 is the degree of deviation between the total number of defects of the first wafer sample after scanning at the first site and the average number of defects scanned by the historical wafer samples of the first site in the first historical period, N2 is the standard value based on the defects scanned by the first wafer sample, N3 is the number of special elements in the first wafer sample, N4 is the number of times the first wafer sample is processed by the key production equipment ID pre-defined by the user, N5 is the remaining waiting time of the first wafer sample, N6 is the production priority of the first wafer sample, and N7 is the number of production failures that have occurred at the first site in the first historical period.

[0049] A fourth aspect of the present invention further provides a device for evaluating the processing sequence of equipment failures based on risk assessment, comprising:

[0050] An information acquisition unit, used to acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where the fault occurs, and an actual occurrence time of the corresponding device fault;

[0051] The estimated waiting time determination unit is used to sort the currently acquired device faults at least twice (for example, sorting multiple device faults randomly), and determine the estimated waiting time T of the corresponding device fault under each sorting scheme based on the estimated processing time and the actual occurrence time of each device fault. i ';

[0052] A first weight determination unit is used to determine a first weight w of a corresponding device failure based on the wafer parameter information, the device information and pre-acquired reference data. i , wherein the reference data includes: relevant data and historical data;

[0053] The equivalent total waiting time determining unit is configured to determine the equivalent total waiting time based on the first weight w i and the estimated waiting time T i 'Determine the equivalent total waiting time T1 of each device failure in each sequencing scheme;

[0054] The sorting scheme determining unit is used to determine a preferred sorting scheme based on the equivalent total waiting time T1 of different sorting schemes.

[0055] Furthermore, in some embodiments, the calculation model used to determine the equivalent waiting time in the equivalent waiting total time determination unit is:

[0056]

[0057] T1 is the equivalent waiting time, w i is the first weight, T i 'Estimated waiting time.

[0058] In some embodiments, the calculation model for determining the first weight in the first weight determination unit is:

[0059] w i =R1N1+R2N2+......+R n N n

[0060] Among them, w i is the first weight, R1, R2, ..., R n is the second weight, N1, N2, ..., N n is a sample parameter of the first wafer sample, the sample parameter including: wafer parameter information and reference data, and n is a natural number greater than or equal to 1 (ie, the number of equipment failures).

[0061] Further, in some embodiments, the calculation model used in the first weight determination unit to determine the first weight is:

[0062] w i =R1N1+R2N2+R3N3+R4N4+R5N5+R6N6+R7N7

[0063] Among them, w iis the first weight, R1, R2, R3, R4, R5, R6, and R7 are the second weights, N1 is the degree of deviation between the total number of defects of the first wafer sample after scanning at the first site and the average number of defects scanned by the historical wafer samples of the first site in the first historical period, N2 is the standard value based on the defects scanned by the first wafer sample, N3 is the number of special elements in the first wafer sample, N4 is the number of times the first wafer sample is processed by the key production equipment ID pre-defined by the user, N5 is the remaining waiting time of the first wafer sample, N6 is the production priority of the first wafer sample, and N7 is the number of production failures that have occurred at the first site in the first historical period.

[0064] A fifth aspect of the present invention is to provide a computer-readable storage medium storing a computer program, wherein the computer program implements the steps of any of the above methods when executed by a processor.

[0065] Beneficial technical effects

[0066] The present invention relates to a method for evaluating the processing sequence of equipment failures based on risk assessment, which performs a comprehensive risk assessment on the corresponding equipment failures based on the actual waiting time (or actual occurrence time) of the equipment failure and the first weight of the equipment failure (that is, the importance of the impact of the equipment failure on chip production). The staff can determine the processing priority of the equipment failure based on the result of the risk assessment (that is, the equivalent waiting time of the equipment failure). By troubleshooting and processing the equipment failure based on the acquired processing priority sequence, the adverse effects of the equipment failure on the production line can be reduced to an acceptable range as soon as possible within a limited time (that is, the quality of the processed wafers meets the production standards at this time), that is, the equivalent processing time of all faults to be processed can be minimized. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following is a brief introduction to the drawings required for use in the embodiments or the prior art description. In all the drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale. Obviously, the drawings described below are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on these drawings without paying creative work.

[0068] Figure 1 is a schematic diagram of a method flow in an exemplary embodiment of the present invention;

[0069] Figure 2 is a schematic diagram of a method flow in another exemplary embodiment of the present invention;

[0070] Figure 3is a schematic diagram of a device structure in an exemplary embodiment of the present invention;

[0071] Figure 4 It is a structural block diagram of an electronic device in an exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0072] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0073] Herein, suffixes such as "module", "component" or "unit" used to represent elements are only used to facilitate the description of the present invention, and have no specific meanings by themselves. Therefore, "module", "component" or "unit" can be used mixedly.

[0074] Embodiment 1

[0075] The first aspect of the present invention is to provide a method for evaluating the processing sequence of equipment failures based on risk assessment, see Figure 1 , the method comprises the steps of:

[0076] S10: Acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where a fault occurs, and an actual waiting time of the device fault;

[0077] Specifically, in some embodiments, the wafer parameter information includes: defect information, and accordingly, step S10 includes:

[0078] Obtain the first wafer sample on the production line;

[0079] Acquire a first wafer image based on the first wafer sample, and determine defect information on the first wafer sample based on the first wafer image, wherein the defect information includes: defect type, defect quantity, and corresponding defect characteristics (such as defect size, etc.);

[0080] Determine fault information on the production line based on defect information.

[0081] In some embodiments, the actual waiting time may be a time interval from the actual occurrence time of the device failure to the current time.

[0082] For example, in this embodiment, the problematic process steps or faulty production equipment that caused the corresponding defects can be determined based on historical experience data, and the occurrence time of the fault or problem that caused the corresponding defects can be further determined in combination with the production timeline of the first wafer sample. The actual waiting time of the fault or problem can be determined based on the occurrence time of the fault or problem and the current time information.

[0083] Alternatively, in other embodiments, the actual waiting time may be the time interval between the time when the equipment failure is reported (i.e., the time when the equipment failure is detected) and the current time. For example, in this embodiment, the actual waiting time is the time interval between the time when the equipment failure is recorded and the current time.

[0084] In some embodiments, the wafer parameter information is a related parameter or image that can reflect defect information of the first wafer sample. For example, the wafer parameter information can be a first wafer image; for another example, the wafer parameter information can include: pixel point information of the first wafer image.

[0085] Furthermore, in some embodiments, wafer data (eg wafer defect information) corresponding to the first wafer sample may be acquired based on the wafer parameter information.

[0086] S20: Determine a first weight of equipment failure based on wafer parameter information, equipment information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data; wherein the relevant data is the production demand of the user, and the historical data is the historical wafer parameter information within a first historical period (such as the past month) (for example, including defect information of wafer products, wafer production and processing data information, etc.).

[0087] For example, in some embodiments, the device information includes: a device name (device ID) or a device number that can be used to find the device.

[0088] For example, in some embodiments, the relevant data includes: the production conditions of the first wafer sample (or other production requirements defined by the user), such as the production priority of the wafer, the interval time between different production processes of the wafer (or the maximum waiting time allowed), and the element information in the first wafer sample (such as the type of elements contained in the wafer after different processing steps).

[0089] In some embodiments, historical data includes: historical parameter information (or historical wafer parameter information) of wafers under the same process or production plan within a first historical period. For example, the historical parameter information includes: defect type and number of defects, etc.; and the frequency of failures occurring at the same process (such as the same site) within the first historical period, and / or the type of failures that occurred, and / or the degree of impact of the failures that occurred on the wafer quality.

[0090] S30: Determine an equivalent waiting time of the equipment failure based on the first weight and the actual waiting time, wherein the equivalent waiting time is used to characterize the urgency of the equipment failure to be processed.

[0091] In this embodiment, the first weight of the equipment failure is determined based on the first wafer sample (i.e., the current wafer to be tested) and the pre-acquired reference data, that is, the degree of adverse effects of the corresponding equipment failure on the production line is determined, or in other words, the magnitude of the impact of the corresponding equipment failure on the chip production line is determined. And the urgency of the corresponding equipment failure is determined based on the actual waiting time of the equipment failure that has occurred and the first weight (specifically, it can be characterized by the equivalent waiting time), that is, a comprehensive risk assessment of the equipment failure that has occurred is performed. Based on the comprehensive risk assessment of equipment failures, the equivalent processing time of the equipment failures to be processed can be effectively reduced. Specifically, when the equivalent waiting time of the equipment failure is longer, it is considered that the risk of the equipment failure is greater, that is, the need for problem handling of the equipment failure is more urgent, and the staff can refer to the results of the risk assessment to give priority to it, thereby efficiently and quickly reducing the adverse effects of the equipment failure on the production line in a short time.

[0092] In some embodiments, the calculation model for determining the first weight is:

[0093] w i =R1N1+R2N2+......+R n N n

[0094] Among them, w i is the first weight, R1, R2, ..., R n is the second weight, used to characterize each sample parameter such as N1, N2, ..., N n In evaluating the importance of the first weight of equipment failure (i.e., the impact size), N1, N2, ..., N n is a sample parameter of a first wafer sample, the sample parameter including: wafer parameter information and reference data, and n is a natural number greater than or equal to 1.

[0095] In some embodiments, the specific value of the second weight can be customized by staff based on historical experience.

[0096] Alternatively, in other embodiments, the optimal solution for the second weight setting may be obtained by fitting based on actual processing time data of historical cases.

[0097] Of course, in other embodiments, N1, N2, ..., N n It can be the normalized value of the sample parameter, specifically, normalized by Max-Min.

[0098] Preferably, in some embodiments, the calculation model for determining the first weight is:

[0099] w i =R1N1+R2N2+R3N3+R4N4+R5N5+R6N6+R7N7

[0100] Among them, w i is the first weight, R1, R2, R3, R4, R5, R6, and R7 are the second weights, N1 is the total number of defects of the first wafer sample after scanning at the first site (i.e., the current site) and the deviation degree of the average number of defects scanned by the historical wafer samples of the first site in the first historical period (the first historical period can be set by the staff, for example, set to the last seven days, or the last month), N2 is the standard value based on the defects scanned by the first wafer sample, N3 is the number of special elements in the first wafer sample, N4 is the number of processing times of the key production equipment ID pre-defined by the user in the first historical period, N5 is the remaining waiting time of the first wafer sample, N6 is the production priority of the first wafer sample, and N7 is the number of production failures that have occurred in the first site in the first historical period.

[0101] In this embodiment, N1, N2, and N3 are wafer parameter information, N4 and N7 are historical data, and N5 and N6 are related data. Among them, the above-mentioned wafer parameter information can be the comparison information (or comparison information such as comparison value) of the wafer parameters of the current first wafer sample and the related data or historical data, such as N1 is the comparison value of the number of defects of the first wafer sample and the number of defects in the historical data.

[0102] Specifically, in some embodiments, the defects scanned on the first wafer sample can be classified according to defect categories, and different defect categories correspond to different control upper limits. When the detected defect exceeds the corresponding control upper limit (OOC=Yes): the standard value N2=10, when the detected defect does not exceed the corresponding control upper limit (OOC=No): the standard value N2=1.

[0103] Special elements (or special EDX elements) are elements that should not exist on the first sample wafer in the current process (or first station). For example, in the early stage of chip manufacturing, metal elements are not allowed to appear. When the presence of special elements is detected: N3 = 10 (Yes), when the presence of special elements is not detected: N3 = 1 (No).

[0104] N4 is the number of times the current first wafer sample is processed by key production equipment pre-defined by the user. Since these devices or machines have a relatively large output or a relatively large impact on the quality of the wafer, they are monitored in detail in this embodiment, and the wafer data produced by these devices or machines are pre-inspected and checked to reduce the equivalent processing time of the fault.

[0105] N5 is the remaining waiting time of the first wafer sample, that is, the remaining Qtime of the current first wafer sample, where Qtime is the maximum waiting time allowed from the end of the current process to the start of the next process. If this waiting time is exceeded, the material structure on the first wafer sample will change, causing the first wafer sample to fail. When Qtime>0, N5=1 / Qtime(hr, hours), Qtime≤0, N5=100×Abs(Qtime)=100×|Qtime|.

[0106] The staff can set the production level of the first wafer sample based on production requirements or historical experience, and determine the value of N6 accordingly, for example, N6=10 (priority=0), N6=5 (Priority=1), N6=2 (Priority=2), N6=1 (Priority=3), N6=1 (Priority=4).

[0107] During the wafer production process, there are many factors that lead to poor wafer quality. The sample parameter combination selected in this embodiment comprehensively considers the key influencing factors of wafer production, and combines the actual needs of wafer production to conduct a more comprehensive risk assessment of equipment failures, so that the staff can reduce the adverse effects of equipment failures to an acceptable range in the shortest time, that is, improve the equivalent processing efficiency of equipment failures on the production line. At the same time, since the evaluation method can take into account the actual needs of wafer production (or the user's customized needs), the method is also very adaptable to production lines of different types or batches.

[0108] The second weight can be flexibly configured by the staff based on work experience or production requirements. For example, in some embodiments, the second weight can be configured as: R1=10, R2=1, R3=100, R4=50, R5=1, R6=1, R7=2.

[0109] Specifically, in some embodiments, the parameter information in the first weight calculation model is shown in the following table:

[0110] Table 1

[0111]

[0112] Furthermore, in some embodiments, the calculation model of the equivalent waiting time is:

[0113] T=w i T i

[0114] Where T is the equivalent waiting time of the fault, w i The first weight of the fault, T i is the actual waiting time for the failure.

[0115] In this embodiment, after the equivalent waiting times of different equipment faults are determined, the staff can evaluate the processing order of the equipment faults based on the equivalent waiting times, such as giving priority to detecting and processing equipment faults with longer equivalent waiting times.

[0116] Furthermore, in some embodiments, the method further comprises the steps of:

[0117] The device failures are prioritized based on the equivalent waiting times.

[0118] For example, the equivalent waiting time of equipment failures is sorted from large to small, so that the staff can analyze and handle the failures according to the handling priority of the equipment failures.

[0119] Furthermore, in order to verify and evaluate the reliability of the evaluation method, in some embodiments, the method further includes the steps of:

[0120] Obtaining the actual processing time of each device fault when performing fault processing based on the priority sorting;

[0121] Determine the total equivalent processing time of the device failure based on each of the actual processing times;

[0122] The reliability of the priority sorting is evaluated based on the equivalent total processing time and a preset standard time.

[0123] In some embodiments, the total equivalent processing time is the time required to reduce the total impact of several equipment failures to within the standard range (or the acceptable range of production). In other words, the total equivalent processing time is the time required to control the defect rate of production line products within the standard.

[0124] Among them, the standard time is the maximum acceptable equivalent processing time for equipment failure processing that meets the production requirements of the production line. For example, when the actual total equivalent processing time is greater than the standard time, it is considered that the processing efficiency of the equipment failure is low. At this time, it can be recommended that the staff further optimize the priority sorting of equipment failures (or further optimize the relevant calculation model of the equivalent waiting time, for example, adjust the first weight and the second weight); when the actual total equivalent processing time is less than the standard time, it is considered that the processing efficiency of the equipment failure meets the production specifications. The standard time can be set by the staff based on historical experience.

[0125] In some embodiments, the calculation model of the equivalent total processing time is:

[0126]

[0127] Where T' is the total equivalent processing time (that is, the total time consumed by the staff to handle the equipment failure based on the equivalent waiting time so that the impact of the equipment failure is reduced to an acceptable range), T α The actual processing time of each equipment failure (that is, the actual time taken by the staff to process the equipment failure based on the equivalent waiting time. For example, if the equipment failure is processed one hour after it occurs, the actual processing time is one hour).

[0128] Of course, in other embodiments, T α It can also be the fault processing completion time of each device fault.

[0129] It is understandable that, due to the relatively complex production process of wafers and the long production line, new equipment failures may occur at any time during the production and processing process, and the resources for handling failures are limited. Therefore, in the actual processing and production process, it is not necessary to reduce the number of equipment failures to zero, but to control the overall impact of equipment failures within an acceptable range, that is, to control the defective rate of products (such as wafers) below the standard range. Therefore, the main purpose of the present invention is to minimize the overall impact of equipment failures within a limited time, especially for chip production lines that are processed uninterruptedly for a long time, and to reduce the defective rate of wafers to the minimum range as soon as possible.

[0130] For example, in a specific embodiment, the currently detected equipment failures are arranged based on the time of occurrence as follows: equipment failure 1, equipment failure 2, equipment failure 3, equipment failure 4, equipment failure 5, and the average processing time for each equipment failure is 20 minutes. At this time, the total impact of the equipment failure can be reduced to an acceptable range by processing equipment failures 1 to 4 in chronological order, and the processing time at this time is 80 minutes. The scheme for sorting equipment failures based on equivalent waiting time is: equipment failure 4, equipment failure 3, equipment failure 5, equipment failure 2, equipment failure 1. At this time, the equipment failure can be reduced to an acceptable range by processing equipment failures 4, 3, and 5 in sequence, and the processing time is 60 minutes. That is, the total equivalent processing time in this embodiment is 60 minutes, which is significantly reduced compared to the processing method of the prior art.

[0131] For example, after a period of working time (such as 1 day, or 1 month), the previously handled equipment failures and the time consumed in handling the equipment failures are analyzed, so that the staff can conduct real-time analysis and feedback on the implementation effect of the method.

[0132] Preferably, in some embodiments, in order to ensure the timeliness of risk assessment (or, to ensure the timeliness of equivalent waiting time), the equivalent waiting time is periodically updated based on changes in actual waiting time. For example, every 10 minutes, the equivalent waiting time of each equipment failure is updated to facilitate staff to obtain the equivalent waiting time of the equipment failure at the current moment.

[0133] Further, in some embodiments, the first wafer sample is periodically obtained, and the wafer parameter information of the first wafer sample is obtained, and the fault information is updated based on the wafer parameter information periodically obtained, as well as the equivalent waiting time corresponding to the equipment failure. In this embodiment, based on the periodic acquisition of wafer parameter information, the equipment failure information (such as including the faulty equipment ID and the equivalent waiting time of the faulty equipment) can be periodically updated, that is, the equipment failure information is in a dynamic state of change. The dynamic update of equipment failure information enhances the timeliness of risk assessment, thereby further improving the equivalent processing efficiency of equipment failure. Among them, the cycle for obtaining the first wafer sample can be customized by the staff. For example, the cycle for obtaining the first wafer sample can be set to 10 minutes, then the first wafer sample is obtained every 10 minutes, and the equipment failure information is updated.

[0134] Alternatively, in other embodiments, the first wafer sample may be acquired in real time, and based on the wafer parameter information acquired in real time, the fault information and the equivalent waiting time corresponding to the equipment fault may be further updated based on the wafer parameter information acquired in real time.

[0135] The evaluation method in this embodiment is based on the current real production data (such as wafer parameter information, etc.), the reference historical data and the specific production requirements (such as relevant data) in the current production process to comprehensively evaluate the adverse effects of equipment failure. Among them, the relevant data reflects the specific business needs in the wafer production process. The staff can customize the settings based on the specific business needs, so that the evaluation method in this embodiment has good versatility and can be applied to the production processes of different batches of products from different manufacturers.

[0136] Embodiment 2

[0137] Based on the above method, the present invention also provides a device for evaluating the processing sequence of equipment failures based on risk assessment, such as Figure 3 As shown, the device comprises:

[0138] The information acquisition module 01 is used to acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where a fault occurs, and an actual waiting time of the device fault;

[0139] A fault weight determination module 03 is used to determine a first weight of a device fault based on the wafer parameter information, the device information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data;

[0140] The equivalent waiting time determination module 05 is used to determine the equivalent waiting time of the device failure based on the first weight and the actual waiting time.

[0141] In some embodiments, the calculation model used by the fault weight determination module to determine the first weight is:

[0142] w i =R1N1+R2N2+......+R n N n

[0143] Among them, w i is the first weight, R1, R2, ..., R n is the second weight, N1, N2, ..., N n is a relative value of a sample parameter of a first wafer sample, where the sample parameter includes: wafer parameter information and reference data, and n is a natural number greater than or equal to 1.

[0144] Preferably, in some embodiments, the calculation model for determining the first weight is:

[0145] w i=R1N1+R2N2+R3N3+R4N4+R5N5+R6N6+R7N7

[0146] Among them, w i is the first weight, R1, R2, R3, R4, R5, R6, and R7 are the second weights, N1 is the degree of deviation between the total number of defects of the first wafer sample after scanning at the first site and the average number of defects scanned by the historical wafer samples of the first site in the first historical period, N2 is the standard value based on the defects scanned by the first wafer sample, N3 is the number of special elements in the first wafer sample, N4 is the number of times the first wafer sample is processed by the key production equipment ID pre-defined by the user, N5 is the remaining waiting time of the first wafer sample, N6 is the production priority of the first wafer sample, and N7 is the number of production failures that have occurred at the first site in the first historical period.

[0147] Furthermore, in some embodiments, the calculation model used by the equivalent waiting time determination module to determine the equivalent waiting time is:

[0148] T=w i T i

[0149] Where T is the equivalent waiting time of the fault, w i The first weight of the fault, T i is the actual waiting time for the failure.

[0150] In some embodiments, the apparatus further comprises:

[0151] A fault sorting module is used to prioritize the device faults based on the equivalent waiting time.

[0152] Preferably, in some embodiments, the information acquisition module 01 is configured to periodically acquire a first wafer sample, and accordingly, the fault weight determination module and the equivalent waiting time determination module update the fault information and the equivalent waiting time corresponding to the equipment fault based on periodic wafer parameter information.

[0153] like Figure 2 As shown, in some embodiments, the coordination process between the provided evaluation device and the production line is as follows:

[0154] Sampling is performed on the wafers currently being processed, and defect detection is performed on the sampled samples (equivalent to the first wafer sample mentioned above). When it is detected that the sampled samples meet the standards, production continues. When it is detected that the samples do not meet the standards, the detected relevant information is input into the evaluation device. The evaluation device performs a comprehensive risk assessment based on the collected information, and finally outputs the equivalent waiting time of the equipment failure (specifically, outputs an equipment failure report sorted by the equivalent waiting time). Subsequently, the staff determines the specific cause of the failure based on the information output by the evaluation device and handles it.

[0155] Embodiment 3

[0156] The third aspect of the present invention is to provide another method for evaluating the processing sequence of equipment failures based on risk assessment, comprising the steps of:

[0157] Acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where the fault occurs, and an actual occurrence time of the corresponding device fault;

[0158] Sort the currently acquired device failures at least twice (for example, sort multiple device failures randomly), and determine the estimated waiting time T of the corresponding device failure under each sorting scheme based on the estimated processing time and the actual occurrence time of each device failure i ';

[0159] Determine a first weight w of a corresponding device failure based on the wafer parameter information, the device information and pre-acquired reference data i , wherein the reference data includes: relevant data and historical data;

[0160] Based on the first weight w i and the estimated waiting time T i 'Determine the equivalent total waiting time T1 of each device failure in each sequencing scheme;

[0161] The preferred sorting scheme is determined based on the equivalent total waiting time T1 of different sorting schemes.

[0162] The evaluation method proposed in this embodiment is based on the current production data (such as the wafer parameter information of the first wafer sample) and pre-calculates and analyzes various possible sorting schemes to determine the execution efficiency of the sorting schemes under multiple possibilities (specifically, it can be characterized by the equivalent total waiting time), and selects the better sorting scheme (that is, the sorting scheme with a shorter equivalent total waiting time). This method includes the same beneficial effects as the above embodiment. The staff analyzes and processes the equipment failures one by one based on the selected sorting schemes, and can minimize the total impact of equipment failures on the chip production line at a faster speed.

[0163] For example, during the operation of a chip production line, multiple equipment failures may be reported in the same period, and different equipment failures may have different degrees of impact on the production line. If the processing time of failures that have a major impact on the production line is placed at the back, it may seriously affect the normal operation of the production line (or, in other words, it may cause a high defective rate of the product), while some equipment failures have a relatively small impact on product quality, but the impact of the failure on product quality may increase over time. In order to minimize the total impact of multiple equipment failures on product quality within a limited time, the evaluation method provided in this embodiment comprehensively considers multiple influencing factors such as the urgency and importance of equipment failures, and conducts a comprehensive evaluation of the adverse effects caused by equipment failures. Based on the recommended priority sorting scheme, the staff can minimize the total impact of multiple equipment failures in the shortest time. In other words, the equivalent processing efficiency of troubleshooting based on the preferred sorting scheme given by this evaluation method is the highest (that is, the elimination effect of the adverse effects of failures per unit time is the best).

[0164] For example, in some embodiments, the sorting scheme with the shortest equivalent waiting total time T1 is determined as the preferred sorting scheme.

[0165] For example, in some embodiments, the sorting schemes whose equivalent total waiting time T1 is less than the preset total waiting time T2 (which can be customized by the staff based on historical experience or production needs) can be determined as preferred sorting schemes, that is, recommended sorting schemes. The staff can select the best sorting scheme from the recommended sorting schemes based on actual conditions.

[0166] Preferably, in order to improve the accuracy and reliability of the evaluation method, in some embodiments, any possible sorting scheme for multiple equipment failures is calculated. For example, in some embodiments, based on the current first wafer sample identification or judgment that 4 equipment failures have occurred, any possible sorting is performed on the identified 4 equipment failures to obtain all possible sortings of the corresponding equipment failures, that is, 24 equipment failure sorting schemes are obtained. Further, for each sorting scheme, the estimated waiting time of each equipment failure in the current sorting scheme is determined based on the current sorting scheme and the estimated processing time of each equipment failure. For example, the order of fault processing in one of the sorting schemes is: Fault A, Fault B, Fault C, Fault D. At this time, Fault A is processed first, and the estimated processing time of Fault A is 30 minutes, and the current time from the actual occurrence of Fault B is 20 minutes, then the estimated waiting time of Fault B in this scheme is 50 minutes.

[0167] In some embodiments, the estimated processing time of each equipment failure can be set based on historical experience values. For example, for a certain equipment failure or a certain processing step where a failure occurs, the processing time of a single failure in the past period of time (such as one year or one month) is obtained, and the average processing time for a certain equipment failure or a processing step where a failure occurs is determined based on several single processing times, and the average processing time is set as the estimated processing time.

[0168] Of course, in other embodiments, when the processing time of different types of equipment failures is not much different, in order to simplify the above process and improve processing efficiency, the estimated processing time of each equipment failure can be set as the average processing time of different equipment failures. For example, when the average processing time of various types of equipment failures in the past period of time (such as one year, or one month, etc.) is 30 minutes, the estimated processing time of each equipment failure is uniformly set to 30 minutes.

[0169] Furthermore, in some embodiments, the calculation model for determining the equivalent waiting time is:

[0170]

[0171] T1 is the equivalent waiting time, w i is the first weight, T i 'Estimated waiting time.

[0172] Among them, the first weight w i The method for determining can refer to the above embodiment and will not be repeated here.

[0173] Preferably, in some embodiments, the first wafer sample (or the wafer parameter information and fault information in the first wafer sample) is periodically acquired. For example, the first wafer sample is acquired every 10 minutes, and accordingly, the estimated waiting time of different equipment faults is updated every 10 minutes, and the preferred sorting scheme is updated.

[0174] Of course, in other embodiments, in order to further ensure the timeliness of the sorting scheme, the first wafer sample can be acquired in real time, and the preferred sorting scheme can be updated in real time based on the first wafer sample acquired in real time.

[0175] The evaluation scheme in this embodiment can intelligently and in real time sort the processing order of the currently discovered equipment failures, so that the staff can minimize the overall impact of the equipment failure on the production line as soon as possible in the early stage of processing, thereby enabling the product yield to be maintained within the standard production range as soon as possible (or avoiding excessive impact of equipment failure on product yield).

[0176] Embodiment 4

[0177] Corresponding to the evaluation method in the third embodiment, the present invention further provides a device for evaluating the processing sequence of equipment failures based on risk evaluation, the device comprising:

[0178] An information acquisition unit, used to acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where the fault occurs, and an actual occurrence time of the corresponding device fault;

[0179] The estimated waiting time determination unit is used to sort the currently acquired device faults at least twice (for example, sorting multiple device faults randomly), and determine the estimated waiting time T of the corresponding device fault under each sorting scheme based on the estimated processing time and the actual occurrence time of each device fault. i ';

[0180] A first weight determination unit is used to determine a first weight w of a corresponding device failure based on the wafer parameter information, the device information and pre-acquired reference data. i , wherein the reference data includes: relevant data and historical data;

[0181] The equivalent total waiting time determining unit is configured to determine the equivalent total waiting time based on the first weight w i and the estimated waiting time T i 'Determine the equivalent total waiting time T1 of each device failure in each sequencing scheme;

[0182] The sorting scheme determining unit is used to determine a preferred sorting scheme based on the equivalent total waiting time T1 of different sorting schemes.

[0183] For example, in some embodiments, the sorting scheme with the shortest equivalent waiting total time T1 is determined as the preferred sorting scheme.

[0184] For example, in some embodiments, the sorting schemes whose equivalent total waiting time T1 is less than the preset total waiting time T2 (which can be customized by the staff based on historical experience or production needs) can be determined as preferred sorting schemes, that is, recommended sorting schemes. The staff can select the best sorting scheme from the recommended sorting schemes based on actual conditions.

[0185] In some embodiments, the estimated processing time of each equipment failure can be set based on historical experience values. For example, for a certain equipment failure or a certain processing step where a failure occurs, the processing time of a single failure in the past period of time (such as one year or one month) is obtained, and the average processing time for a certain equipment failure or a processing step where a failure occurs is determined based on several single processing times, and the average processing time is set as the estimated processing time.

[0186] Of course, in other embodiments, when the processing time of different types of equipment failures is not much different, in order to simplify the above process and improve processing efficiency, the estimated processing time of each equipment failure can be set as the average processing time of different equipment failures. For example, when the average processing time of various types of equipment failures in the past period of time (such as one year, or one month, etc.) is 30 minutes, the estimated processing time of each equipment failure is uniformly set to 30 minutes.

[0187] Furthermore, in some embodiments, the calculation model used to determine the equivalent waiting time in the equivalent waiting total time determination unit is:

[0188]

[0189] T1 is the equivalent waiting time, w i is the first weight, T i 'Estimated waiting time.

[0190] The first weight reflects the importance of the impact of equipment failure on chip production. i The method for determining can refer to the above embodiment and will not be repeated here.

[0191] Preferably, in some embodiments, the first wafer sample (or the wafer parameter information and fault information in the first wafer sample) is periodically acquired, and accordingly, the wafer acquisition unit is configured to periodically acquire the first wafer sample, and acquire the wafer parameter information of the first wafer sample, and update the fault information based on the periodically acquired wafer parameter information, as well as the actual occurrence time corresponding to the equipment failure. Accordingly, the device periodically dynamically updates the preferred sorting scheme. For example, the information acquisition unit acquires the first wafer sample every 10 minutes, and accordingly, the estimated waiting time of different equipment failures is updated every 10 minutes, and the preferred sorting scheme is updated.

[0192] Of course, in other embodiments, in order to further ensure the timeliness of the sorting scheme, the first wafer sample can be obtained in real time, and the preferred sorting scheme can be updated in real time based on the first wafer sample obtained in real time. Accordingly, the wafer acquisition unit is configured to obtain the first wafer sample in real time, obtain the wafer parameter information of the first wafer sample, and update the fault information based on the wafer parameter information obtained in real time, as well as the actual occurrence time corresponding to the equipment fault. Accordingly, the device dynamically updates the preferred sorting scheme in real time.

[0193] The evaluation scheme in this embodiment can intelligently and real-timely sort the processing order of the currently discovered equipment failure multiple times, and perform real-time evaluation and analysis of different sorting schemes, so that the staff can minimize the overall impact of the equipment failure on the production line as soon as possible in the early stage of processing, that is, the product yield can be maintained within the standard production range as soon as possible (or avoid the equipment failure from having too great an impact on the product yield).

[0194] Embodiment 5

[0195] A fifth aspect of the present invention is to provide an electronic device, such as Figure 4 As shown, it includes a memory 502, a processor 501, and a computer program stored in the memory 502 and executable on the processor 501. When the processor 501 executes the program, the steps of the method described above are implemented. For ease of explanation, only the parts related to the embodiments of this specification are shown. For specific technical details not disclosed, please refer to the method part of the embodiments of this specification. The electronic device can be any electronic device including various electronic devices, PCs, network cloud servers, or even mobile phones, tablet computers, PDAs (Personal Digital Assistants), POS (Point of Sales), vehicle-mounted computers, desktop computers, etc.

[0196] Specifically, Figure 45 is a block diagram of the electronic device structure of an exemplary embodiment of the present invention. The bus 500 may include any number of interconnected buses 500 and bridges, which link various circuits including one or more processors represented by the processor 501 and a memory represented by the memory. The bus 500 may also link various other circuits such as peripherals, voltage regulators, and power management circuits, which are well known in the art and are therefore not further described herein. The communication interface 503 provides an interface between the bus and the receiver and / or transmitter 504, which may be a separate independent receiver or transmitter 504 or the same element such as a transceiver, providing a unit for communicating with various other devices on a transmission medium. The processor 501 is responsible for managing the bus 500 and general processing, while the memory 502 may be used to store data used by the processor 501 when performing operations.

[0197] The computer readable storage medium may include a data signal propagated in a baseband or as part of a carrier wave, wherein a readable program code is carried. This propagated data signal may take a variety of forms, including but not limited to an electromagnetic signal, an optical signal, or any suitable combination of the above. The readable storage medium may also be any readable medium other than a readable storage medium, which may send, propagate, or transmit a program for use by an instruction execution system, an apparatus, or a device or used in combination with it. The program code contained on the readable storage medium may be transmitted with any appropriate medium, including but not limited to wireless, wired, optical cable, RF, etc., or any suitable combination of the above.

[0198] Program code for performing the operations of the present disclosure may be written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Java, C++, etc., and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as a separate software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server. In cases involving a remote computing device, the remote computing device may be connected to the user computing device through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computing device (e.g., through the Internet using an Internet service provider).

[0199] The above-mentioned computer-readable medium carries one or more programs. When the above-mentioned one or more programs are executed by a device, the computer-readable medium realizes the following functions: obtaining a first wafer sample, and obtaining wafer parameter information and fault information of the first wafer sample based on the first wafer sample, and the fault information includes: information of a device where a fault occurs, and an actual waiting time after the device has a corresponding fault; determining a first weight of the device failure based on the wafer parameter information, the device information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data; determining an equivalent waiting time of the device failure based on the first weight and the actual waiting time.

[0200] In other embodiments, when the one or more programs are executed by a device, the computer-readable medium implements the following functions: obtaining a first wafer sample, and obtaining wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device having a fault, and an actual occurrence time of the corresponding device fault; sorting each currently acquired device fault at least twice (for example, sorting multiple device faults randomly), and determining an estimated waiting time T of the corresponding device fault under each sorting scheme based on the estimated processing time and the actual occurrence time of each device fault. i '; Determine a first weight w of a corresponding device failure based on the wafer parameter information, the device information and pre-acquired reference data i , wherein the reference data includes: relevant data and historical data; based on the first weight w i and the estimated waiting time T i 'Determine the equivalent total waiting time T1 of each device failure in each sorting scheme; determine the preferred sorting scheme based on the equivalent total waiting time T1 of different sorting schemes.

[0201] Those skilled in the art will appreciate that the above modules can be distributed in the device according to the description of the embodiment, or can be changed accordingly and only used in one or more devices different from the embodiment. The modules of the above embodiments can be combined into one module, or further divided into multiple sub-modules.

[0202] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a computer terminal (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0203] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0204] The embodiments of the present invention are described above in conjunction with the accompanying drawings, but the present invention is not limited to the above-mentioned specific implementation modes, which are merely illustrative rather than restrictive. Under the guidance of the present invention, ordinary technicians in this field can also make many forms without departing from the scope of protection of the present invention and the claims, all of which are within the protection of the present invention.

Claims

1. A method for evaluating the processing sequence of equipment failures based on risk assessment, characterized in that: include: Acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where a fault occurs, and an actual waiting time of the device fault; Determine a first weight of a device failure based on the wafer parameter information, the device information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data; Determine an equivalent waiting time of the device failure based on the first weight and the actual waiting time, wherein the equivalent waiting time is used to characterize the urgency of the device failure to be processed; The calculation model for determining the first weight is: ； in, is the first weight, R 1, R 2, R 3. R 4. R 5. R 6. R 7 is the second weight, N 1 is the deviation degree between the total number of defects of the first wafer sample after scanning at the first station and the average number of defects of the historical wafer sample scanning at the first station in the first historical period, N 2 is the standard value of defects scanned based on the first wafer sample, N 3 is the number of special elements in the first wafer sample, N 4 is the number of times the first wafer sample is processed by the key production equipment ID predefined by the user, N 5 is the remaining waiting time of the first wafer sample, N 6 is the production priority of the first wafer sample, N 7 is the number of production failures that occurred at the first site in the first historical period.

2. The evaluation method according to claim 1, characterized in that: The calculation model of the equivalent waiting time is: in, T is the equivalent waiting time of the fault, is the first weight, is the actual waiting time for the failure.

3. The evaluation method according to claim 1, characterized in that: Also includes the steps: The device failures are prioritized based on the equivalent waiting time.

4. A device for evaluating the processing sequence of equipment failures based on risk assessment, characterized in that: include: An information acquisition module, used to acquire a first wafer sample, and acquire wafer parameter information and fault information of the first wafer sample based on the first wafer sample, wherein the fault information includes: information of a device where a fault occurs, and an actual waiting time of the device fault; A fault weight determination module, configured to determine a first weight of a device fault based on the wafer parameter information, the device information and pre-acquired reference data, wherein the reference data includes: relevant data and historical data; An equivalent waiting time determination module is used to determine the equivalent waiting time of the device failure based on the first weight and the actual waiting time, wherein the equivalent waiting time is used to characterize the urgency of the device failure to be processed; wherein the calculation model for determining the first weight is: ； in, is the first weight, R 1, R 2, R 3. R 4. R 5. R 6. R 7 is the second weight, N 1 is the deviation degree between the total number of defects of the first wafer sample after scanning at the first station and the average number of defects of the historical wafer sample scanning at the first station in the first historical period, N 2 is the standard value of defects scanned based on the first wafer sample, N 3 is the number of special elements in the first wafer sample, N 4 is the number of times the first wafer sample is processed by the key production equipment ID predefined by the user, N 5 is the remaining waiting time of the first wafer sample, N 6 is the production priority of the first wafer sample, N 7 is the number of production failures that occurred at the first site in the first historical period.

5. The evaluation device according to claim 4, characterized in that The calculation model used by the equivalent waiting time determination module to determine the equivalent waiting time is: in, T is the equivalent waiting time of the fault, is the first weight, is the actual waiting time for the failure.

6. The evaluation device according to claim 4, characterized in that Also includes: A fault sorting module is used to sort the processing priorities of the device faults based on the equivalent waiting time.

Images