WO2023000556A1 - 调度路径确定、晶圆调度方法、装置、设备及存储介质 - Google Patents

调度路径确定、晶圆调度方法、装置、设备及存储介质 Download PDF

Info

Publication number
WO2023000556A1
WO2023000556A1 PCT/CN2021/130582 CN2021130582W WO2023000556A1 WO 2023000556 A1 WO2023000556 A1 WO 2023000556A1 CN 2021130582 W CN2021130582 W CN 2021130582W WO 2023000556 A1 WO2023000556 A1 WO 2023000556A1
Authority
WO
WIPO (PCT)
Prior art keywords
machine
candidate
historical
target
site
Prior art date
Application number
PCT/CN2021/130582
Other languages
English (en)
French (fr)
Inventor
陈振豪
Original Assignee
长鑫存储技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 长鑫存储技术有限公司 filed Critical 长鑫存储技术有限公司
Publication of WO2023000556A1 publication Critical patent/WO2023000556A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B19/00—Programme-control systems
    • G05B19/02—Programme-control systems electric
    • G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/04—Manufacturing

Definitions

  • the embodiments of the present application relate to but are not limited to the field of semiconductors, and in particular relate to a scheduling path determination, wafer scheduling method, device, equipment, and storage medium.
  • the embodiments of the present application provide a scheduling route determination, wafer scheduling method, device, equipment, and storage medium.
  • an embodiment of the present application provides a scheduling path determination method, the method including:
  • each of the target scheduling paths includes each of the processes A target machine in the site.
  • an embodiment of the present application provides an apparatus for determining a scheduling path, the apparatus including:
  • the first determination module is configured to determine the first set of candidate machines for each process site based on the historical yield index of each machine in each process site in the set production process;
  • the second determining module is configured to determine a second set of candidate machines for each of the process sites based on the historical measurement indicators of the machines in each of the process sites;
  • the third determination module is configured to determine at least one target scheduling path of the production process based on the first candidate machine set and the second candidate machine set of each process site; wherein, each of the target scheduling paths includes a target machine in each of the process stations.
  • the embodiment of the present application provides a wafer scheduling method, the method comprising:
  • the production scheduling of the wafer is performed to obtain a wafer product.
  • an embodiment of the present application provides a wafer scheduling device, the device comprising:
  • the sixth determining module is configured to determine at least one target scheduling path by using the above method for determining a scheduling path;
  • the seventh determining module is configured to determine the scheduling path to be scheduled from the at least one target scheduling path based on the set process parameter conditions;
  • the scheduling module is configured to perform production scheduling on the wafer based on the scheduling path to be scheduled to obtain wafer products.
  • an embodiment of the present application provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements part of the above method when executing the program or all steps.
  • the embodiments of the present application provide a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, some or all of the steps in the above method are implemented.
  • the first candidate machine set for each process site is determined; Historical measurement indicators, determine the second candidate machine set for each process site; determine at least one target scheduling path of the production process based on the first candidate machine set and the second candidate machine set for each process site; wherein, Each target scheduling path includes a target machine in each process station.
  • the target scheduling path can be determined based on the historical yield conditions and historical measurement conditions of each machine in the process station, so that at least one target scheduling path with different historical yield conditions and different historical measurement conditions can be determined, and then can be The target scheduling path that meets different product yield and capacity requirements is obtained.
  • FIG. 1 is a schematic diagram of an implementation flow of a scheduling path determination method provided in an embodiment of the present application
  • FIG. 2 is a schematic diagram of an implementation flow of a method for determining a scheduling path provided in an embodiment of the present application
  • FIG. 3 is a schematic diagram of an implementation flow of a method for determining a scheduling path provided in an embodiment of the present application
  • FIG. 4 is a schematic diagram of an implementation flow of a method for determining a scheduling path provided in an embodiment of the present application
  • FIG. 5 is a schematic diagram of an implementation flow of a wafer scheduling method provided in an embodiment of the present application.
  • FIG. 6A is a schematic diagram of the distribution of the historical yield of each machine in a process station provided by the embodiment of the present application.
  • 6B is a schematic diagram of the distribution of measurement indicators of machine components in the historical processes of each machine in a process station provided by the embodiment of the present application;
  • FIG. 7 is a schematic diagram of the composition and structure of an apparatus for determining a dispatching route provided by an embodiment of the present application.
  • FIG. 8 is a schematic diagram of the composition and structure of a wafer scheduling device provided in an embodiment of the present application.
  • FIG. 9 is a schematic diagram of a hardware entity of a computer device provided by an embodiment of the present application.
  • first/second in the application documents, add the following explanation.
  • first/second/third are only used to distinguish similar objects and do not mean Regarding the specific ordering of objects, it can be understood that “first/second/third” can be exchanged for a specific order or sequence if allowed, so that the embodiments of the application described here can performed in an order other than that shown or described.
  • An embodiment of the present application provides a method for determining a scheduling path, and the method may be executed by a processor of a computer device.
  • the computer device refers to any server, notebook computer, tablet computer, desktop computer, smart TV, set-top box, mobile device (such as mobile phone, portable video player, personal digital assistant, dedicated messaging device, portable game device), etc. Appropriate equipment with data processing capabilities.
  • Fig. 1 is a schematic diagram of the implementation flow of a dispatching path determination method provided in the embodiment of the present application. As shown in Fig. 1, the method includes the following steps S101 to S103:
  • Step S101 based on the historical yield index of each machine in each process station in the set production process, determine a first candidate machine set for each process station.
  • the set production process may be determined according to the production flow of the wafer product to be produced, including at least one process performed on the wafer during the production process of the wafer product, wherein each process may correspond to a process station , where the process can be performed on the wafer at the process station.
  • a process site may include at least one machine of the same type, and in each process of the production process, a machine may be determined from the corresponding process site and used to perform the process on the wafer .
  • the historical yield index of the machine can be any suitable index that can reflect the yield rate of the wafers processed by the machine in the historical process, for example, the maximum value, the minimum yield rate of the wafer processed in the historical process One or more of value, mean, mode, or median.
  • the wafer processed by the machine can be tested to obtain the yield data of the processed wafer, and record the yield data.
  • the historical yield index of each machine can be obtained.
  • statistics may be made on the yield data of the wafers processed by the machine within the set historical time range to obtain the historical yield index of the machine.
  • a first set of candidate machines for the process site may be determined based on the historical yield indicators of the machines in the process site.
  • the first set of machine candidates in the process station may include at least one machine in the process station.
  • any suitable method may be used according to the actual situation to determine the first set of candidate machines in the process site based on the historical yield indicators of the machines in the process site, which is not limited here.
  • the machines whose historical yield index of each machine in the process site meets the set yield conditions can be added to the first candidate machine set of the process site, or the historical yield rate of each machine in the process site can be The machines whose indicators do not meet the set yield conditions are added to the first candidate machine set of the process site, and a specific number of machines with the highest historical yield indicators among the machines in the process site can also be added to the first candidate machine set of the process site.
  • Step S102 based on the historical measurement indicators of each machine in each process site, determine a second candidate machine set for each process site.
  • the historical measurement index of the machine may be any suitable index obtained through measurement in the historical process of the machine.
  • the historical measurement index may include at least one of the following: a measurement index of machine components in historical processes, and a measurement index of wafer products in historical processes.
  • the measurement index of the machine components in the historical process refers to the index obtained by measuring the state of each component in the machine in the historical process, including but not limited to the temperature index of each component in the machine, the inside or outside of the component One or more of the gas flow indicators, etc.
  • the measurement indicators of wafer products in the historical process refer to the indicators obtained by measuring the state of the wafer products processed by the machine in the historical process, including but It is not limited to one or more of temperature indicators, critical dimensions, etc. of wafer products.
  • appropriate measurement sensors and measurement equipment can be used to measure each component or wafer product in the machine during the machine execution process according to the actual indicators to be measured to obtain the measurement indicators. And record the obtained measurement indicators. By querying the measurement indicators of the historical records, the historical measurement indicators of each machine can be obtained. In some embodiments, the measurement index of the machine within the set historical time range can be queried to obtain the historical measurement index of the machine.
  • each machine it can be measured every time the machine executes the process to obtain the historical measurement index of the full amount of the machine, or based on the set measurement strategy, it can Measurement is carried out in the process to obtain the historical measurement index of the machine part, which is not limited here.
  • a second candidate machine set for the process station may be determined based on the historical measurement indicators of the machines in the process station.
  • the second candidate machine set of the process station may include at least one machine in the process station.
  • any suitable method may be used according to the actual situation to determine the second candidate machine set of the process site based on the historical measurement indicators of each machine in the process site, which is not limited here.
  • the machines whose historical measurement indicators of each machine in the process site meet the set index conditions can be added to the second candidate machine set of the process site, or the historical measurement indicators of each machine in the process site Machines that do not meet the set index conditions are added to the second candidate machine set of the process site, and a specific number of machines with the highest historical measurement indicators among the machines in the process site can also be added to the second candidate of the process site Machine collection.
  • Step S103 based on the first candidate machine set and the second candidate machine set of each process site, determine at least one target scheduling path of the production process; wherein each target scheduling path includes each A target machine in the process station.
  • At least one target machine tool of the process site may be determined based on the first set of candidate machines and the second set of candidate machines of the process site.
  • at least one target machine tool of the process site may be determined in an appropriate manner based on the first candidate machine set and the second candidate machine set of the process site according to actual conditions, which is not limited here. For example, the intersection of the first candidate machine set and the second candidate machine set of the process site can be obtained, and at least one target machine can be determined from the obtained intersection; A union is obtained from the candidate machine sets, and at least one target machine is determined from the obtained union.
  • the scheduling sequence of the wafer among the various process stations can be determined. According to the scheduling sequence, a target machine is selected from each process station, and a target scheduling path of the production process can be obtained.
  • the above step S103 may include the following steps S111 to S112:
  • Step S111 taking the intersection of the first candidate machine set and the second candidate machine set for each of the process stations to obtain at least one target machine for each of the process stations;
  • Step S112 based on at least one target machine of each process station, determine at least one target scheduling path in the production process; wherein, each of the target scheduling paths includes a target of each process station Machine.
  • each of the target machines includes at least one process chamber, and the above step S103 may include the following steps S121 to S122:
  • Step S131 for each machine in the first candidate machine set and the second candidate machine set of each process site, determine at least one candidate process chamber of the machine.
  • each process of the production process the processing of the wafer can be completed in the process chamber of the machine.
  • Each tool station may contain at least one process chamber.
  • at least one candidate process chamber of the machine tool may be determined from at least one process chamber of the machine tool in any suitable manner according to actual conditions, which is not limited here.
  • at least one candidate process chamber can be randomly determined from at least one process chamber of the machine, or based on the historical yield index and/or historical measurement index of each process chamber in the machine, from at least one process chamber of the machine At least one candidate process chamber is determined in one process chamber.
  • Step S132 based on at least one candidate process chamber for each machine in the first candidate machine set and at least one candidate process chamber for each machine in the second candidate machine set for each process site, determine At least one target scheduling path in the production process; wherein, each of the target scheduling paths includes a target process chamber in each of the process stations.
  • a target machine is selected from each process station, and a target process chamber is determined from at least one candidate process chamber of the target machine, A target scheduling path including a target process chamber in each process station can be obtained.
  • the first candidate machine set for each process site is determined; Historical measurement indicators, determine the second candidate machine set for each process site; determine at least one target scheduling path of the production process based on the first candidate machine set and the second candidate machine set for each process site; wherein, Each target scheduling path includes a target machine in each process station.
  • the target scheduling path can be determined based on the historical yield conditions and historical measurement conditions of each machine in the process station, so that at least one target scheduling path with different historical yield conditions and different historical measurement conditions can be determined, and then can be The target scheduling path that meets different product yield and capacity requirements is obtained.
  • An embodiment of the present application provides a method for determining a scheduling path, and the method may be executed by a processor of a computer device. As shown in Figure 2, the method includes the following steps S201 to S206:
  • Step S201 based on the set yield rate statistical conditions, determine at least one historical yield rate of each machine in each process station in the set production process.
  • the historical yield of the machine is the yield of the wafers processed by the machine in the historical process
  • the yield of the wafer can represent the pass rate of the chips on the wafer. For example, if 1000 chips can be cut out of a wafer, and a 0/1 test is performed on each chip, the yield of the wafer can be obtained as the ratio of the number of chips measured as 1 to the total number of chips 1000.
  • the statistical condition for yield rate may be a preset statistical condition for statistically calculating the historical yield rate of a tool, and may include but not limited to one or more of statistical time range, process chamber to be counted, and the like. At least one historical yield rate of each machine in each process station may be obtained statistically based on the yield rate statistical condition.
  • the statistical yield rate condition may include a set statistical time range, then the yield rate of wafers processed by each machine can be counted within the statistical time range to obtain at least one historical yield rate of each machine .
  • the yield statistical condition may include the set process chamber to be counted, and then the yield rate of the wafers processed by the process chamber to be counted set in each machine can be counted to obtain the yield rate of each machine At least one historical yield.
  • Step S202 based on at least one historical yield rate of each machine in each process site, determine the historical yield distribution information of each machine in each process site.
  • the distribution of at least one historical yield rate of each machine in each process station can be analyzed to obtain the historical yield distribution information of each machine in each process station.
  • the historical yield distribution information of the machine may include, but not limited to, one or more of the average, maximum, minimum, mode, and specific quantile of the historical yield of the machine, and may also include The distribution feature of the historical yield rate of the machine is not limited here.
  • the historical yield distribution information of each machine in each process station may be determined in an appropriate manner according to the information actually contained in the historical yield distribution information, which is not limited here. For example, statistical values such as the average value, maximum value, minimum value, mode number, and specific quantiles of the historical yield rate of the machine can be obtained by directly counting at least one historical yield of the machine; for the machine The distribution feature of the historical yield rate can be extracted from at least one historical yield rate of the machine by using any suitable feature extraction algorithm.
  • Step S203 for each of the process sites, determine the first candidate machine whose historical yield distribution information in the process site satisfies a preset yield distribution condition.
  • the preset yield distribution condition may be a condition that the historical yield distribution information of the first candidate machine must meet in advance according to the actual situation, and may include but not limited to the limitation of the statistical value of the historical yield of the machine One or more of conditions, restrictions on the distribution characteristics of the historical yield rate of the machine, and the like.
  • the historical yield distribution information of the machine is statistical values such as the average, maximum, minimum, mode, and specific quantile of the historical yield of the machine
  • the preset yield distribution condition can be a preset
  • the value range of the statistical value, at least one of the statistical values such as the average value, maximum value, minimum value, mode number, and specific quantile of the historical yield rate in the process site can be within the value range of the preset statistical value
  • the machine is determined as the first candidate machine.
  • the historical yield distribution information of the machine is the distribution feature of the historical yield rate of the machine
  • the preset yield distribution condition can be the preset distribution feature
  • the distribution feature of the historical yield rate in the process site can be combined with the preset At least one machine that matches the distribution feature is determined as the first candidate machine.
  • Step S204 adding the first candidate machine of each process site to the first candidate machine set of the process site.
  • Step S205 based on the historical measurement indicators of each machine in each process site, determine a second candidate machine set for each process site.
  • Step S206 based on the first set of candidate machines and the second set of candidate machines of each process site, determine at least one target scheduling path of the production process; wherein each target scheduling path includes each A target machine in the process station.
  • steps S205 to S206 correspond to the aforementioned steps S102 to S103, and for implementation, reference may be made to the specific implementation manners of the aforementioned steps S102 to S103.
  • the historical yield distribution information includes the average value of the historical yield
  • the first candidate for determining the historical yield distribution information in the process site in the above step S203 that satisfies the preset yield distribution condition Machines can include:
  • Step S211 determining a first number of machines with the highest historical yield average value in the process site as first candidate machines.
  • the first number may be a value determined according to actual conditions, such as 1, 2, 3, 5, etc., which is not limited here.
  • the first quantity can be set by the user or defaulted by the system.
  • At least one historical yield rate of each machine in each process station in the set production process is determined; based on at least one historical yield rate of each machine in each process station Yield, determine the historical yield distribution information of each machine in each process site; for each process site, determine the first candidate machine whose historical yield distribution information in the process site meets the preset yield distribution conditions; The first candidate machine of a process site is added to the first candidate machine set of the process site.
  • the historical yield distribution information of each machine in the first candidate machine set of the process site can meet the preset yield distribution condition, so that the target machine of each process site in the target scheduling path can be improved. Yield, which in turn can improve the yield and productivity of the production process.
  • An embodiment of the present application provides a method for determining a scheduling path, and the method may be executed by a processor of a computer device. As shown in Figure 3, the method includes the following steps S301 to S304:
  • Step S301 based on the historical yield index of each machine in each process station in the set production process, determine a first candidate machine set for each process station.
  • step S301 corresponds to the aforementioned step S101, and the specific implementation manner of the aforementioned step S101 can be referred to for implementation.
  • Step S302 for each of the process stations, based on the set measurement index statistical conditions, determine the historical measurement indexes of each machine in the process station.
  • the measurement index statistical conditions may be pre-set conditions for filtering and counting the historical measurement indexes of the machine, which may include but not limited to the set wafer products, processes, process chambers, sensors, One or more of parameters such as process steps and key dimensions. At least one historical measurement index of each machine in each process station may be obtained through screening and statistics based on statistical conditions of the measurement index.
  • each component or wafer product in the machine can be measured during the process of each machine performing a process to obtain a large number of measurement indicators, and the obtained measurement indicators can be recorded.
  • the historical measurement indicators that meet the statistical conditions of the measurement indicators can be obtained from a large number of recorded historical measurement indicators, so that Obtain the historical measurement indicators of each machine in the process site.
  • Step S303 based on the historical measurement indicators of each machine in each process site, determine a second candidate machine set for each process site.
  • Step S304 based on the first set of candidate machines and the second set of candidate machines of each process site, determine at least one target scheduling path of the production process; wherein, each target scheduling path includes each A target machine in the process station.
  • steps S303 to S304 correspond to the aforementioned steps S102 to S103, and for implementation, reference may be made to the specific implementation manners of the aforementioned steps S102 to S103.
  • the above step S303 may include the following steps S311 to S313:
  • Step S311 determining the target value range of the measurement index of each process station.
  • the target value range of the measurement index of each process station may be preset or determined based on the historical measurement indexes of the process station, which is not limited here.
  • each process station may correspond to multiple measurement indicators, and the target value range may include the target value range of each measurement indicator.
  • the target value ranges of the same measurement index in different process stations may be the same or different.
  • Step S312 for each of the process stations, determine second candidate machines in the process stations whose historical measurement indexes are within the target value range of the measurement indexes of the process stations.
  • At least one machine in each process station whose historical measurement index is within the target value range of the measurement index of the process station may be determined as the second candidate machine of the process station.
  • Step S313 adding the second candidate machine of each process site into the second candidate machine set of the process site.
  • the above step S311 may include the following steps S321 to S323:
  • Step S321 for each of the process stations, determine a second number of third candidate machines with the highest historical yield average value in the process stations.
  • the second number may be a numerical value determined according to actual conditions, such as 1, 2, 3, 5, etc., which is not limited here.
  • the second quantity may be set by the user, or may be defaulted by the system.
  • the second number of machines with the highest historical yield average value in each process station may be determined as the third candidate machines of the process station.
  • Step S322 adding each third candidate machine of each process site into the third candidate machine set of the process site.
  • Step S323 based on the maximum value and the minimum value of the historical measurement indicators of each machine in the third candidate machine set of each process site, determine the target value range of the measurement index of each process site .
  • the minimum value of the historical measurement indicators of each machine in the third candidate machine set in the process site can be used as the lower boundary of the target value range
  • the maximum value can be used as the upper boundary of the target value range, so as to determine the process
  • the target value range of the measurement index of the site that is, it should be greater than or equal to the minimum value and less than or equal to the maximum value.
  • the value range of historical measurement indicators in the second number of machines with the highest average value of historical yield in each process site can be determined as the target value range of each process site, so that based on the target value range
  • the determined second candidate machine can have a higher yield rate, which can further increase the yield rate of the target machine at each process station in the target scheduling path, and further improve the yield rate and production capacity of the production process.
  • the historical measurement indexes of each machine in the process station are determined based on the set measurement index statistical conditions. In this way, the historical measurement indicators of each machine in each process station can be determined simply and quickly.
  • An embodiment of the present application provides a method for determining a scheduling path, and the method may be executed by a processor of a computer device. As shown in Figure 4, the method includes the following steps S401 to S406:
  • Step S401 based on the historical yield index of each machine in each process station in the set production process, determine a first candidate machine set for each process station.
  • Step S402 based on the historical measurement indicators of each machine in each process site, determine a second candidate machine set for each process site.
  • Step S403 based on the first candidate machine set and the second candidate machine set of each process site, determine at least one target scheduling path of the production process; wherein each target scheduling path includes each A target machine in the process station.
  • steps S401 to S403 correspond to the aforementioned steps S101 to S103 , and for implementation, reference may be made to the specific implementation manners of the aforementioned steps S101 to S103 .
  • Step S404 determining a deviation index representing the yield deviation of each machine in each of the process stations.
  • the deviation index of the process site can be any suitable index that can characterize the yield deviation of each machine in the process site, including but not limited to the standard deviation, average deviation, relative One or more of mean deviation, variance, standard deviation, etc.
  • the deviation index of the process station may include the deviation index of at least one machine in the process station. By performing statistical analysis on the historical yield rate of each machine in the process station, the deviation index of at least one machine can be determined, that is, the deviation index of the process station.
  • Step S405 adding the process sites whose deviation index is greater than the deviation threshold in each process site to the abnormal process site set.
  • the deviation threshold may be an appropriate value determined according to actual conditions for judging whether the yield deviation index of the machine is abnormal.
  • the deviation threshold may be set by the user or defaulted by the system, which is not limited here.
  • the deviation index of each process station can include the deviation index of at least one machine in the process station, and when the deviation index of at least one machine is greater than the deviation threshold, it can be determined that the process station is an abnormal process station, so that Add this crafting station to the collection of unusual crafting stations.
  • the process site is an abnormal process site, and the process site is added to the abnormal process Collection of sites.
  • step S406 an early warning is given to a third number of process sites with the largest deviation indicators in the set of abnormal process sites.
  • the third number may be a value determined according to actual conditions, such as 1, 2, 3, 5, etc., which is not limited here.
  • the third quantity can be set by the user or defaulted by the system.
  • the third number of process stations with the largest deviation index in the abnormal process station set can be determined.
  • the deviation index of the two process sites can be determined by comparing the maximum value of the deviation index of each machine in the two process sites, or by comparing the The average value of the deviation index of each machine is used to determine the size of the deviation index in the two process stations, which is not limited here. at the time of implementation. Those skilled in the art can use any suitable method to compare the magnitude of the deviation index in different process stations according to the actual situation.
  • Early warnings to process sites can include but are not limited to one or more of voice early warnings, indicator lights early warnings, telephone early warnings, email early warnings, instant messaging software information early warnings, etc. During implementation, those skilled in the art can use according to actual conditions. A suitable way is to give an early warning to the third number of process stations with the largest deviation index in the set of abnormal process stations, which is not limited here.
  • the deviation index of the process station is greater than Abnormal machines that deviate from the threshold, and give an early warning to each abnormal machine.
  • the above step S404 may include the following steps S411 to S412:
  • Step S411 determining the average value and average deviation of the historical yield of each machine in each process station.
  • Step S412 for each of the process stations, determine the ratio of the average value of the historical yield of each machine in the process station to the average deviation as the deviation index of the process station.
  • the ratio of the average value of the historical yield of each machine in the process station to the average deviation can be determined as the deviation index of each machine, so as to obtain the deviation index of the process station.
  • the absolute value of the ratio of the average value of the historical yield of the machine to the average deviation may be determined as the deviation index of the machine.
  • the deviation index representing the yield deviation situation of each machine in each process site is determined; the process site whose deviation index is greater than the deviation threshold in each process site is added to the abnormal process site set; the abnormal process site set Early warning is given to the third number of process stations with the largest deviation indicators.
  • abnormal process stations in the production process can be found in time, and abnormal machines in the abnormal process stations can be found in time, so that users can maintain the abnormal process stations and abnormal machines in time, thereby improving the stability of the production process.
  • the determination of the scheduling path in the production process can be further optimized, thereby further improving the yield and production capacity of wafer products.
  • An embodiment of the present application provides a wafer scheduling method, which can be executed by a processor of a computer device. As shown in Figure 5, the method includes the following steps S501 to S503:
  • step S501 at least one target scheduling path is determined by using the scheduling path determination method described in any of the above-mentioned embodiments.
  • Step S502 based on the set process parameter conditions, determine a scheduling path to be scheduled from the at least one target scheduling path.
  • the process parameter conditions may include any suitable parameter conditions for controlling parameters in the production process, for example, yield conditions for controlling wafer yield, time conditions for controlling product production time, and the like.
  • suitable parameter conditions for controlling parameters in the production process for example, yield conditions for controlling wafer yield, time conditions for controlling product production time, and the like.
  • those skilled in the art can determine appropriate process parameter conditions according to actual conditions, which are not limited here.
  • the target scheduling path satisfying the process parameter condition among the at least one target scheduling path can be determined as the scheduling path to be scheduled.
  • the target scheduling path whose yield rate of the wafer reaches the set yield threshold can be determined as the scheduling path to be scheduled; the target scheduling path whose production time of the product does not exceed the set duration threshold can also be determined as the scheduling path to be scheduled Scheduling path.
  • the process parameter conditions include at least one of the following: yield conditions and duration conditions.
  • Step S503 based on the scheduling path to be scheduled, perform production scheduling on the wafer to obtain a wafer product.
  • the scheduling path to be scheduled may include a target machine in each process station.
  • the wafer products can be sequentially dispatched to the target machines of each process station in the scheduling path to be dispatched for process processing to obtain wafer products.
  • the above step S502 may include the following steps S511 to S512:
  • Step S511 for each target scheduling path, based on the historical process parameters of the target machine in each process station in the target scheduling path, determine the process parameters of the target scheduling path.
  • the historical process parameters of the machine may be the process parameters achieved by the machine during the historical process, which may include but not limited to one or more of historical wafer yield, historical product production time, and the like.
  • the process parameters of the target scheduling path refer to the process parameters that can be achieved in the process of wafer production scheduling based on the target scheduling path and obtaining wafer products, which may include but not limited to wafer yield rate, product production time, etc. one or more.
  • the process parameters of the target scheduling route can be estimated. For example, when the process parameter is the wafer yield rate, the average value of the historical wafer yield rate of the target machine in each process station in the target scheduling path can be determined as the wafer yield rate of the target scheduling path, and the The minimum value of the historical wafer yield rate of the target machine in each process station in the target scheduling path is determined as the wafer yield rate of the target scheduling path, which is not limited here.
  • the average value of the historical product production time of the target machine in each process station in the target scheduling path can be determined as the product production time of the target scheduling path, and the target scheduling The maximum value of the historical product production time of the target machine in each process station in the path is determined as the product production time of the target scheduling path.
  • Step S512 determining the target scheduling path whose process parameter satisfies the process parameter condition among the at least one target scheduling path as the scheduling path to be scheduled.
  • At least one target scheduling path is determined by using the scheduling path determination method described in any of the above embodiments; based on the set process parameter conditions, the scheduling path to be scheduled is determined from at least one target scheduling path; Based on the scheduling path to be scheduled, the production scheduling of the wafer is performed to obtain the wafer product.
  • the scheduling path to be scheduled that meets the set process parameter conditions can be determined from at least one target scheduling path determined to meet different product yield and production capacity requirements, so that the production process of the wafer product can meet the set process parameter condition.
  • the embodiment of the present application provides a scheduling route determination method, which can collect the measurement results during the production process, the environmental measurement values collected by the sensors of the machine, and the results of the yield test of the chip, etc., and automatically generate wafers The optimal scheduling path to ensure the highest probability of producing products with the best quality, so that the maximum production capacity can be achieved.
  • the dispatching route determination method provided in the embodiment of the present application includes the following steps S601 to S604:
  • Step S601 for each process station in the set production process, obtain the first candidate machine set Set ⁇ Z ⁇ of the process station.
  • the first set of candidate machines Se ⁇ Z ⁇ of each process station includes N machines with the largest average historical yield rate in the process station, where N is a set positive integer.
  • FIG. 6A is a schematic diagram of the distribution of historical yields of each machine in a process station provided by an embodiment of the present application.
  • the horizontal axis includes machines A to E in the process station
  • the vertical axis is the average value of the historical yield of the machines, where the machines are sorted from large to small according to the average historical yield They are machines D, B, E, A, and C respectively. If the first candidate machine set Set ⁇ Z ⁇ of the process site includes the three machines with the largest average historical yield rate in the process site, then the process The first candidate machine set Set ⁇ Z ⁇ of the site is ⁇ machine D, machine B, machine E ⁇ .
  • Step S602 based on the measurement index of the machine components in the historical process of each machine in each process station and the measurement index of the wafer product in the historical process, respectively determine the fourth candidate machine set of each process site Set ⁇ A ⁇ and the fifth set of candidate machines Set ⁇ B ⁇ .
  • the fourth candidate machine set Set ⁇ A ⁇ for each process site can be determined based on the measurement index of the machine components in the historical process of each machine in each process site.
  • the fourth candidate machine set Set ⁇ A ⁇ of each process site can be determined through the following steps S611 to S613:
  • Step S611 for each machine in each process site, according to one or more of the set parameters such as wafer products, processes, process chambers, sensors, process steps, etc., from a large number of historical processes
  • the measurement index of the machine components in the historical process of the machine is obtained from the measurement data of the machine components;
  • Step S612 for each process site, analyze the measurement indicators of the machine components in the historical processes of the M machines with the largest average historical yield rate in the process site, and obtain the historical processes of the M machines The maximum value USL w and the minimum value LSL w among the measurement indicators of the machine components, where M is a set positive integer;
  • Step S613 for each process site, add the machine with the measurement index of the machine components in the historical process in the process site between the maximum value USL w and the minimum value LSL w to the fourth candidate machine of the process site Collection Set ⁇ A ⁇ .
  • FIG. 6B is a schematic diagram of the distribution of measurement indicators of machine components in the historical process of each machine in a process station provided by an embodiment of the present application.
  • the horizontal axis includes machines A to E in the process station, and the vertical axis is the measurement index of the machine components in the historical process of the machine, wherein the measurement index of the machine components in the historical process
  • the machines whose indicators are between the maximum value USL w and the minimum value LSL w include machines B, D, and E, then the fourth candidate machine set Set ⁇ A ⁇ of the process site is ⁇ machine B, machine D, Machine E ⁇ .
  • the fifth candidate machine set Set ⁇ B ⁇ for each process site can be determined based on the measurement index of the wafer product in the historical process of each machine in each process site.
  • the fifth candidate machine set Set ⁇ B ⁇ for each process site can be determined through the following steps S621 to S623:
  • Step S621 for each machine in each process site, according to one or more of the set parameters such as wafer products, processes, process chambers, critical dimensions, etc., process the wafer from a large number of historical processes
  • the measurement index of the wafer product in the historical process of the machine is obtained from the measurement data of the product;
  • Step S622 for each process site, analyze the measurement indicators of the wafer products in the historical processes of the L machines with the largest average historical yield rate in the process site, and obtain the historical processes of the L machines The maximum value USL s and the minimum value USL s in the measurement index of the wafer product, wherein L is a set positive integer;
  • Step S623 for each process site, add the machine with the measurement index of the wafer product in the historical process in the process site between the maximum value USL s and the minimum value LSL s to the fifth candidate machine of the process site Collection Set ⁇ B ⁇ .
  • both the fourth candidate machine set and the fifth candidate machine set can be implemented as the second candidate machine set in the foregoing embodiments.
  • Step S603 based on the first set of candidate machines Set ⁇ Z ⁇ , the fourth set of candidate machines Set ⁇ A ⁇ and the fifth set of candidate machines Set ⁇ B ⁇ of each process station, determine at least one target schedule of the production process path; wherein, each target scheduling path includes a target machine in each of the process stations.
  • the intersection of the first set of candidate machines Set ⁇ Z ⁇ , the fourth set of candidate machines Set ⁇ A ⁇ and the fifth set of candidate machines Set ⁇ B ⁇ of each process site can be obtained, and the obtained intersection set can be determined At least one target machine for each process station.
  • the scheduling sequence of the wafer among the various process stations can be determined.
  • a target machine is selected from each process station, and a target scheduling path of the production process can be obtained.
  • the automatically generated target scheduling path can be displayed through the scheduling path query interface on the terminal device, and the user can input statistical time, process chamber and other yield statistical conditions on the scheduling path query interface, as well as wafer products, Test the statistical conditions of measurement indicators such as ID, parameters, and sorted statistical indicators, and click the query button on the scheduling path query interface to automatically generate at least one target scheduling path based on the input yield statistical conditions and measurement indicator statistical conditions , and the automatically generated target scheduling path is displayed on the scheduling path query interface. For each target machine in the target scheduling path, different colors may be used for display according to the yield rate of the target machine.
  • red can be used to display target machines with a yield rate less than 25%
  • yellow can be used to show target machines with a yield rate greater than or equal to 25% and less than 75%
  • green can be used to show target machines with a yield rate greater than or equal to 75%.
  • Step S604 based on the yield deviation index of each machine in each process site, determine the abnormal process site and the abnormal machines in the abnormal process site, and give an early warning to the abnormal process site and the abnormal machines in the abnormal process site.
  • the yield deviation index of the machine may be the absolute value of the ratio between the average value of the historical yield of the machine and the deviation of the historical yield.
  • the yield deviation index is very large. In this case, the yield rate of the final product of this machine may still be not high. Therefore, a machine with a large yield deviation index can be regarded as an abnormal machine, and the process site to which the abnormal machine belongs is an abnormal process site. It is necessary to screen out the abnormal machine and the corresponding abnormal process site for early warning to assist in further optimization. Policy target dispatch path.
  • FIG. 7 is a schematic diagram of the composition and structure of a dispatching route determination device provided in an embodiment of the present application.
  • the dispatching route determination device 700 includes: a first determination module 710, a second determination module 720, and a third determination module 730, of which:
  • the first determination module 710 is configured to determine a first set of candidate machines for each process site based on the historical yield indicators of each machine in each process site in the set production process;
  • the second determination module 720 is configured to determine a second set of candidate machines for each of the process sites based on the historical measurement indicators of the machines in each of the process sites;
  • the third determining module 730 is configured to determine at least one target scheduling path of the production process based on the first set of candidate machines and the second set of candidate machines of each of the process sites; wherein, each of the target scheduling A target machine in each of said process stations is included in the path.
  • the historical yield index includes at least one historical yield
  • the first determining module is further configured to: determine the yield rate in each process station in the set production process based on the set yield statistical condition. At least one historical yield rate of each machine; based on at least one historical yield rate of each machine in each said process site, determine the historical yield distribution information of each machine in each said process site; for each The process site, determine the first candidate machine whose historical yield distribution information in the process site satisfies the preset yield distribution condition; add the first candidate machine of each process site to the first candidate machine of the process site A collection of candidate machines.
  • the historical yield distribution information includes the average value of historical yield
  • the first determination module is further configured to: assign the first number of machines with the highest average historical yield in the process site to The station is determined as the first candidate station.
  • the device further includes: a fourth determining module, configured to, for each of the process stations, determine the historical measurement of each machine in the process station based on the set measurement index statistical conditions index.
  • the fourth determination module is further configured to: determine the target value range of the measurement index of each of the process stations; for each of the process stations, determine the historical measurement The second candidate machine whose index is within the target value range of the measurement index of the process station; adding the second candidate machine of each process station to the second candidate machine set of the process station.
  • the fourth determination module is further configured to: for each of the process sites, determine the second number of third candidate machines with the highest average value of historical yield in the process site; Each third candidate machine of the process site is added to the third candidate machine set of the process site; based on the historical measurement indicators of each machine in the third candidate machine set of each process site The maximum and minimum values of each process station are determined to determine the target value range of the measurement index of each process station.
  • the historical measurement indicators include at least one of the following: measurement indicators for tool components in historical processes, and measurement indicators for wafer products in historical processes.
  • the third determination module is further configured to: take the intersection of the first set of candidate machines and the second set of candidate machines for each of the process sites to obtain at least one set of candidate machines for each of the process sites Target machines; based on at least one target machine of each of the process stations, determine at least one target scheduling path in the production process; wherein, each of the target scheduling paths includes one of each of the process stations target machine.
  • each of the target machines includes at least one process chamber
  • the third determination module is further configured to: for each of the process stations, a first candidate machine set and a second candidate machine set For each machine in the set, determine at least one candidate process chamber of the machine; based on the at least one candidate process chamber and the second For at least one candidate process chamber of each machine in the candidate machine set, at least one target scheduling path in the production process is determined; wherein, each of the target scheduling paths includes one of each of the process stations target process chamber.
  • the device further includes: a fifth determining module configured to determine a deviation index representing the yield deviation of each machine in each of the process stations; an adding module configured to add each of the Among the process stations, the process stations whose deviation indicators are greater than the deviation threshold are added to the set of abnormal process stations; the early warning module is configured to give early warning to the third number of process stations with the largest deviation indicators in the set of abnormal process stations.
  • the fifth determination module is further configured to: determine the average value and the average deviation of the historical yield of each tool in each of the process stations; for each of the process stations, the process The ratio of the average value of the historical yield of each machine in the station to the average deviation is determined as the deviation index of the process station.
  • FIG. 8 is a schematic diagram of the composition and structure of a wafer scheduling device provided in an embodiment of the present application.
  • the wafer scheduling device 800 includes: a sixth determination module 810, a seventh determination module 820, and a scheduling module 830, wherein :
  • the sixth determining module 810 is configured to determine at least one target scheduling path by using the above scheduling path determination method
  • the seventh determining module 820 is configured to determine a scheduling path to be scheduled from the at least one target scheduling path based on the set process parameter conditions;
  • the scheduling module 830 is configured to perform production scheduling on wafers based on the scheduling path to be scheduled to obtain wafer products.
  • the seventh determination module is further configured to: for each of the target scheduling paths, determine the target scheduling based on the historical process parameters of the target machine in each process station in the target scheduling path Process parameter of the path: determining the target scheduling path whose process parameter satisfies the condition of the process parameter among the at least one target scheduling path as the scheduling path to be scheduled.
  • the process parameter conditions include at least one of the following: yield conditions and duration conditions.
  • the above dispatching route determination method is implemented in the form of software function modules and sold or used as an independent product, it can also be stored in a computer-readable storage medium.
  • the essence of the technical solution of the embodiment of the present application or the part that contributes to the related technology can be embodied in the form of a software product, the software product is stored in a storage medium, and includes several instructions to make a A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes: various media that can store program codes such as U disk, mobile hard disk, read-only memory (Read Only Memory, ROM), magnetic disk or optical disk.
  • embodiments of the present application are not limited to any specific combination of hardware and software.
  • an embodiment of the present application provides a computer device, including a memory and a processor, the memory stores a computer program that can run on the processor, and the processor implements the steps in the above method when executing the program.
  • an embodiment of the present application provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the steps in the above method are implemented.
  • an embodiment of the present application provides a computer program product
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program, and when the computer program is read and executed by a computer, the above method can be implemented. some or all of the steps.
  • the computer program product can be specifically realized by means of hardware, software or a combination thereof.
  • the computer program product is embodied as a computer storage medium, and in another optional embodiment, the computer program product is embodied as a software product, such as a software development kit (Software Development Kit, SDK) etc. Wait.
  • FIG. 9 is a schematic diagram of a hardware entity of a computer device in the embodiment of the present application.
  • the hardware entity of the computer device 900 includes: a processor 901, a communication interface 902, and a memory 903, wherein:
  • Processor 901 generally controls the overall operation of computer device 900 .
  • the communication interface 902 enables the computer device to communicate with other terminals or servers through the network.
  • the memory 903 is configured to store instructions and applications executable by the processor 901, and can also cache data to be processed or processed by the processor 901 and various modules in the computer device 900 (for example, image data, audio data, voice communication data and Video communication data) can be realized by flash memory (FLASH) or random access memory (Random Access Memory, RAM).
  • FLASH FLASH
  • RAM Random Access Memory
  • the disclosed devices and methods may be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division.
  • the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms of.
  • the units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed to multiple network units; Part or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be used as a single unit, or two or more units can be integrated into one unit; the above-mentioned integration
  • the unit can be realized in the form of hardware or in the form of hardware plus software functional unit.
  • the above-mentioned integrated units in the embodiments of the present application are implemented in the form of software function modules and sold or used as independent products, they may also be stored in a computer-readable storage medium.
  • the computer software products are stored in a storage medium and include several instructions to make A computer device (which may be a personal computer, a server, or a network device, etc.) executes all or part of the methods described in the various embodiments of the present application.
  • the aforementioned storage medium includes various media capable of storing program codes such as removable storage devices, ROMs, magnetic disks or optical disks.
  • the first candidate machine set for each process site is determined; Historical measurement indicators, determine the second candidate machine set for each process site; determine at least one target scheduling path of the production process based on the first candidate machine set and the second candidate machine set for each process site; wherein, Each target scheduling path includes a target machine in each process station.
  • the target scheduling path can be determined based on the historical yield conditions and historical measurement conditions of each machine in the process station, so that at least one target scheduling path with different historical yield conditions and different historical measurement conditions can be determined, and then can be The target scheduling path that meets different product yield and capacity requirements is obtained.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Economics (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Quality & Reliability (AREA)
  • Manufacturing & Machinery (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Theoretical Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Tourism & Hospitality (AREA)
  • Automation & Control Theory (AREA)
  • Primary Health Care (AREA)
  • General Health & Medical Sciences (AREA)
  • Health & Medical Sciences (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • General Engineering & Computer Science (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • General Factory Administration (AREA)

Abstract

一种调度路径确定、晶圆调度方法、装置、设备及存储介质，其中，调度路径确定方法包括：基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一工艺站点的第一候选机台集合(S101)；基于每一工艺站点中各机台的历史量测指标，确定每一工艺站点的第二候选机台集合(S102)；基于每一工艺站点的第一候选机台集合和第二候选机台集合，确定生产工艺的至少一条目标调度路径，每一目标调度路径中包括每一工艺站点中的一个目标机台(S103)。

Description

调度路径确定、晶圆调度方法、装置、设备及存储介质
相关申请的交叉引用
本申请基于申请号为202110812969.9、申请日为2021年7月19日、发明名称为“调度路径确定、晶圆调度方法、装置、设备及存储介质”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本申请作为参考。
技术领域
本申请实施例涉及但不限于半导体领域，尤其涉及一种调度路径确定、晶圆调度方法、装置、设备及存储介质。
背景技术
在半导体产品的生产工艺中，通常在保障产品良率的基础上，以最大产能为目标进行生产。但是，对于品质要求较高的客户，相关技术中的晶圆调度的方案，还无法满足相应的产品良率及产能需求。
发明内容
有鉴于此，本申请实施例提供一种调度路径确定、晶圆调度方法、装置、设备及存储介质。
本申请实施例的技术方案是这样实现的：
一方面，本申请实施例提供一种调度路径确定方法，所述方法包括：
基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合；
基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合；
基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径 中包括每一所述工艺站点中的一个目标机台。
另一方面，本申请实施例提供一种调度路径确定装置，所述装置包括：
第一确定模块，配置为基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合；
第二确定模块，配置为基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合；
第三确定模块，配置为基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
再一方面，本申请实施例提供一种晶圆调度方法，所述方法包括：
采用上述调度路径确定方法，确定至少一条目标调度路径；
基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径；
基于所述待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。
又一方面，本申请实施例提供一种晶圆调度装置，所述装置包括：
第六确定模块，配置为采用上述调度路径确定方法，确定至少一条目标调度路径；
第七确定模块，配置为基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径；
调度模块，配置为基于所述待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。
又一方面，本申请实施例提供一种计算机设备，包括存储器和处理器，所述存储器存储有可在处理器上运行的计算机程序，所述处理器执行所述程序时实现上述方法中的部分或全部步骤。
又一方面，本申请实施例提供一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述方法中的部分或全部步骤。
本申请实施例中，基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一工艺站点的第一候选机台集合；基于每一工艺站点中各机台的历史量测指标，确定每一工艺站点的第二候选机台集合；基于 每一工艺站点的第一候选机台集合和第二候选机台集合，确定生产工艺的至少一条目标调度路径；其中，每一目标调度路径中包括每一工艺站点中的一个目标机台。这样，可以基于工艺站点中各机台的历史良率情况以及历史量测情况，确定目标调度路径，从而可以确定具有不同历史良率情况以及不同历史量测情况的至少一条目标调度路径，进而可以得到满足不同产品良率及产能需求的目标调度路径。
附图说明
图1为本申请实施例提供的一种调度路径确定方法的实现流程示意图；
图2为本申请实施例提供的一种调度路径确定方法的实现流程示意图；
图3为本申请实施例提供的一种调度路径确定方法的实现流程示意图；
图4为本申请实施例提供的一种调度路径确定方法的实现流程示意图；
图5为本申请实施例提供的一种晶圆调度方法的实现流程示意图；
图6A为本申请实施例提供的一种工艺站点中各机台的历史良率的分布示意图；
图6B为本申请实施例提供的一种工艺站点中各机台的历史工序中对机台组件的量测指标的分布示意图；
图7为本申请实施例提供的一种调度路径确定装置的组成结构示意图；
图8为本申请实施例提供的一种晶圆调度装置的组成结构示意图；
图9为本申请实施例提供的一种计算机设备的硬件实体示意图。
具体实施方式
为了使本申请实施例的目的、技术方案和优点更加清楚，下面结合附图和实施例对本申请实施例的技术方案进一步详细阐述，所描述的实施例不应视为对本申请实施例的限制，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本申请实施例保护的范围。
在以下的描述中，涉及到“一些实施例”，其描述了所有可能实施例的子集，但是可以理解，“一些实施例”可以是所有可能实施例的相同子集或不同子集，并且可以在不冲突的情况下相互结合。
如果申请文件中出现“第一/第二”的类似描述则增加以下的说明，在 以下的描述中，所涉及的术语“第一/第二/第三”仅仅是区别类似的对象，不代表针对对象的特定排序，可以理解地，“第一/第二/第三”在允许的情况下可以互换特定的顺序或先后次序，以使这里描述的本申请实施例能够以除了在这里图示或描述的以外的顺序实施。
除非另有定义，本文所使用的所有的技术和科学术语与属于本申请实施例的技术领域的技术人员通常理解的含义相同。本文中所使用的术语只是为了描述本申请实施例的目的，不是旨在限制本申请实施例。
本申请实施例提供一种调度路径确定方法，该方法可以由计算机设备的处理器执行。其中，计算机设备指的可以是服务器、笔记本电脑、平板电脑、台式计算机、智能电视、机顶盒、移动设备(例如移动电话、便携式视频播放器、个人数字助理、专用消息设备、便携式游戏设备)等任意合适的具备数据处理能力的设备。图1为本申请实施例提供的一种调度路径确定方法的实现流程示意图，如图1所示，该方法包括如下步骤S101至步骤S103：
步骤S101，基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合。
这里，设定的生产工艺可以是根据待生产的晶圆产品的生产流程确定的，包括在晶圆产品的生产过程中对晶圆进行的至少一道工序，其中，每一道工序可以对应一个工艺站点，在该工艺站点中可以对晶圆执行该工序。在实施时，一个工艺站点中可以包括至少一个同类型的机台，在生产工艺的每一道工序中，可以从对应的工艺站点中确定一个机台，并利用该机台对晶圆执行该工序。
机台的历史良率指标可以是任意合适的可以反映机台在历史工序中所处理的晶圆的良率情况的指标，例如，历史工序中所处理的晶圆的良率的最大值、最小值、平均值、众数或中位数等中的一种或多种。在实施时，针可以在机台的工序完成后，对机台处理后的晶圆进行测试，得到处理后晶圆的良率数据，并对该良率数据进行记录。通过查询历史记录的良率数据，可以得到各机台的历史良率指标。在一些实施例中，可以对设定的历史时间范围内机台在所处理的晶圆的良率数据进行统计，得到机台的历史良率指标。
对于每一工艺站点，可以基于该工艺站点中各机台的历史良率指标，确定该工艺站点的第一候选机台集合。工艺站点的第一候选机台集合中可以包括该工艺站点中的至少一个机台。在实施时，可以根据实际情况采用任意合适的方式基于工艺站点中各机台的历史良率指标，确定该工艺站点的第一候选机台集合，这里并不限定。例如，可以将工艺站点中各机台的历史良率指标满足设定的良率条件的机台加入该工艺站点的第一候选机台集合，也可以将工艺站点中各机台的历史良率指标不满足设定的良率条件的机台加入该工艺站点的第一候选机台集合，还可以将工艺站点中各机台中历史良率指标最高的特定数量的机台加入该工艺站点的第一候选机台集合。
步骤S102，基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合。
这里，机台的历史量测指标可以是在机台的历史工序中通过量测得到的任意合适的指标。在一些实施例中，所述历史量测指标可以包括以下至少之一：历史工序中对机台组件的量测指标、历史工序中对晶圆产品的量测指标。其中，历史工序中对机台组件的量测指标指的是在历史工序中对机台中各组件的状态进行量测得到的指标，包括但不限于机台中各组件的温度指标、组件内部或外部的气体流量指标等中的一种或多种；历史工序中对晶圆产品的量测指标指的是在历史工序中对机台所处理的晶圆产品的状态进行量测得到的指标，包括但不限于晶圆产品的温度指标、关键尺寸等中的一种或多种。
在实施时，可以根据实际待量测的指标采用合适的量测传感器、量测设备等在机台执行工序的过程中对机台中各组件或晶圆产品等进行量测，得到量测指标，并对该得到的量测指标进行记录。通过查询历史记录的量测指标，可以得到各机台的历史量测指标。在一些实施例中，可以对设定的历史时间范围内机台在的量测指标进行查询，得到机台的历史量测指标。
对于每一机台，可以在该机台每一次执行工序的过程中均进行量测，得到该机台全量的历史量测指标，也可以基于设定的量测策略，在机台执行的部分工序中进行量测，得到该机台部分的历史量测指标，这里并不限定。
对于每一工艺站点，可以基于该工艺站点中各机台的历史量测指标，确定该工艺站点的第二候选机台集合。工艺站点的第二候选机台集合中可以包括该工艺站点中的至少一个机台。在实施时，可以根据实际情况采用任意合适的方式基于工艺站点中各机台的历史量测指标，确定该工艺站点的第二候选机台集合，这里并不限定。例如，可以将工艺站点中各机台的历史量测指标满足设定的指标条件的机台加入该工艺站点的第二候选机台集合，也可以将工艺站点中各机台的历史量测指标不满足设定的指标条件的机台加入该工艺站点的第二候选机台集合，还可以将工艺站点中各机台中历史量测指标最高的特定数量的机台加入该工艺站点的第二候选机台集合。
步骤S103，基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
这里，对于每一工艺站点，可以基于该工艺站点的第一候选机台集合和第二候选机台集合确定该工艺站点的至少一个目标机台。在实施时，可以根据实际情况采用合适的方式基于工艺站点的第一候选机台集合和第二候选机台集合确定该工艺站点的至少一个目标机台，这里并不限定。例如，可以对工艺站点的第一候选机台集合和第二候选机台集合取交集，从得到的交集中确定至少一个目标机台；也可以对工艺站点的第一候选机台集合和第二候选机台集合取并集，从得到的并集中确定至少一个目标机台。
根据各工艺站点中对晶圆进行的工序在晶圆产品的生产工艺中的执行顺序，可以确定晶圆在各工艺站点之间的调度顺序。按照该调度顺序，从每一工艺站点中各选择一个目标机台，可以得到生产工艺的一条目标调度路径。
在一些实施例中，上述步骤S103可以包括如下步骤S111至步骤S112：
步骤S111，对每一所述工艺站点的第一候选机台集合和第二候选机台集合取交集，得到每一所述工艺站点的至少一个目标机台；
步骤S112，基于每一所述工艺站点的至少一个目标机台，确定所述生产工艺中的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点的一个目标机台。
在一些实施例中，每一所述目标机台包含至少一个工艺腔室，上述步骤S103可以包括如下步骤S121至步骤S122：
步骤S131，针对每一所述工艺站点的第一候选机台集合以及第二候选机台集合中的每一机台，确定所述机台的至少一个候选工艺腔室。
这里，在生产工艺的每一道工序中，对晶圆的处理可以在机台的工艺腔室中完成。每一机台可以包含至少一个工艺腔室。在实施时，可以根据实际情况采用任意合适的方式从机台的至少一个工艺腔室中确定该机台的至少一个候选工艺腔室，这里并不限定。例如，可以从机台的至少一个工艺腔室中随机确定至少一个候选工艺腔室，也可以基于机台中各工艺腔室的历史良率指标和/或历史量测指标等，从机台的至少一个工艺腔室中确定至少一个候选工艺腔室。
步骤S132，基于每一所述工艺站点的第一候选机台集合中每一机台的至少一个候选工艺腔室和第二候选机台集合中每一机台的至少一个候选工艺腔室，确定所述生产工艺中的至少一条目标调度路径；其中，每一条所述目标调度路径中包括每一所述工艺站点中的一个目标工艺腔室。
这里，可以根据晶圆在各工艺站点之间的调度顺序，从每一工艺站点中各选择一个目标机台，并从该目标机台的至少一个候选工艺腔室中确定一个目标工艺腔室，可以得到一条包括每一工艺站点中的一个目标工艺腔室的目标调度路径。
本申请实施例中，基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一工艺站点的第一候选机台集合；基于每一工艺站点中各机台的历史量测指标，确定每一工艺站点的第二候选机台集合；基于每一工艺站点的第一候选机台集合和第二候选机台集合，确定生产工艺的至少一条目标调度路径；其中，每一目标调度路径中包括每一工艺站点中的一个目标机台。这样，可以基于工艺站点中各机台的历史良率情况以及历史量测情况，确定目标调度路径，从而可以确定具有不同历史良率情况以及不同历史量测情况的至少一条目标调度路径，进而可以得到满足不同产品良率及产能需求的目标调度路径。
本申请实施例提供一种调度路径确定方法，该方法可以由计算机设备的处理器执行。如图2所示，该方法包括如下步骤S201至步骤S206：
步骤S201，基于设定的良率统计条件，确定设定的生产工艺中每一工艺站点中各机台的至少一个历史良率。
这里，机台的历史良率为机台在历史工序中所处理的晶圆的良率，晶圆的良率可以表征晶圆上芯片的合格率。例如，如一片晶圆可以切出1000片的芯片，针对每个芯片做0/1的测试，可以得到该晶圆的良率为：测为1的芯片数量与芯片总数1000的比值。
良率统计条件可以是预先设定的用于对机台的历史良率进行统计的统计条件，可以包括但不限于统计时间范围、待统计工艺腔室等中的一种或多种。每一工艺站点中各机台的至少一个历史良率可以是基于该良率统计条件统计得到的。例如，良率统计条件可以包括设定的统计时间范围，则可以对该统计时间范围内经过每一机台处理后的晶圆的良率进行统计，得到每一机台的至少一个历史良率。又如，良率统计条件可以包括设定的待统计工艺腔室，则可以对每一机台中设定的待统计工艺腔室所处理的晶圆的良率进行统计，得到每一机台的至少一个历史良率。
步骤S202，基于每一所述工艺站点中各机台的至少一个历史良率，确定每一所述工艺站点中各机台的历史良率分布信息。
这里，可以对每一工艺站点中各机台的至少一个历史良率的分布情况进行分析，得到每一工艺站点中各机台的历史良率分布信息。机台的历史良率分布信息可以包括但不限于该机台的历史良率的平均值、最大值、最小值、众数、特定的分位数等中的一种或多种，还可以包括该机台的历史良率的分布特征，这里并不限定。
在实施时，可以根据历史良率分布信息实际包含的信息，采用合适的方式确定每一工艺站点中各机台的历史良率分布信息，这里并不限定。例如，对于机台的历史良率的平均值、最大值、最小值、众数、特定的分位数等统计值，可以通过对机台的至少一个历史良率进行直接统计得到；对于机台的历史良率的分布特征，可以采用任意合适的特征提取算法，从机台的至少一个历史良率中提取得到。
步骤S203，针对每一所述工艺站点，确定所述工艺站点中历史良率分布信息满足预设良率分布条件的第一候选机台。
这里，预设良率分布条件可以是预先根据实际情况设定的第一候选机 台的历史良率分布信息需要满足的条件，可以包括但不限于对机台的历史良率的统计值的限定条件、对机台的历史良率的分布特征的限定条件等中的一种或多种。
例如，机台的历史良率分布信息为机台的历史良率的平均值、最大值、最小值、众数、特定的分位数等统计值，预设良率分布条件可以是预设的统计值的取值范围，可以将工艺站点中历史良率的平均值、最大值、最小值、众数、特定的分位数等统计值在预设的统计值的取值范围内的至少一个机台确定为第一候选机台。
又如，机台的历史良率分布信息为机台的历史良率的分布特征，预设良率分布条件可以是预设分布特征，可以将工艺站点中历史良率的分布特征与该预设分布特征匹配的至少一个机台确定为第一候选机台。
步骤S204，将每一所述工艺站点的第一候选机台加入所述工艺站点的第一候选机台集合。
步骤S205，基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合。
步骤S206，基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
这里，步骤S205至步骤S206对应于前述步骤S102至步骤S103，在实施时可以参照前述步骤S102至步骤S103的具体实施方式。
在一些实施例中，所述历史良率分布信息包括历史良率的平均值，上述步骤S203中所述的确定所述工艺站点中历史良率分布信息满足预设良率分布条件的第一候选机台，可以包括：
步骤S211，将所述工艺站点中历史良率的平均值最高的第一数量的机台确定为第一候选机台。
这里，第一数量可以是根据实际情况确定的数值，如1、2、3、5等，这里并不限定。在实施时，第一数量可以是用户设定的，也可以是系统默认的。
本申请实施例中，基于设定的良率统计条件，确定设定的生产工艺中每一工艺站点中各机台的至少一个历史良率；基于每一工艺站点中各机台 的至少一个历史良率，确定每一工艺站点中各机台的历史良率分布信息；针对每一工艺站点，确定工艺站点中历史良率分布信息满足预设良率分布条件的第一候选机台；将每一工艺站点的第一候选机台加入该工艺站点的第一候选机台集合。这样，可以使得工艺站点的第一候选机台集合中的每一机台的历史良率分布信息能够满足预设良率分布条件，从而可以提高目标调度路径中每一工艺站点的目标机台的良率，进而可以提高生产工艺的良率及产能。
本申请实施例提供一种调度路径确定方法，该方法可以由计算机设备的处理器执行。如图3所示，该方法包括如下步骤S301至步骤S304：
步骤S301，基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合。
这里，步骤S301对应于前述步骤S101，在实施时可以参照前述步骤S101的具体实施方式。
步骤S302，针对每一所述工艺站点，基于设定的量测指标统计条件，确定所述工艺站点中各机台的历史量测指标。
这里，量测指标统计条件可以是预先设定的用于对机台的历史量测指标进行筛选、统计的条件，可以包括但不限于设定的晶圆产品、工序、工艺腔室、传感器、工序步骤、关键尺寸等参数中的一种或多种。每一工艺站点中各机台的至少一个历史量测指标可以是基于该量测指标统计条件进行筛选及统计得到的。
在实施时，可以在各机台执行工序的过程中对机台中各组件或晶圆产品等进行量测，得到大量的量测指标，并对该得到的量测指标进行记录。在确定工艺站点中各机台的历史量测指标的过程中，可以基于量测指标统计条件，从记录的大量历史量测指标中，获取满足该量测指标统计条件的历史量测指标，从而得到工艺站点中各机台的历史量测指标。
步骤S303，基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合。
步骤S304，基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
这里，步骤S303至步骤S304对应于前述步骤S102至步骤S103，在实施时可以参照前述步骤S102至步骤S103的具体实施方式。
在一些实施例中，上述步骤S303可以包括如下步骤S311至步骤S313：
步骤S311，确定每一所述工艺站点的量测指标的目标取值范围。
这里，每一工艺站点的量测指标的目标取值范围可以是预先设定的，也可以是基于工艺站点的历史量测指标确定的，这里并不限定。
在一些实施例中，每一工艺站点可以对应多个量测指标，目标取值范围中可以包括每一量测指标的目标取值范围。不同工艺站点中同一量测指标的目标取值范围可以是相同的，也可以是不同的。
步骤S312，针对每一所述工艺站点，确定所述工艺站点中历史量测指标在所述工艺站点的量测指标的目标取值范围内的第二候选机台。
这里，可以将每一工艺站点中历史量测指标在该工艺站点的量测指标的目标取值范围内的至少一个机台确定为该工艺站点的第二候选机台。
步骤S313，将每一所述工艺站点的第二候选机台加入所述工艺站点的第二候选机台集合。
在一些实施例中，上述步骤S311可以包括如下步骤S321至步骤S323：
步骤S321，针对每一所述工艺站点，确定所述工艺站点中历史良率的平均值最高的第二数量的第三候选机台。
这里，第二数量可以是根据实际情况确定的数值，如1、2、3、5等，这里并不限定。在实施时，第二数量可以是用户设定的，也可以是系统默认的。
在实施时，可以将每一工艺站点中历史良率的平均值最高的第二数量的机台确定为该工艺站点的第三候选机台。
步骤S322，将每一所述工艺站点的每一第三候选机台加入所述工艺站点的第三候选机台集合。
步骤S323，基于每一所述工艺站点的第三候选机台集合中各机台的历史量测指标中的最大值和最小值，确定每一所述工艺站点的量测指标的目标取值范围。
这里，可以将工艺站点中第三候选机台集合中各机台的历史量测指标中的最小值作为目标取值范围的下边界、最大值作为目标取值范围的上边 界，从而确定该工艺站点的量测指标的目标取值范围，也即该大于或等于该最小值且小于或等于该最大值。这样，可以将每一工艺站点中历史良率的平均值最高的第二数量的机台中历史量测指标的取值范围确定为每一工艺站点的目标取值范围，从而基于该目标取值范围确定的第二候选机台可以具有较高的良率，进而可以进一步提高目标调度路径中每一工艺站点的目标机台的良率，进而可以进一步提高生产工艺的良率及产能。
本申请实施例中，针对每一所述工艺站点，基于设定的量测指标统计条件，确定工艺站点中各机台的历史量测指标。这样，可以简单快速地确定每一工艺站点中各机台的历史量测指标。
本申请实施例提供一种调度路径确定方法，该方法可以由计算机设备的处理器执行。如图4所示，该方法包括如下步骤S401至步骤S406：
步骤S401，基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合。
步骤S402，基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合。
步骤S403，基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
这里，步骤S401至步骤S403对应于前述步骤S101至步骤S103，在实施时可以参照前述步骤S101至步骤S103的具体实施方式。
步骤S404，确定每一所述工艺站点中表征各机台的良率偏差情况的偏差指标。
这里，工艺站点的偏差指标可以是任意合适的能够表征工艺站点中各机台的良率偏差情况的指标，包括但不限于工艺站点中各机台的历史良率的标准偏差、平均偏差、相对平均偏差、方差、标准差等中的一种或多种。在实施时，工艺站点的偏差指标可以包括该工艺站点中至少一个机台的偏差指标。通过对工艺站点中每一机台的历史良率进行统计分析，可以确定至少一个机台的偏差指标，也即工艺站点的偏差指标。
步骤S405，将每一所述工艺站点中偏差指标大于偏差阈值的工艺站点加入异常工艺站点集合。
这里，偏差阈值可以是根据实际情况确定的用于判断机台的良率偏差指标是否异常的合适的值。在实施时，偏差阈值可以是用户设定的，也可以是系统默认的，这里并不限定。
每一工艺站点的偏差指标中可以包括该该工艺站点中至少一个机台的偏差指标，在至少一个机台的偏差指标大于偏差阈值的情况下，可以确定该工艺站点为异常工艺站点，从而可以将该工艺站点加入异常工艺站点集合。
在一些实施例中，可以在工艺站点中偏差指标大于偏差阈值的机台的数量大于设定的机台数量阈值的情况下，确定该工艺站点为异常工艺站点，并将该工艺站点加入异常工艺站点集合。
步骤S406，对所述异常工艺站点集合中偏差指标最大的第三数量的工艺站点进行预警。
这里，第三数量可以是根据实际情况确定的数值，如1、2、3、5等，这里并不限定。在实施时，第三数量可以是用户设定的，也可以是系统默认的。
可以通过对异常工艺站点集合中每一工艺站点中至少一个机台的偏差指标进行比较，确定异常工艺站点集合中偏差指标最大的第三数量的工艺站点。对于两个待比较的工艺站点，可以通过比较这两个工艺站点中各机台的偏差指标的最大值来确定这两个工艺站点中偏差指标的大小，也可以通过比较这两个工艺站点中各机台的偏差指标的平均值来确定这两个工艺站点中偏差指标的大小，这里并不限定。在实施时。本领域技术人员可以根据实际情况采用任意合适的方式比较不同工艺站点中偏差指标的大小。
对工艺站点的预警可以包括但不限于语音预警、指示灯预警、电话预警、邮件预警、即时通讯软件信息预警等中的一种或多种，在实施时，本领域技术人员可以根据实际情况采用合适的方式对异常工艺站点集合中偏差指标最大的第三数量的工艺站点进行预警，这里并不限定。
在一些实施例中，对于异常工艺站点集合中偏差指标最大的第三数量的工艺站点中的每一工艺站点，可以基于该工艺站点中各机台的偏差指标，确定该工艺站点中偏差指标大于偏差阈值的异常机台，并对每一异常机台进行预警。
在一些实施例中，上述步骤S404可以包括如下步骤S411至步骤S412：
步骤S411，确定每一所述工艺站点中各机台的历史良率的平均值和平均偏差。
步骤S412，针对每一所述工艺站点，将所述工艺站点中各机台的历史良率的平均值与平均偏差的比值确定为所述工艺站点的偏差指标。
这里，对于每一个工艺站点，可以将该工艺站点中每一机台的历史良率的平均值与平均偏差的比值确定为每一机台的偏差指标，从而得到该工艺站点的偏差指标。在一些实施例中，针对每一机台，可以将该机台的历史良率的平均值与平均偏差的比值的绝对值确定为该机台的偏差指标。
本申请实施例中，确定每一工艺站点中表征各机台的良率偏差情况的偏差指标；将每一工艺站点中偏差指标大于偏差阈值的工艺站点加入异常工艺站点集合；对异常工艺站点集合中偏差指标最大的第三数量的工艺站点进行预警。这样，可以及时发现生产工艺中的异常工艺站点，并能及时发现异常工艺站点中的异常机台，以便用户对异常工艺站点以及异常机台进行及时地维护，从而可以提高生产工艺的稳定性。此外，还能基于发现的异常工艺站点以及异常机台，对生产工艺中的调度路径的确定进行进一步优化，从而进一步提高晶圆产品的良率以及产能。
本申请实施例提供一种晶圆调度方法，该方法可以由计算机设备的处理器执行。如图5所示，该方法包括如下步骤S501至步骤S503：
步骤S501，采用上述任一实施例中所述的调度路径确定方法，确定至少一条目标调度路径。
步骤S502，基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径。
这里，工艺参数条件可以包括任意合适的对生产工艺中的参数进行控制的参数条件，例如，对晶圆的良率进行控制的良率条件，对产品生产时长进行控制的时长条件等。在实施时，本领域技术人员可以根据实际情况确定合适的工艺参数条件，这里并不限定。
通过对至少一条目标调度路径进行分析，可以将至少一条目标调度路径中满足该工艺参数条件的目标调度路径确定为待调度的调度路径。例如，可以将晶圆的良率达到设定的良率阈值的目标调度路径确定为待调度的调 度路径；也可以将产品生产时长不超过设定的时长阈值的目标调度路径确定为待调度的调度路径。
在一些实施例中，所述工艺参数条件包括以下至少之一：良率条件、时长条件。
步骤S503，基于所述待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。
这里，待调度的调度路径中可以包括各工艺站点中的一个目标机台。可以根据各工艺站点的调度顺序，将晶圆产品依次调度至待调度的调度路径中各工艺站点的目标机台中进行工序处理，得到晶圆产品。
在一些实施例中，上述步骤S502可以包括如下步骤S511至步骤S512：
步骤S511，针对每一所述目标调度路径，基于所述目标调度路径中每一工艺站点中目标机台的历史工艺参数，确定所述目标调度路径的工艺参数。
这里，机台的历史工艺参数可以是机台在历史的工序处理过程中达到的工艺参数，可以包括但不限于历史晶圆良率、历史产品生产时长等中的一种或多种。目标调度路径的工艺参数指的是基于目标调度路径，对晶圆进行生产调度，得到晶圆产品的过程中能够达到的工艺参数，可以包括但不限于晶圆良率、产品生产时长等中的一种或多种。
基于目标调度路径中每一工艺站点中目标机台的历史工艺参数，可以对目标调度路径的工艺参数进行预估。例如，对于工艺参数为晶圆良率的情况，可以将目标调度路径中每一工艺站点中目标机台的历史晶圆良率的平均值确定为目标调度路径的晶圆良率，还可以将目标调度路径中每一工艺站点中目标机台的历史晶圆良率的最小值确定为目标调度路径的晶圆良率，这里并不限定。
又如，对于工艺参数为产品生产时长的情况，可以将目标调度路径中每一工艺站点中目标机台的历史产品生产时长的平均值确定为目标调度路径的产品生产时长，还可以将目标调度路径中每一工艺站点中目标机台的历史产品生产时长的最大值确定为目标调度路径的产品生产时长。
步骤S512，将所述至少一条目标调度路径中工艺参数满足所述工艺参数条件的目标调度路径确定为所述待调度的调度路径。
本申请实施例中，采用上述任一实施例中所述的调度路径确定方法，确定至少一条目标调度路径；基于设定的工艺参数条件，从至少一条目标调度路径中确定待调度的调度路径；基于待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。这样，可以从确定的满足不同产品良率及产能需求的至少一条目标调度路径中确定满足设定的工艺参数条件的待调度的调度路径，从而可以使得晶圆产品的生产工艺满足设定的工艺参数条件。
本申请实施例提供一种调度路径确定方法，该方法可以收集生产工艺过程中的量测结果、机台的传感器采集的环境量测值以及对芯片进行良率测试的结果等，自动化生成晶圆的最优化调度路径，以确保生产品质最优产品的概率最高，从而可以实现最大产能。
相关技术中，由于生产工艺中的每一工艺站点中同类型的不同工作机台以及同一工作机台的不同工艺腔室之间存在差异，导致不同调度路径的产品良率不同。
本申请实施例提供的调度路径确定方法包括如下步骤S601至步骤S604：
步骤S601，针对设定的生产工艺中的每一工艺站点，获取该工艺站点的第一候选机台集合Set{Z}。
这里，每一工艺站点的第一候选机台集合Se{Z}中包括该工艺站点中历史良率的平均值最大的N个机台，其中N为设定的正整数。
图6A为本申请实施例提供的一种工艺站点中各机台的历史良率的分布示意图。如图6A所示，横轴上包括工艺站点中的机台A至E，纵轴为机台的历史良率的平均值，其中，各机台按照历史良率的平均值由大到小排序分别为机台D、B、E、A、C，若工艺站点的第一候选机台集合Set{Z}中包括该工艺站点中历史良率的平均值最大的3个机台，则该工艺站点的第一候选机台集合Set{Z}为{机台D，机台B，机台E}。
步骤S602，基于每一工艺站点中各机台的历史工序中对机台组件的量测指标和历史工序中对晶圆产品的量测指标，分别确定每一工艺站点的第四候选机台集合Set{A}和第五候选机台集合Set{B}。
这里，基于每一工艺站点中各机台的历史工序中对机台组件的量测指标可以确定每一工艺站点的第四候选机台集合Set{A}。在实施时，可以通 过如下步骤S611至步骤S613确定每一工艺站点的第四候选机台集合Set{A}：
步骤S611，针对每一工艺站点中的每一机台，根据设定的晶圆产品、工序、工艺腔室、传感器、工序步骤等参数中的一种或多种，从大量的历史工序中对机台组件的量测数据中得到该机台的历史工序中对机台组件的量测指标；
步骤S612，针对每一工艺站点，对该工艺站点中历史良率的平均值最大的M个机台的历史工序中对机台组件的量测指标进行分析，得到该M个机台的历史工序中对机台组件的量测指标中的最大值USL w和最小值LSL w，其中M为设定的正整数；
步骤S613，针对每一工艺站点，将该工艺站点中历史工序中对机台组件的量测指标在最大值USL w和最小值LSL w之间的机台加入该工艺站点的第四候选机台集合Set{A}。
例如，工艺站点历史良率的平均值最大的3个机台为{机台D，机台B，机台E}，可以分别对机台D、B、E的历史工序中对机台组件的量测指标进行分析，得到机台D、B、E的历史工序中对机台组件的量测指标中的最大值USL w和最小值LSL w。图6B为本申请实施例提供的一种工艺站点中各机台的历史工序中对机台组件的量测指标的分布示意图。如图6B所示，横轴上包括工艺站点中的机台A至E，纵轴为机台的历史工序中对机台组件的量测指标，其中，历史工序中对机台组件的量测指标在最大值USL w和最小值LSL w之间的机台包括机台B、D、E，则该工艺站点的第四候选机台集合Set{A}为{机台B，机台D，机台E}。
基于每一工艺站点中各机台的历史工序中对晶圆产品的量测指标可以确定每一工艺站点的第五候选机台集合Set{B}。在实施时，可以通过如下步骤S621至步骤S623确定每一工艺站点的第五候选机台集合Set{B}：
步骤S621，针对每一工艺站点中的每一机台，根据设定的晶圆产品、工序、工艺腔室、关键尺寸等参数中的一种或多种，从大量的历史工序中对晶圆产品的量测数据中得到该机台的历史工序中对晶圆产品的量测指标；
步骤S622，针对每一工艺站点，对该工艺站点中历史良率的平均值最 大的L个机台的历史工序中对晶圆产品的量测指标进行分析，得到该L个机台的历史工序中对晶圆产品的量测指标中的最大值USL s和最小值USL s，其中L为设定的正整数；
步骤S623，针对每一工艺站点，将该工艺站点中历史工序中对晶圆产品的量测指标在最大值USL s和最小值LSL s之间的机台加入该工艺站点的第五候选机台集合Set{B}。
需要说明的是，第四候选机台集合和第五候选机台集合均可以作为前述实施例中的第二候选机台集合进行实施。
步骤S603，基于每一工艺站点的第一候选机台集合Set{Z}、第四候选机台集合Set{A}和第五候选机台集合Set{B}，确定生产工艺的至少一条目标调度路径；其中，每一目标调度路径中包括每一所述工艺站点中的一个目标机台。
这里，可以对每一工艺站点的第一候选机台集合Set{Z}、第四候选机台集合Set{A}和第五候选机台集合Set{B}取交集，从得到的交集中确定每一工艺站点的至少一个目标机台。根据各工艺站点中对晶圆进行的工序在晶圆产品的生产工艺中的执行顺序，可以确定晶圆在各工艺站点之间的调度顺序。按照该调度顺序，从每一工艺站点中各选择一个目标机台，可以得到生产工艺的一条目标调度路径。
在一些实施例中，可以通过终端设备上的调度路径查询界面显示自动生成的目标调度路径，用户可以在该调度路径查询界面输入统计时间、工艺腔室等良率统计条件，以及晶圆产品、测试ID、参数、排序的统计指标等量测指标统计条件，并点击调度路径查询界面上的查询按钮，即可基于输入的良率统计条件和量测指标统计条件，自动生成至少一条目标调度路径，并在调度路径查询界面显示自动生成的目标调度路径。对于目标调度路径中的每一目标机台，可以根据目标机台的良率的不同采用不同的颜色进行显示。例如，可以采用红色显示良率小于25％的目标机台，采用黄色显示良率大于或等于25％且小于75％的目标机台，采用绿色显示良率大于或等于75％的目标机台。在鼠标点击或悬浮在调度路径查询界面的工艺站点或目标机台上的情况下，可以显示对应的工艺站点或目标机台的详细信息。
步骤S604，基于每一工艺站点中各机台的良率偏差指标，确定异常工艺站点以及异常工艺站点中的异常机台，并对异常工艺站点以及异常工艺站点中的异常机台进行预警。
这里，机台的良率偏差指标可以是机台的历史良率的平均值与历史良率的偏差之间的比值的绝对值。在晶圆产品的生产工艺中，虽然有的机台历史良率的平均值很高，但是良率偏差指标很大，在这种情况下，该机台最终产品的良率仍可能不高，因此可以将良率偏差指标大的机台认为是异常机台，异常机台所属的工艺站点即为异常工艺站点，需要将异常机台以及相应的异常工艺站点筛选出来进行预警，以协助进一步优化策略目标调度路径。
图7为本申请实施例提供的一种调度路径确定装置的组成结构示意图，如图7所示，调度路径确定装置700包括：第一确定模块710、第二确定模块720、和第三确定模块730，其中：
第一确定模块710，配置为基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合；
第二确定模块720，配置为基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合；
第三确定模块730，配置为基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机。
在一些实施例中，所述历史良率指标包括至少一个历史良率，所述第一确定模块还配置为：基于设定的良率统计条件，确定设定的生产工艺中每一工艺站点中各机台的至少一个历史良率；基于每一所述工艺站点中各机台的至少一个历史良率，确定每一所述工艺站点中各机台的历史良率分布信息；针对每一所述工艺站点，确定所述工艺站点中历史良率分布信息满足预设良率分布条件的第一候选机台；将每一所述工艺站点的第一候选机台加入所述工艺站点的第一候选机台集合。
在一些实施例中，所述历史良率分布信息包括历史良率的平均值，所述第一确定模块还配置为：将所述工艺站点中历史良率的平均值最高的第一数量的机台确定为第一候选机台。
在一些实施例中，所述装置还包括：第四确定模块，配置为针对每一所述工艺站点，基于设定的量测指标统计条件，确定所述工艺站点中各机台的历史量测指标。
在一些实施例中，所述第四确定模块还配置为：确定每一所述工艺站点的量测指标的目标取值范围；针对每一所述工艺站点，确定所述工艺站点中历史量测指标在所述工艺站点的量测指标的目标取值范围内的第二候选机台；将每一所述工艺站点的第二候选机台加入所述工艺站点的第二候选机台集合。
在一些实施例中，所述第四确定模块还配置为：针对每一所述工艺站点，确定所述工艺站点中历史良率的平均值最高的第二数量的第三候选机台；将每一所述工艺站点的每一第三候选机台加入所述工艺站点的第三候选机台集合；基于每一所述工艺站点的第三候选机台集合中各机台的历史量测指标中的最大值和最小值，确定每一所述工艺站点的量测指标的目标取值范围。
在一些实施例中，所述历史量测指标包括以下至少之一：历史工序中对机台组件的量测指标、历史工序中对晶圆产品的量测指标。
在一些实施例中，所述第三确定模块还配置为：对每一所述工艺站点的第一候选机台集合和第二候选机台集合取交集，得到每一所述工艺站点的至少一个目标机台；基于每一所述工艺站点的至少一个目标机台，确定所述生产工艺中的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点的一个目标机台。
在一些实施例中，每一所述目标机台包含至少一个工艺腔室，所述第三确定模块还配置为：针对每一所述工艺站点的第一候选机台集合以及第二候选机台集合中的每一机台，确定所述机台的至少一个候选工艺腔室；基于每一所述工艺站点的第一候选机台集合中每一机台的至少一个候选工艺腔室和第二候选机台集合中每一机台的至少一个候选工艺腔室，确定所述生产工艺中的至少一条目标调度路径；其中，每一条所述目标调度路径中包括每一所述工艺站点中的一个目标工艺腔室。
在一些实施例中，所述装置还包括：第五确定模块，配置为确定每一所述工艺站点中表征各机台的良率偏差情况的偏差指标；添加模块，配置 为将每一所述工艺站点中偏差指标大于偏差阈值的工艺站点加入异常工艺站点集合；预警模块，配置为对所述异常工艺站点集合中偏差指标最大的第三数量的工艺站点进行预警。
在一些实施例中，所述第五确定模块还配置为：确定每一所述工艺站点中各机台的历史良率的平均值和平均偏差；针对每一所述工艺站点，将所述工艺站点中各机台的历史良率的平均值与平均偏差的比值确定为所述工艺站点的偏差指标。
图8为本申请实施例提供的一种晶圆调度装置的组成结构示意图，如图8所示，晶圆调度装置800包括：第六确定模块810、第七确定模块820和调度模块830，其中：
第六确定模块810，配置为采用上述调度路径确定方法，确定至少一条目标调度路径；
第七确定模块820，配置为基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径；
调度模块830，配置为基于所述待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。
在一些实施例中，所述第七确定模块还配置为：针对每一所述目标调度路径，基于所述目标调度路径中每一工艺站点中目标机台的历史工艺参数，确定所述目标调度路径的工艺参数；将所述至少一条目标调度路径中工艺参数满足所述工艺参数条件的目标调度路径确定为所述待调度的调度路径。
在一些实施例中，所述工艺参数条件包括以下至少之一：良率条件、时长条件。
以上装置实施例的描述，与上述方法实施例的描述是类似的，具有同方法实施例相似的有益效果。对于本申请装置实施例中未披露的技术细节，请参照本申请方法实施例的描述而理解。
需要说明的是，本申请实施例中，如果以软件功能模块的形式实现上述的调度路径确定方法，并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出 来，该软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括：U盘、移动硬盘、只读存储器(Read Only Memory，ROM)、磁碟或者光盘等各种可以存储程序代码的介质。这样，本申请实施例不限制于任何特定的硬件和软件结合。
对应地，本申请实施例提供一种计算机设备，包括存储器和处理器，所述存储器存储有可在处理器上运行的计算机程序，所述处理器执行所述程序时实现上述方法中的步骤。
对应地，本申请实施例提供一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现上述方法中的步骤。
对应地，本申请实施例提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序被计算机读取并执行时，实现上述方法中的部分或全部步骤。该计算机程序产品可以具体通过硬件、软件或其结合的方式实现。在一个可选实施例中，所述计算机程序产品具体体现为计算机存储介质，在另一个可选实施例中，计算机程序产品具体体现为软件产品，例如软件开发包(Software Development Kit，SDK)等等。
这里需要指出的是：以上存储介质、计算机程序产品和设备实施例的描述，与上述方法实施例的描述是类似的，具有同方法实施例相似的有益效果。对于本申请存储介质、计算机程序产品和设备实施例中未披露的技术细节，请参照本申请方法实施例的描述而理解。
需要说明的是，图9为本申请实施例中计算机设备的一种硬件实体示意图，如图9所示，该计算机设备900的硬件实体包括：处理器901、通信接口902和存储器903，其中：
处理器901通常控制计算机设备900的总体操作。
通信接口902可以使计算机设备通过网络与其他终端或服务器通信。
存储器903配置为存储由处理器901可执行的指令和应用，还可以缓存待处理器901以及计算机设备900中各模块待处理或已经处理的数据(例如，图像数据、音频数据、语音通信数据和视频通信数据)，可以通过闪存(FLASH)或随机访问存储器(Random Access Memory，RAM)实现。
应理解，说明书通篇中提到的“一个实施例”或“一实施例”意味着与实施例有关的特定特征、结构或特性包括在本申请的至少一个实施例中。因此，在整个说明书各处出现的“在一个实施例中”或“在一实施例中”未必一定指相同的实施例。此外，这些特定的特征、结构或特性可以任意适合的方式结合在一个或多个实施例中。应理解，在本申请的各种实施例中，上述各过程的序号的大小并不意味着执行顺序的先后，各过程的执行顺序应以其功能和内在逻辑确定，而不应对本申请实施例的实施过程构成任何限定。上述本申请实施例序号仅仅为了描述，不代表实施例的优劣。
需要说明的是，在本文中，术语“包括”、“包含”或者其任何其他变体意在涵盖非排他性的包含，从而使得包括一系列要素的过程、方法、物品或者装置不仅包括那些要素，而且还包括没有明确列出的其他要素，或者是还包括为这种过程、方法、物品或者装置所固有的要素。在没有更多限制的情况下，由语句“包括一个……”限定的要素，并不排除在包括该要素的过程、方法、物品或者装置中还存在另外的相同要素。
在本申请所提供的几个实施例中，应该理解到，所揭露的设备和方法，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元；既可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。
另外，在本申请各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加软件功能单元的形式实现。
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步 骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(Read Only Memory，ROM)、磁碟或者光盘等各种可以存储程序代码的介质。
或者，本申请实施例上述集成的单元如果以软件功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请实施例的技术方案本质上或者说对相关技术做出贡献的部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本申请各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、ROM、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，仅为本申请的实施方式，但本申请实施例的保护范围并不局限于此，任何熟悉本技术领域的技术人员在本申请实施例揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本申请实施例的保护范围之内。因此，本申请实施例的保护范围应以所述权利要求的保护范围为准。
工业实用性
本申请实施例中，基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一工艺站点的第一候选机台集合；基于每一工艺站点中各机台的历史量测指标，确定每一工艺站点的第二候选机台集合；基于每一工艺站点的第一候选机台集合和第二候选机台集合，确定生产工艺的至少一条目标调度路径；其中，每一目标调度路径中包括每一工艺站点中的一个目标机台。这样，可以基于工艺站点中各机台的历史良率情况以及历史量测情况，确定目标调度路径，从而可以确定具有不同历史良率情况以及不同历史量测情况的至少一条目标调度路径，进而可以得到满足不同产品良率及产能需求的目标调度路径。

Claims (18)

  1. 一种调度路径确定方法，所述方法包括：
    基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合；
    基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合；
    基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
  2. 根据权利要求1所述的方法，其中，所述历史良率指标包括至少一个历史良率，所述基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合，包括：
    基于设定的良率统计条件，确定设定的生产工艺中每一工艺站点中各机台的至少一个历史良率；
    基于每一所述工艺站点中各机台的至少一个历史良率，确定每一所述工艺站点中各机台的历史良率分布信息；
    针对每一所述工艺站点，确定所述工艺站点中历史良率分布信息满足预设良率分布条件的第一候选机台；
    将每一所述工艺站点的第一候选机台加入所述工艺站点的第一候选机台集合。
  3. 根据权利要求2所述的方法，其中，所述历史良率分布信息包括历史良率的平均值，所述确定所述工艺站点中历史良率分布信息满足预设良率分布条件的第一候选机台，包括：
    将所述工艺站点中历史良率的平均值最高的第一数量的机台确定为第一候选机台。
  4. 根据权利要求1所述的方法，其中，在所述基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合之前，所述方法还包括：
    针对每一所述工艺站点，基于设定的量测指标统计条件，确定所述 工艺站点中各机台的历史量测指标。
  5. 根据权利要求4所述的方法，其中，所述基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合，包括：
    确定每一所述工艺站点的量测指标的目标取值范围；
    针对每一所述工艺站点，确定所述工艺站点中历史量测指标在所述工艺站点的量测指标的目标取值范围内的第二候选机台；
    将每一所述工艺站点的第二候选机台加入所述工艺站点的第二候选机台集合。
  6. 根据权利要求5所述的方法，其中，所述确定每一所述工艺站点的量测指标的目标取值范围，包括：
    针对每一所述工艺站点，确定所述工艺站点中历史良率的平均值最高的第二数量的第三候选机台；
    将每一所述工艺站点的每一第三候选机台加入所述工艺站点的第三候选机台集合；
    基于每一所述工艺站点的第三候选机台集合中各机台的历史量测指标中的最大值和最小值，确定每一所述工艺站点的量测指标的目标取值范围。
  7. 根据权利要求1至6中任一项所述的方法，其中，所述历史量测指标包括以下至少之一：历史工序中对机台组件的量测指标、历史工序中对晶圆产品的量测指标。
  8. 根据权利要求1至6中任一项所述的方法，其中，所述基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径，包括：
    对每一所述工艺站点的第一候选机台集合和第二候选机台集合取交集，得到每一所述工艺站点的至少一个目标机台；
    基于每一所述工艺站点的至少一个目标机台，确定所述生产工艺中的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点的一个目标机台。
  9. 根据权利要求1至6中任一项所述的方法，其中，每一所述目标 机台包含至少一个工艺腔室，所述基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径，包括：
    针对每一所述工艺站点的第一候选机台集合以及第二候选机台集合中的每一机台，确定所述机台的至少一个候选工艺腔室；
    基于每一所述工艺站点的第一候选机台集合中每一机台的至少一个候选工艺腔室和第二候选机台集合中每一机台的至少一个候选工艺腔室，确定所述生产工艺中的至少一条目标调度路径；其中，每一条所述目标调度路径中包括每一所述工艺站点中的一个目标工艺腔室。
  10. 根据权利要求1至6中任一项所述的方法，其中，所述方法还包括：
    确定每一所述工艺站点中表征各机台的良率偏差情况的偏差指标；
    将每一所述工艺站点中偏差指标大于偏差阈值的工艺站点加入异常工艺站点集合；
    对所述异常工艺站点集合中偏差指标最大的第三数量的工艺站点进行预警。
  11. 根据权利要求10所述的方法，其中，所述确定每一所述工艺站点中表征各机台的良率偏差情况的偏差指标，包括：
    确定每一所述工艺站点中各机台的历史良率的平均值和平均偏差；
    针对每一所述工艺站点，将所述工艺站点中各机台的历史良率的平均值与平均偏差的比值确定为所述工艺站点的偏差指标。
  12. 一种晶圆调度方法，所述方法包括：
    采用权利要求1至11中任一项所述的调度路径确定方法，确定至少一条目标调度路径；
    基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径；
    基于所述待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。
  13. 根据权利要求12所述的方法，其中，所述基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径，包括：
    针对每一所述目标调度路径，基于所述目标调度路径中每一工艺站 点中目标机台的历史工艺参数，确定所述目标调度路径的工艺参数；
    将所述至少一条目标调度路径中工艺参数满足所述工艺参数条件的目标调度路径确定为所述待调度的调度路径。
  14. 根据权利要求12或13所述的方法，其中，所述工艺参数条件包括以下至少之一：良率条件、时长条件。
  15. 一种调度路径确定装置，包括：
    第一确定模块，配置为基于设定的生产工艺中每一工艺站点中各机台的历史良率指标，确定每一所述工艺站点的第一候选机台集合；
    第二确定模块，配置为基于每一所述工艺站点中各机台的历史量测指标，确定每一所述工艺站点的第二候选机台集合；
    第三确定模块，配置为基于每一所述工艺站点的第一候选机台集合和第二候选机台集合，确定所述生产工艺的至少一条目标调度路径；其中，每一所述目标调度路径中包括每一所述工艺站点中的一个目标机台。
  16. 一种晶圆调度装置，所述装置包括：
    第六确定模块，配置为采用权利要求1至11中任一项所述的调度路径确定方法，确定至少一条目标调度路径；
    第七确定模块，配置为基于设定的工艺参数条件，从所述至少一条目标调度路径中确定待调度的调度路径；
    调度模块，配置为基于所述待调度的调度路径，对晶圆进行生产调度，得到晶圆产品。
  17. 一种计算机设备，包括存储器和处理器，所述存储器存储有可在处理器上运行的计算机程序，所述处理器执行所述程序时实现权利要求1至14任一项所述方法中的步骤。
  18. 一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被处理器执行时实现权利要求1至14任一项所述方法中的步骤。
PCT/CN2021/130582 2021-07-19 2021-11-15 调度路径确定、晶圆调度方法、装置、设备及存储介质 WO2023000556A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202110812969.9 2021-07-19
CN202110812969.9A CN115639786A (zh) 2021-07-19 2021-07-19 调度路径确定、晶圆调度方法、装置、设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023000556A1 true WO2023000556A1 (zh) 2023-01-26

Family

ID=84940657

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2021/130582 WO2023000556A1 (zh) 2021-07-19 2021-11-15 调度路径确定、晶圆调度方法、装置、设备及存储介质

Country Status (2)

Country Link
CN (1) CN115639786A (zh)
WO (1) WO2023000556A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116487303A (zh) * 2023-06-21 2023-07-25 长鑫存储技术有限公司 半导体产品制造过程中氮气吹扫实现方法及电子设备

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW462102B (en) * 2000-11-06 2001-11-01 Promos Technologies Inc Method for monitoring the performance of a manufacturing machine
TW473788B (en) * 2000-09-14 2002-01-21 Promos Technologies Inc Method and system for determining the best process path
CN1770182A (zh) * 2004-11-04 2006-05-10 中芯国际集成电路制造(上海)有限公司 半导体制造代工厂关键机台实时派工预测系统
CN101965569A (zh) * 2008-03-06 2011-02-02 应用材料公司 用于控制设备工程系统的良品率预测反馈
CN104216344A (zh) * 2013-06-03 2014-12-17 富泰华工业（深圳）有限公司 生产排配系统及方法
JP2017045143A (ja) * 2015-08-24 2017-03-02 株式会社Sumco シリコンウェーハの工程計画立案システム、工程計画立案装置、工程計画立案方法及びプログラム
CN106557540A (zh) * 2015-09-30 2017-04-05 台湾积体电路制造股份有限公司 用于晶圆与机台指派的系统
CN107919297A (zh) * 2016-10-08 2018-04-17 中芯国际集成电路制造(上海)有限公司 用于芯片制造的方法和系统
CN111539556A (zh) * 2020-04-02 2020-08-14 北京北方华创微电子装备有限公司 晶片调度方法及装置

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW473788B (en) * 2000-09-14 2002-01-21 Promos Technologies Inc Method and system for determining the best process path
TW462102B (en) * 2000-11-06 2001-11-01 Promos Technologies Inc Method for monitoring the performance of a manufacturing machine
CN1770182A (zh) * 2004-11-04 2006-05-10 中芯国际集成电路制造(上海)有限公司 半导体制造代工厂关键机台实时派工预测系统
CN101965569A (zh) * 2008-03-06 2011-02-02 应用材料公司 用于控制设备工程系统的良品率预测反馈
CN104216344A (zh) * 2013-06-03 2014-12-17 富泰华工业（深圳）有限公司 生产排配系统及方法
JP2017045143A (ja) * 2015-08-24 2017-03-02 株式会社Sumco シリコンウェーハの工程計画立案システム、工程計画立案装置、工程計画立案方法及びプログラム
CN106557540A (zh) * 2015-09-30 2017-04-05 台湾积体电路制造股份有限公司 用于晶圆与机台指派的系统
CN107919297A (zh) * 2016-10-08 2018-04-17 中芯国际集成电路制造(上海)有限公司 用于芯片制造的方法和系统
CN111539556A (zh) * 2020-04-02 2020-08-14 北京北方华创微电子装备有限公司 晶片调度方法及装置

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116487303A (zh) * 2023-06-21 2023-07-25 长鑫存储技术有限公司 半导体产品制造过程中氮气吹扫实现方法及电子设备
CN116487303B (zh) * 2023-06-21 2023-11-03 长鑫存储技术有限公司 半导体产品制造过程中氮气吹扫实现方法及电子设备

Also Published As

Publication number Publication date
CN115639786A (zh) 2023-01-24

Similar Documents

Publication Publication Date Title
TWI645484B (zh) 用於半導體製造的自動化工具參數影響識別系統的方法和裝置
US9811391B1 (en) Load balancing and conflict processing in workflow with task dependencies
CN110580649B (zh) 一种商品潜力值的确定方法和装置
EP3690663A1 (en) Application cleaning method and apparatus, storage medium and electronic device
CN110457577B (zh) 数据处理方法、装置、设备和计算机存储介质
CN111143697B (zh) 一种内容推荐的方法以及相关装置
WO2023000556A1 (zh) 调度路径确定、晶圆调度方法、装置、设备及存储介质
CN106027317B (zh) 信任感知的Web服务质量预测系统及方法
CN110889036A (zh) 一种多维度信息的处理方法、装置及终端设备
CN109447103B (zh) 一种基于硬聚类算法的大数据分类方法、装置及设备
CN111816253A (zh) 一种基因检测解读方法及装置
US10853130B1 (en) Load balancing and conflict processing in workflow with task dependencies
CN113762377A (zh) 网络流量识别方法、装置、设备及存储介质
JP5402375B2 (ja) 情報処理装置、基準値決定方法およびプログラム
Roberts et al. Interactive Analytical Treemaps for Visualisation of Call Centre Data.
CN116564409A (zh) 基于机器学习的转移性乳腺癌转录组测序数据识别方法
Dewhurst et al. Systematic analysis of non-structural protein features for the prediction of PTM function potential by artificial neural networks
CN109359108A (zh) 报表提取方法、装置、存储介质及电子设备
CN111178055B (zh) 语料识别方法、装置、终端设备和介质
JP2020198080A (ja) １以上のプロセスを監視しセンサデータを提供する複数のセンサを含むシステムのための方法
Mercatanti et al. CRIMEtoYHU: a new web tool to develop yeast-based functional assays for characterizing cancer-associated missense variants
US20230086106A1 (en) Intellectual-property analysis platform
US20230090090A1 (en) Intellectual-property analysis platform
CN113343038A (zh) 数据可视化展示方法及装置
KR20140073624A (ko) 기업의 해외 진출 역량 평가 방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 21950794

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE