Machine determination method, task assignment method, system, equipment and medium

By standardizing the quality parameters of the machine during semiconductor chip manufacturing process, the preferred machine is determined, and the problem of poor processing quality of semiconductor chips in the prior art is solved, and the satisfaction of high-quality needs and the accuracy of processing task assignment is achieved. .

CN118410997BActive Publication Date: 2024-11-19NEXCHIP SEMICON CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410873941.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-02
Publication Date
2024-11-19
Estimated Expiration
2044-07-02

AI Technical Summary

Technical Problem

The prior art is difficult to accurately distinguish the processing quality of the machine during semiconductor chip manufacturing, resulting in semiconductor chips with higher quality requirements being assigned to machines with relatively average processing quality, making it difficult to ensure high processing quality.

Method used

By obtaining the parameter values ​​of multiple machines relative to multiple quality parameters, performing standardized processing, generating a set of standard values ​​of different standardized algorithms, and determining the preferred machine based on these standard values ​​to ensure that the process product executed by the preferred machine is of better quality than that of the quality of the process products performed by the preferred machine Non-preferred machine.

Benefits of technology

It has achieved accurate improvement of the processing quality of semiconductor chips, met the needs of high processing quality, and better reflected the differences between machines through the evaluation of multiple quality parameters, ensuring the accuracy of processing tasks.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118410997B_ABST
    Figure CN118410997B_ABST
Patent Text Reader

Abstract

The present application provides a method for determining a machine, a method for assigning tasks, a system, a device and a medium. The method obtains parameter values ​​of multiple machines respectively relative to multiple quality parameters; wherein the multiple machines correspond to specified processing techniques; the parameter values ​​of the multiple quality parameters are standardized to obtain standard values ​​corresponding to the multiple quality parameters; wherein the standard values ​​of the specified quality parameters among the multiple quality parameters are divided into multiple standard value sets, and the multiple standard value sets include a first standard value set and a second standard value set, the standard values ​​in the second standard value set are greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms; based on the standard values ​​of the multiple quality parameters, a preferred machine is determined among the multiple machines. The preferred machine can be determined more accurately.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The embodiments of the present application relate to the field of semiconductor processing and manufacturing, and specifically to a method for determining a machine, a method for assigning tasks, a system, a device, and a medium. Background Art

[0002] During the production process of semiconductor chips, tasks are assigned to machines through the dispatching system (RTD, Real Time Dispatch).

[0003] Typically, a processing task list is maintained in the dispatching system, and the urgency of the tasks in the processing task list and the load balance of the machines involved in the corresponding processing technology are comprehensively evaluated, and the processing tasks in the processing task list are dispatched to the machines.

[0004] The processing quality of the machine to perform the processing task has a certain impact on the quality of the final semiconductor chip. In some cases, some semiconductor chips used in specific fields also have higher requirements for processing quality.

[0005] Therefore, there is a need in the prior art to improve the processing quality of semiconductor chips. Summary of the invention

[0006] The present application provides a machine determination method, a task assignment method, a system, a device and a medium, which can improve the processing quality of semiconductor chips to a certain extent by more accurately determining the optimal machine.

[0007] The present application provides a method for determining a machine, the method comprising: obtaining parameter values ​​of a plurality of machines respectively corresponding to a plurality of quality parameters; wherein the plurality of machines correspond to specified processing techniques; standardizing the parameter values ​​of the plurality of quality parameters to obtain standard values ​​corresponding to the plurality of quality parameters; wherein the standard values ​​of a specified quality parameter among the plurality of quality parameters are divided into a plurality of standard value sets, the plurality of standard value sets comprising a first standard value set and a second standard value set, the standard values ​​in the second standard value set being greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms; based on the standard values ​​of the plurality of quality parameters, determining a preferred machine among the plurality of machines; wherein the quality of a process product obtained by the preferred machine executing the specified processing technique is better than the quality of a process product obtained by a non-preferred machine executing the specified processing technique.

[0008] Optionally, the step of standardizing the parameter values ​​of the multiple quality parameters to obtain standard values ​​corresponding to the multiple quality parameters includes: performing forward processing on the parameter values ​​of at least some of the quality parameters to obtain positive values ​​corresponding to at least some of the quality parameters; wherein the at least some of the quality parameters include the specified quality parameters; sorting the positive values ​​of the specified quality parameters to obtain a positive value sequence; determining a boundary value as a segment boundary in the positive value sequence; wherein the boundary value divides the positive value sequence into multiple positive value sets, the multiple positive value sets include a first positive value set and a second positive value set, and the positive values ​​in the second positive value set are greater than the positive values ​​in the first positive value set; performing standardization on the first positive value set and the second positive value set respectively to obtain the first standard value set and the second standard value set.

[0009] Optionally, the step of determining a boundary value serving as a segment boundary in the forward value sequence includes: performing a second-order difference operation on the forward value sequence to obtain a second-order difference value sequence; and taking the positive value corresponding to the difference value in the second-order difference value sequence that is greater than a specified threshold as the boundary value.

[0010] Optionally, the steps of performing standardization processing on the first positive value set and the second positive value set respectively to obtain the first standard value set and the second standard value set include: performing standardization processing on the first positive value set based on a first standardization algorithm to obtain a first standard value set corresponding to the first positive value set; performing standardization processing on the second positive value set based on a second standardization algorithm to obtain a second standard value set corresponding to the second positive value set; wherein the second standardization algorithm includes using the first standardization algorithm to calculate the result value corresponding to the positive value in the second positive value set, and adding the result value to the last standard value in the first standard value set to obtain the standard value corresponding to the positive value.

[0011] Optionally, the multiple quality parameters include: defect count increase, film thickness uniformity, over-specification ratio, quality abnormality handling system trigger rate, normal operation time ratio and maintenance cycle stage score; wherein, the defect count increase is the increase in the number of defects after the test workpiece is subjected to the specified processing technology by the machine relative to the number of defects before processing, and the film thickness uniformity is used to indicate the uniformity of the film on the process product after processing by the machine; the over-specification ratio is used to indicate the ratio of the number of process products whose parameter values ​​exceed the upper limit or are less than the lower limit among the process products processed by the machine to the total number of process products processed by the machine; the quality abnormality handling system trigger rate is used to indicate the ratio of the number of process products processed by the machine that trigger the quality abnormality handling system to the total number of process products processed by the machine; the normal operation time ratio is used to indicate the ratio of the actual normal operation time of the machine in a specified time period to the specified time period; the maintenance cycle stage score is used to indicate the stage in which the machine is in the maintenance cycle; wherein, the specified quality parameters include the defect count increase.

[0012] Optionally, based on the standard values ​​of the multiple quality parameters, the step of determining a preferred machine from the multiple machines includes: constructing a machine performance value corresponding to each machine based on the standard value of the defect count increase value and the standard value of the film thickness uniformity; wherein the machine performance value is used to represent the evaluation of the machine when performing process testing; constructing a production quality value corresponding to each machine based on the standard value of the over-specification ratio and the standard value of the quality abnormality handling system trigger rate; wherein the production quality value is used to represent the quality stability of the machine in executing the specified processing technology; constructing an operation stability evaluation value corresponding to each machine based on the standard value of the normal operating time ratio and the standard value of the maintenance cycle stage score; wherein the operation stability evaluation value is used to represent the evaluation of the operation stability of the machine; obtaining a quality evaluation value based on the machine performance value, the production quality value and the operation stability evaluation value using the entropy weight method; wherein the quality evaluation value is used to characterize the quality of the process product obtained by the machine; and determining a specified number of machines as the preferred machines according to the quality evaluation values ​​representing the quality from high to low.

[0013] Optionally, the method further includes: obtaining a machine information set and machine status information corresponding to the specified processing technology; wherein the machine information set includes machine information of multiple machines corresponding to the specified processing technology; for a machine whose machine status information indicates that it is in an abnormal state, if the machine information of the machine is associated with a maximum process interval duration, the machine information is removed from the machine information set; wherein the abnormal state includes: a downtime state, a maintenance state or a repair state; for a machine whose machine status information indicates that it is in an abnormal state, if the machine information of the machine is not associated with a maximum process interval duration and the duration of being in the abnormal state exceeds a specified duration, the machine information of the machine is removed from the machine information set, and the machines represented by the remaining machine information in the machine information set are in a state in which the specified processing technology can be executed; accordingly, the step of obtaining parameter values ​​of multiple machines respectively relative to multiple quality parameters includes: obtaining parameter values ​​of the machines represented by the machine information in the machine information set respectively relative to multiple quality parameters.

[0014] In another aspect, the present application further provides a method for assigning semiconductor processing tasks, the method comprising: assigning a semiconductor processing task with high quality requirements to a preferred tool determined by any of the aforementioned tool determination methods.

[0015] In another aspect, the present application also provides a work dispatching system, which includes: an acquisition unit, used to acquire parameter values ​​of multiple machines respectively corresponding to multiple quality parameters; wherein the multiple machines correspond to specified processing techniques; a processing unit, used to standardize the parameter values ​​of the multiple quality parameters to obtain standard values ​​corresponding to the multiple quality parameters; wherein the standard values ​​of specified quality parameters among the multiple quality parameters are divided into multiple standard value sets, and the multiple standard value sets include a first standard value set and a second standard value set, the standard values ​​in the second standard value set are greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms; a determination unit, used to determine a preferred machine among the multiple machines based on the standard values ​​of the multiple quality parameters; wherein the quality of the process product obtained by the preferred machine performing the specified processing technique is better than the quality of the process product obtained by the non-preferred machine performing the specified processing technique.

[0016] In another aspect, the present application also provides an electronic device, comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement a method for determining a machine as described in any of the foregoing descriptions, or to enable the one or more processors to implement a method for dispatching semiconductor processing tasks as described in the foregoing descriptions.

[0017] In another aspect, the present application also provides a computer storage medium storing a computer program, wherein the computer program, when executed by a processor, implements any of the aforementioned methods for determining a machine, or implements the aforementioned method for dispatching semiconductor processing tasks.

[0018] The unexpected technical effect of the present invention is that by using multiple quality parameters to evaluate multiple machines, the preferred machine among the multiple machines is obtained, so as to allocate processing tasks with higher processing quality requirements to the preferred machine, thereby meeting the requirements of the processing tasks for high processing quality. Furthermore, in the process of evaluating multiple machines, the parameter values ​​of some quality parameters will be segmented and standardized, so that the standard values ​​of the quality parameters can better reflect the differences between different machines, and the preferred machine can be determined more accurately. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 Shown is a flow chart of a method for determining a machine platform provided in one embodiment of the present application.

[0020] Figure 2 Shown is a schematic diagram of the working process of a work dispatching system provided in one embodiment of the present application.

[0021] Figure 3 Shown is a schematic diagram of the interaction between a dispatching system, a manufacturing execution system and a machine process control system provided in one embodiment of the present application.

[0022] Figure 4 Shown is a module diagram of a work dispatching system provided in one embodiment of the present application.

[0023] Figure 5 Shown is a schematic diagram of an electronic device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0025] In the description of the embodiments of the present application, it should be understood that the terms "first" and "second" are used for descriptive purposes only and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present application, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0026] In the related art, multiple processing techniques are involved in the manufacturing process of semiconductor chips, and the machines used in each processing technique may be different. For example, the photolithography process requires a photolithography machine, and the thin film deposition process requires corresponding thin film deposition equipment. Usually, each processing technique is equipped with multiple machines to improve the overall production efficiency.

[0027] Normally, machines are regularly maintained so that machines that can receive processing tasks meet the basic processing quality requirements. However, there will be certain differences in the quality of the process products processed by multiple machines of the same processing technology. For example, the number of defects of process products processed by some machines is relatively small, and the operation stability of some machines themselves is relatively high. In this way, there will be certain differences in the quality of semiconductor chips obtained by executing multiple identical processing technologies. For example, a batch of wafers are assigned to machines with relatively general processing quality in multiple processing technologies during the process of being processed into semiconductor chips, and the quality of the semiconductor chips finally obtained may be relatively general, while another batch of wafers are assigned to some machines with higher processing quality during the process of being processed into semiconductor chips, so that the semiconductor chips finally obtained have better quality. Of course, the processing tasks may be randomly assigned to the machines involved in each processing technology, so that the quality of the semiconductor chips finally obtained will have certain fluctuations.

[0028] In some cases, semiconductor chips used in some specific fields have higher requirements for quality. If the usual processing process is used, the final yield of the semiconductor chips may be low. For example, the use environment of automotive chips used in automobiles may be more complex, so automotive chips require higher quality. Specifically, the operating temperature range of automotive chips may be about -40°C to about 115°C, the humidity range may be 0~100%, the tolerable failure rate needs to be less than or equal to 10PPM (Parts Per Million), the working life will need to be 15~20 years, and it needs to comply with the standard AEC-Q100. In contrast, the operating temperature range of semiconductor chips in general consumer electronics is about 0°C to about 40°C, the humidity of the use environment is usually low, the tolerable failure rate needs to be less than or equal to 200PPM, the working life is generally 3 to 5 years, and it needs to comply with the standard JESD48.

[0029] In the semiconductor chip manufacturing process, multiple semiconductor chips may involve the same processing technology and share the same machines involved in the processing technology. It is difficult for the dispatching system to accurately identify the processing quality of the machine, so that the processing tasks of semiconductor chips with higher quality requirements may be assigned to machines with relatively average processing quality, making it difficult to ensure the processing quality of semiconductor chips with higher quality requirements.

[0030] Therefore, it is necessary to provide a technical solution that can more accurately determine the optimal machine to improve the processing quality of semiconductor chips to a certain extent.

[0031] See also Figure 1 The present invention provides a method for determining a machine. The method for determining a machine can be applied to a dispatching system. The dispatching system can be used to dispatch processing tasks to machines involved in various processing processes during the semiconductor chip manufacturing process. The method for determining a machine can include the following steps.

[0032] Step S110: Obtain parameter values ​​of a plurality of machines respectively corresponding to a plurality of quality parameters; wherein the plurality of machines correspond to a specified processing technology.

[0033] The quality parameter may be a predefined parameter that is closely related to the processing quality of the machine. The quality parameter may include parameters related to the machine operation stability, or parameters related to the quality of the process product of the machine. The process product may refer to the product obtained after the machine performs a processing process on the semiconductor material.

[0034] In some embodiments, the quality parameters may include, but are not limited to: defect count increase, film thickness uniformity, over-specification ratio, quality abnormality handling system trigger rate, normal operation time ratio, and maintenance cycle stage score.

[0035] The defect count increase value is the increase in the number of defects after the test workpiece is subjected to the specified processing technology by the machine relative to the number of defects before processing. Specifically, the test workpiece can be first placed in the test equipment to measure the number of defects before the test workpiece is subjected to processing, and after the test workpiece is subjected to the specified processing technology by the machine, it is placed in the test equipment again to measure the number of defects after the test workpiece is subjected to processing, and the number of defects after processing is subtracted from the number of defects before processing to obtain the defect count increase value caused by the machine performing the specified processing technology. The smaller the parameter value of the defect count increase value, the better the quality of the process product processed by the machine.

[0036] The film thickness uniformity can be used to indicate the uniformity of the film on the process product after the machine is processed. Specifically, the process product after the machine is processed can be placed in the test equipment to measure the uniformity of the film of the process product. The smaller the parameter value of the film thickness uniformity, the better the quality of the process product processed by the machine.

[0037] The over-specification ratio can be used to indicate the ratio of the number of process products whose parameter values ​​exceed the upper limit or are less than the lower limit to the total number of process products processed by the machine. Specifically, multiple parameters may be measured for the process products processed by the machine, and the multiple parameters may include but are not limited to quality parameters. Each parameter may be set with an upper limit and / or a lower limit. When the parameter value is greater than the upper limit or less than the lower limit, it can be determined that an abnormality has occurred in the process of the machine executing the specified processing technology. The smaller the parameter value of the over-specification ratio, the better the stability of the machine. A machine with better stability helps to improve the processing quality of the machine.

[0038] The quality exception handling system trigger rate can be used to indicate the ratio of the number of process products processed by the machine that trigger the quality exception handling system to the total number of process products processed by the machine. The quality exception handling system can be used to monitor, identify and analyze quality problems in the semiconductor chip manufacturing process. Specifically, the quality exception handling system can monitor the working conditions of the machine and the process product conditions, and will sound an alarm after a problem is identified. The smaller the parameter value of the quality exception handling system trigger rate, the better the stability of the machine.

[0039] The normal operation time percentage is used to indicate the ratio of the actual normal operation time of the machine in the specified time period to the specified time period. Specifically, the machine may stop working due to some faults. The longer the machine stops working, it may indicate that the stability of the machine itself is poor. The longer the actual normal operation time of the machine is, the better the stability of the machine is. The specified time period can be a set time period. For example, the specified time period can be 1 month, 2 months, or 6 months, etc., or the specified time period can also be 1 week, 2 weeks, 3 weeks, or 5 weeks, etc. Of course, the specified time period can also be 1 year, 3 years, or 5 years, etc. The larger the parameter value of the normal operation time percentage, the better the stability of the machine.

[0040] The maintenance cycle stage score is used to indicate the stage in the maintenance cycle that the machine is in. Specifically, a maintenance cycle can be divided into multiple stages, and each stage corresponds to a parameter value. For example, the maintenance cycle is divided into 5 stages, and the parameter value corresponding to the third stage in the middle is 3, the parameter values ​​corresponding to the second and fourth stages adjacent to the third stage are both 2, and the parameter values ​​corresponding to the first and fifth stages are both 1. Of course, there can be other settings for the number of stages and the parameter values ​​corresponding to each stage, which will not be repeated here. The larger the parameter value of the maintenance cycle stage score, the better the stability of the machine.

[0041] In this embodiment, the designated processing technology may be any processing technology in the semiconductor chip processing process. The designated processing technology may involve multiple machines. The number of machines may include but is not limited to 4, 5, 7 or 9, etc. In some cases, when the number of machines is small, in order to ensure the production efficiency of semiconductor chips, the dispatching system may assign processing tasks to the machines according to the progress requirements without determining the preferred machine. For example, the number of machines is 1, 2 or 3.

[0042] Step S112: Standardize the parameter values ​​of multiple quality parameters to obtain standard values ​​corresponding to the multiple quality parameters; wherein the standard values ​​of specified quality parameters among the multiple quality parameters are divided into multiple standard value sets, the multiple standard value sets include a first standard value set and a second standard value set, the standard values ​​in the second standard value set are greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms.

[0043] The dimensions of the parameter values ​​of multiple quality parameters are different, so that relative to the processing quality of the machine, the larger the parameter values ​​of some quality parameters are, the better the stability of the machine is, for example, the normal operation time ratio and the maintenance cycle stage score. The smaller the parameter values ​​of some quality parameters are, the better the processing quality of the machine is, for example, the defect count increase value, film thickness uniformity and over-specification ratio. Therefore, it is necessary to unify the dimensions of the parameter values ​​of multiple quality parameters in order to further determine the preferred machine based on the quality parameters.

[0044] In some embodiments, the dispatching system can perform positive processing on the parameter values ​​of at least some quality parameters to obtain positive values ​​corresponding to at least some quality parameters; wherein at least some quality parameters include specified quality parameters; sorting processing is performed on the positive values ​​of the specified quality parameters to obtain a positive value sequence; boundary values ​​serving as segment boundaries are determined in the positive value sequence; wherein the boundary values ​​divide the positive value sequence into multiple positive value sets, the multiple positive value sets include a first positive value set and a second positive value set, and the positive values ​​in the second positive value set are greater than the positive values ​​in the first positive value set; standardization processing is performed on the first positive value set and the second positive value set, respectively, to obtain a first standard value set and a second standard value set.

[0045] The dispatch system can perform positive processing on the parameter values ​​of multiple quality parameters, so that the larger the values ​​of the multiple quality parameters are, the better the overall state of the machine is. For example, the dispatch system can perform positive processing on the parameter values ​​of quality parameters such as defect count increase, film thickness uniformity, over-specification ratio, and quality abnormality processing system trigger rate. In some embodiments, the formula for performing positive processing can be f(x) = max -x. Among them, f(x) is used to represent the positive value corresponding to the parameter value, max represents the maximum value of the parameter value involved in a quality parameter, and x represents the parameter value that is processed positively.

[0046] In some cases, due to certain differences between multiple machines, the parameter values ​​of some quality parameters among multiple quality parameters may fluctuate greatly. If the standard values ​​are obtained using the same standardization algorithm, it may be difficult to reflect the difference information of such parameter values. The quality parameters with large fluctuations can be used as designated quality parameters, and the parameter values ​​of the designated quality parameters can be standardized in sections, so that smaller parameter values ​​and larger parameter values ​​are standardized using different standardization algorithms, respectively, so that the final standard values ​​can better reflect the differences in parameter values.

[0047] In some implementations, taking the designated quality parameter as a defect count increase value as an example, a segmented standardization process for parameter values ​​is introduced. The number of defects in the process product obtained by the machine can be separately counted according to different defect sizes to obtain count increase values ​​of different defect sizes, so that the following multiple lines of data sequence can be formed.

[0048]

[0049] The value of n represents the number of different defect sizes, and the value of m represents the number of machines. (i≤n, j≤m) corresponds to a machine, indicating the count increase value of the machine corresponding to the i-th defect size.

[0050] In some cases, the aforementioned multi-row data sequence may not be a regular data matrix. There is no correlation between the value of n and the value of m. Furthermore, in the actual production process, the count increase values ​​of all defect sizes may not be tested for all machines in the same processing technology, and there may be count increase values ​​for only some machines for a certain defect size. The dispatching system can select the defect size involving the most machines from multiple defect sizes, and select the count increase value of the defect size as the parameter value of the defect count increase value. In some embodiments, if the number of defect sizes involving the most machines is also multiple, the dispatching system can select a defect size with a smaller count increase value from the multiple defect sizes, and use the count increase value of the defect size as the parameter value of the defect count increase value.

[0051] The dispatching system can use the above-mentioned positive processing for the count increase values ​​of all defect sizes, and then directly determine the positive value of the defect count increase value. Of course, the dispatching system can also first determine the parameter value of the defect count increase value and then perform the positive processing to obtain the positive value.

[0052] Furthermore, a plurality of positive values ​​of the defect count increment value may be sorted to obtain a positive value sequence, for example, in ascending order.

[0053] The dispatching system can determine a boundary value in a positive value sequence, and divide the positive value sequence into a first positive value set and a second positive value set based on the boundary value. The boundary value can be a positive value in the positive value sequence. The boundary value can be used as a demarcation, and the positive values ​​before the boundary value in the positive value sequence can be used as the first positive value set, and the positive values ​​after the boundary value can be used as the second positive value set. The boundary value itself can be placed in the first positive value set or in the second positive value set. Preferably, the boundary value is placed in the second positive value set.

[0054] In some implementations, the dispatching system may perform a second-order difference operation on the positive value sequence to obtain a second-order difference value sequence; and use the positive value corresponding to the second-order difference value in the second-order difference value sequence that is greater than a specified threshold as a boundary value.

[0055] Specifically, assume that the forward value sequence is [y1, y2, ..., y z ], z can represent the number of positive values ​​in the positive value sequence. Any y i (1≤i≤z) represents a positive value. A first-order difference operation can be performed based on two adjacent positive values. The specific formula 1 for the first-order difference operation is as follows.

[0056] Formula 1.

[0057] After the first-order difference value sequence is obtained by calculation according to Formula 1, the first-order difference value can be used to calculate again according to Formula 1 to obtain a second-order difference value sequence.

[0058] In some implementations, the second-order difference operation may also be performed directly based on the forward value sequence according to the following formula 2.

[0059] Formula 2.

[0060] The dispatching system can convert the second-order difference value sequence [∆ 2 y1, ..., ∆ 2 y (z-2) ] is compared with the set threshold, and the positive value corresponding to the first second-order difference value greater than the specified threshold is used as the boundary value in order. For example, the value of the specified threshold may be 8, 9, 10, 11, 12, ..., 20, 21 or 30, etc. Preferably, the value of the specified threshold is 10. Of course, the value of the specified threshold may not be limited to the above-mentioned list. Further, after determining the first second-order difference value greater than the specified threshold, the corresponding positive value may be obtained by reverse calculation based on the above formula 1, and the positive value may be used as the boundary value.

[0061] The second-order difference value can be used to indicate that the fluctuation trend of the positive value is getting bigger or smaller. When the second-order difference value is greater than the specified threshold, it can be considered that the fluctuation trend of the positive value is large, and the positive value corresponding to the second-order difference value can be used as the boundary value to divide the positive value sequence into a first positive value set and a second positive value set. At this time, the positive values ​​in the second positive value set will increase much more than the positive values ​​in the first positive value set, resulting in a large increase. In order to retain the data fluctuation information of the second positive value relative to the first positive value, different standardization algorithms can be used for the first positive value set and the second positive value set to obtain the first standard value set and the second standard value set.

[0062] In some embodiments, the dispatching system can standardize the first positive value set based on a first standardization algorithm to obtain a first standard value set corresponding to the first positive value set; and standardize the second positive value set based on a second standardization algorithm to obtain a second standard value set corresponding to the second positive value set; wherein the second standardization algorithm includes using the first standardization algorithm to calculate the result value corresponding to the positive value in the second positive value set, and adding the result value to the last standard value in the first standard value set to obtain the standard value corresponding to the positive value.

[0063] By using appropriate standardization algorithms for different positive value sets, the final standard value set can retain more data fluctuation information, which helps the dispatching system to more accurately determine the preferred machine. For example, assuming that the first positive value set has k positive values, the first positive value set and the second positive value set have a total of g positive values, and the positive value sequence has g positive values. The first standardization algorithm can be used for the first positive value set as shown in Formula 3 below.

[0064] Formula 3.

[0065] in, Used to represent the minimum value of the positive values ​​in the first positive value set. Used to represent the maximum value of the positive value in the first positive value set. i It is used to represent any positive value in the first positive value set. Wherein, the value range of i is 1≤i≤k. y(i) is used to represent the standard value corresponding to any positive value in the first positive value set.

[0066] A second normalization algorithm such as Formula 3 may be used for the second positive value set.

[0067] Formula 4.

[0068] in, Used to represent the minimum value of the positive values ​​in the second positive value set. It is used to represent the maximum value of the positive value in the second positive value set. The value range of j is (k+1)≤j≤g. y(j) is used to represent the standard value corresponding to any positive value in the second positive value set.

[0069] In this implementation, the last standard value in the first standard value set is used as an operator to obtain the standard value in the second standard value set, so that the standard value in the second standard value set will be based on the last standard value in the first standard value set. The standard values ​​in the second standard value set and the standard values ​​in the first standard value set can better reflect the value differences of the parameter values ​​of the quality parameters, so that the first standard value set and the second standard value set can better characterize the corresponding machines.

[0070] In some embodiments, the dispatching system may perform positive processing on the count increase values ​​of all defect sizes to obtain multiple positive value sequences corresponding to different defect sizes, and further calculate the aforementioned standard value for each positive value sequence. Of course, the dispatching system may also calculate the aforementioned standard value only for the positive value determined as the defect count increase value.

[0071] In some embodiments, the specified quality parameter is not limited to the defect count increment value exemplified above, but may also include other quality parameters with large value fluctuations. Based on the inspiration of multiple embodiments of this specification, technicians in the relevant field may standardize other quality parameters in sections, which will not be repeated here.

[0072] In some embodiments, quality parameters such as film thickness uniformity, over-specification ratio, quality abnormality handling system trigger rate, normal operation time ratio, and maintenance cycle stage score can also be standardized based on the aforementioned formula 3 to obtain a standard value for each quality parameter.

[0073] Step S114: determining a preferred machine from among multiple machines based on standard values ​​of multiple quality parameters; wherein the quality of a process product obtained by executing the specified process on the preferred machine is better than the quality of a process product obtained by executing the specified process on a non-preferred machine.

[0074] The standard values ​​of the multiple quality parameters can better characterize the corresponding machines. Thus, the standard values ​​of the multiple quality parameters can be used to determine the preferred machine among multiple machines.

[0075] In some embodiments, the dispatching system can construct a machine performance value corresponding to each machine based on the standard value of the defect count increase value and the standard value of the film thickness uniformity; wherein the machine performance value is used to represent the evaluation of the machine when performing process testing; the production quality value corresponding to each machine is constructed based on the standard value of the over-specification ratio and the standard value of the quality abnormality processing system trigger rate; wherein the production quality value is used to represent the quality stability of the machine in executing a specified processing technology; the operation stability evaluation value corresponding to each machine is constructed based on the standard value of the normal operation time ratio and the standard value of the maintenance cycle stage score; wherein the operation stability evaluation value is used to represent the evaluation of the operation stability of the machine; the entropy weight method is used to obtain the quality evaluation value based on the machine performance value, the production quality value and the operation stability evaluation value; wherein the quality evaluation value is used to characterize the quality of the process product obtained by the machine; according to the quality evaluation value representing the quality from high to low, a specified number of machines are determined as the preferred machines. The value of the specified number can be pre-specified. For example, the value of the specified number can be 1, 2, 3, 5 or 10, etc., which will not be repeated. In some embodiments, the dispatching system can calculate the specified number according to the formula (Count*0.3)+1. Count is used to represent the total number of machines involved in the specified processing technology. Alternatively, Count is used to represent the total number of candidate machines used to determine the preferred machine. For example, to determine the preferred machine among 10 machines, the specified number according to the above formula is 4.

[0076] The dispatching system can perform weighted summation on the standard value of the defect count increase and the standard value of the film thickness uniformity to obtain the measurement machine performance value. Of course, the method for calculating the measurement machine performance value is not limited to weighted summation, and can also be to multiply the standard value of the defect count increase by the standard value of the film thickness uniformity, or other algorithms. In this embodiment, the weight of the defect count increase can be much greater than the weight of the film thickness uniformity. For example, the weight of the defect count increase can be 0.9, and the weight of the film thickness uniformity can be 0.1. It can be considered that the defect count increase is the most direct and important quality parameter for evaluating the processing quality of the machine. In this way, the weight of the defect count increase is much greater than the weight of the film thickness uniformity, so that the final quality evaluation value can better represent the quality of the machine. Of course, the weight of the defect count increase is not limited to 0.9, but can also be 0.91, 0.92, 0.93 or 0.95, etc., and the corresponding weight of the film thickness uniformity can be 0.09, 0.08, 0.07 or 0.05. The weight of the defect count increase value may also be 0.85, 0.8, 0.75, 0.7 or 0.65, etc. Correspondingly, the weight of the film thickness uniformity may be 0.15, 0.2, 0.25, 0.3 or 0.35, etc.

[0077] The dispatch system can obtain the production quality value by weighted summing up the standard value of the over-specification ratio and the standard value of the quality anomaly handling system trigger rate. Of course, the algorithm for calculating the production quality of the dispatch system is not limited to weighted summing, and other algorithms can also be used, such as multiplying the standard value of the over-specification ratio and the standard value of the quality anomaly handling system trigger rate. In this embodiment, the weight of the over-specification ratio can be 0.6, and the weight of the quality anomaly handling system trigger rate can be 0.4. Of course, the weights of the two can also be adjusted as needed. For example, the weight of the over-specification ratio and the weight of the quality anomaly handling system trigger rate are both 0.5. Alternatively, the weight of the over-specification ratio can be 0.7, and the trigger rate of the quality anomaly handling system trigger rate can be 0.3, etc. No more details.

[0078] The dispatching system can perform weighted summation based on the standard value of the normal operation time ratio and the standard value of the maintenance cycle stage score to obtain the operation stability evaluation value corresponding to each machine. Of course, the algorithm for calculating the operation stability evaluation value of the dispatching system is not limited to weighted summation, and other algorithms can also be used, such as multiplying the standard value of the normal operation time ratio with the standard value of the maintenance cycle node score. In this embodiment, the weights of the normal operation time ratio and the maintenance cycle stage score can both be 0.5. Of course, the weights of the two can also be fine-tuned, which will not be repeated.

[0079] The dispatching system can use the entropy weight method (Topsis algorithm) to calculate the quality evaluation value of each machine based on the machine performance value, production quality value and stability evaluation value of each machine. And the machines can be sorted according to the quality evaluation value. Specifically, the dispatching system has the machine information of each machine. The dispatching system can sort the machine information based on the quality evaluation value, and then select a specified number of machine information. The machine represented by the selected machine information is the preferred machine. In the dispatching system, a preferred label can be added to the selected machine information to indicate that the machine represented by the machine information with the preferred label is the preferred machine. Of course, a preferred machine information list can also be maintained separately in the dispatching system, and the machine represented by the machine information in the preferred machine information list is the preferred machine.

[0080] In some embodiments, the dispatching system may re-execute the machine determination method after each specified time interval to update the machine information representing the preferred machine. For example, the dispatching system may execute the machine determination method once every 10 minutes. Of course, the specified time interval is not limited to 10 minutes, and may also be 11 minutes, 13 minutes, 20 minutes, etc.

[0081] See also Figure 2. In some embodiments, the dispatch system can also obtain a set of machine information and machine status information corresponding to a specified processing technology; wherein the set of machine information includes machine information of multiple machines corresponding to the specified processing technology. Semiconductor chips may require the use of multiple processing technologies, and there may be certain differences in the machines used for different processing technologies. The dispatch system can determine the preferred machine for each processing technology respectively, so as to assign processing tasks to the machine according to the actual processing quality requirements when executing each processing technology. Of course, the dispatch system can also be set to determine the preferred machine only for some processing technologies.

[0082] The dispatching system can obtain the semiconductor chip manufacturing tasks involved in the specified processing technology. Furthermore, the dispatching system can obtain the execution status identifier of the semiconductor chip manufacturing tasks involved in the specified processing technology, and when the execution status identifier corresponding to the semiconductor chip manufacturing task is a specified value, it is determined that the semiconductor chip task is in the execution state. Some semiconductor chip manufacturing tasks require that there is a maximum process interval duration for the multiple processing technologies involved, and usually a determined machine is associated with the semiconductor chip manufacturing tasks that require the maximum process interval duration. In this way, some machines themselves may also be associated with the maximum process interval duration. When the semiconductor chip manufacturing task is in the execution state, the machines involved will be constrained by the maximum process interval duration. If the semiconductor chip manufacturing task is not in the execution state, the machines involved in its processing technology will not be constrained by the maximum process interval duration. The machine represented by the machine information associated with the maximum process interval duration is the machine that needs to start processing the process product within the maximum process interval duration.

[0083] Specifically, the dispatch system can obtain the machine status information of the machine from the database of the Manufacturing Execution System (MES), and read the maximum process interval duration associated with the machine information from the Production Data Warehouse (PDW).

[0084] The dispatch system can identify and remove machine information that cannot be used as the preferred machine from the machine information set based on the machine status information.

[0085] For machines whose machine status information indicates that they are in a normal state, the corresponding machine information will be retained in the machine information set. Machines in a normal state can be used as candidate machines for determining the preferred machine. That is, the preferred machine will be determined from the candidate machines. A machine in a normal state can indicate that the machine is in a working state or an idle state.

[0086] For machines whose machine status information indicates that they are in an abnormal state, if the machine information of the machine is associated with the maximum process interval duration, the dispatch system can remove the machine information from the machine information set. Among them, the abnormal state includes that the machine state is neither idle nor working; or, the abnormal state includes: downtime, maintenance or repair. Of course, being in an abnormal state does not necessarily mean that the machine cannot be used as a candidate machine, and further identification is also required. For example, if the machine is only in a short-term downtime state, the machine can be used as a candidate machine.

[0087] In this embodiment, if a machine status is idle or working, the dispatch system may consider the status of the corresponding machine to be normal. If a machine status is in an abnormal state, for example, the machine status is neither idle nor working. At this time, the machine represented by the machine status may have some abnormal conditions. For machines that are neither idle nor working, the dispatch system will determine whether the machine represented by the machine information can be used as a candidate machine for determining the preferred machine based on whether the corresponding machine information is associated with the maximum process interval time. When the machine information is associated with the maximum process interval time, it is determined that the machine represented by the machine information cannot be used as a candidate machine for the preferred machine, and the machine information is removed from the machine information set. Because the machine associated with the maximum process interval time needs to strictly control the progress of the assigned tasks, even if it is determined as the preferred machine, it is difficult to change the original associated processing task situation, making the machine associated with the maximum process interval time not suitable as a candidate machine for the preferred machine.

[0088] For machines whose machine status information indicates that they are in an abnormal state, if the machine is not associated with the maximum process interval time but the duration of being in the abnormal state exceeds the specified time, the dispatching system can remove the machine information of the machine from the machine information set. If the machine is not associated with the maximum process interval time and the duration of being in neither the idle state nor the working state exceeds the threshold, it will be determined that the corresponding machine will be in a downtime state for a long time, or in a repair state or maintenance state. At this time, the machine itself is not suitable as a candidate machine for the preferred machine.

[0089] The machines represented by the remaining machine information in the machine information set are in a state where the designated processing process can be executed and can be candidates for the preferred machine.

[0090] In some cases, the dispatch system can obtain system card control information from the Abnormality Report Management System (ARM) and / or the Material Review Board (MRB), which includes the machine information of the card-controlled machine. Usually, the card-controlled machine may have certain abnormalities, or it may have just been repaired but the specific situation needs further inspection, etc., making the card-controlled machine unsuitable as a candidate for the preferred machine. The dispatch system can remove the machine information belonging to the system global card-controlled machine from the machine information set.

[0091] After removing the machine information that is not suitable as a candidate machine from the machine information set, the dispatching system can further determine the preferred machine from the machines represented by the machine information included in the machine information set. Specifically, the dispatching system can obtain the parameter values ​​of the machines represented by the machine information in the machine information set relative to multiple quality parameters, so that the preferred machine can be determined based on the parameter values ​​of the multiple quality parameters.

[0092] See also Figure 3 . One embodiment of the present specification also provides a method for dispatching semiconductor processing tasks. The dispatching method can be applied to a dispatching system. The dispatching system has multiple semiconductor processing tasks, and at least some of the multiple semiconductor processing tasks have high quality requirements. For example, a designated high quality requirement label is set for the semiconductor processing tasks with high quality requirements in the dispatching system. Of course, the dispatching system can also directly analyze whether the semiconductor processing task has high quality requirements based on the task information of the semiconductor processing task.

[0093] The dispatching method may include: dispatching a semiconductor processing task with high quality requirements to a preferred machine determined by the machine determination method as described in any of the aforementioned embodiments. The dispatching system can be used to receive a task dispatching request issued by a manufacturing execution system, and the task dispatching request may be accompanied by target machine information representing the machine to which the task is assigned. The dispatching system can compare the target machine information with the machine information of the determined preferred machine to determine whether the machine to which the task is assigned is the preferred machine. When the machine represented by the target machine information is determined to be the preferred machine, the semiconductor processing task with high quality requirements can be dispatched to the preferred machine represented by the target machine information. In this way, the semiconductor processing task with high quality requirements is undertaken by the preferred machine, which can improve the overall quality of the semiconductor chip finally processed to a certain extent.

[0094] In some embodiments, a semiconductor processing task may include multiple task batches. After receiving the semiconductor processing task, the manufacturing execution system may select a task batch from the semiconductor processing task and issue an operation start instruction to the tool control system (TCS), which may notify the preferred tool to start processing and execute the processing work for the selected task batch.

[0095] See also Figure 4 An embodiment of the present specification further provides a work dispatching system, which may include: an acquisition unit, a processing unit, and a determination unit.

[0096] The acquisition unit is used to acquire parameter values ​​of multiple machines respectively corresponding to multiple quality parameters; wherein the multiple machines correspond to designated processing techniques.

[0097] A processing unit is used to standardize the parameter values ​​of multiple quality parameters to obtain standard values ​​corresponding to the multiple quality parameters; wherein the standard values ​​of a specified quality parameter among the multiple quality parameters are divided into multiple standard value sets, the multiple standard value sets include a first standard value set and a second standard value set, the standard values ​​in the second standard value set are greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms.

[0098] The determination unit is used to determine a preferred machine among multiple machines based on standard values ​​of multiple quality parameters; wherein the quality of a process product obtained by performing a specified processing process on the preferred machine is better than the quality of a process product obtained by performing the specified processing process on a non-preferred machine.

[0099] In this embodiment, the functions and effects achieved by the dispatching system can be found in the aforementioned embodiments and will not be described in detail.

[0100] See also Figure 5 The present description embodiment can provide an electronic device, the electronic device comprising: a memory, and one or more processors communicatively connected to the memory; the memory stores instructions executable by one or more processors, the instructions are executed by the one or more processors to enable the one or more processors to implement the method in any of the above embodiments.

[0101] The electronic device may include a processor, a non-volatile storage medium, an internal memory and a communication interface connected by a system bus. The non-volatile storage medium may store an operating system and related computer programs.

[0102] The present specification also provides a computer-readable storage medium, which stores a computer program. The computer program is used to implement the method in any of the above embodiments when executed by a processor.

[0103] The embodiments of this specification also provide a computer program product including instructions, which, when executed by a computer, enables the computer to execute the method in any of the above embodiments.

[0104] The unexpected technical effect of the present invention is that by using multiple quality parameters to evaluate multiple machines, the preferred machine among the multiple machines is obtained, so as to allocate processing tasks with higher processing quality requirements to the preferred machine, thereby meeting the requirements of the processing tasks for high processing quality. Furthermore, in the process of evaluating multiple machines, the parameter values ​​of some quality parameters will be segmented and standardized, so that the standard values ​​of the quality parameters can better reflect the differences between different machines, and the preferred machine can be determined more accurately.

[0105] It is understood that the specific examples herein are only intended to help those skilled in the art better understand the embodiments of the present specification, and are not intended to limit the scope of the present invention. Furthermore, the multiple embodiments described in this specification may be interpreted in comparison with each other.

[0106] It can be understood that in the various implementations of this specification, the size of the sequence number of each process does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation methods of this specification.

[0107] It can be understood that the various embodiments described in this specification can be implemented individually or in combination, and the embodiments of this specification are not limited to this.

[0108] Unless otherwise specified, all technical and scientific terms used in the embodiments of this specification have the same meaning as those generally understood by those skilled in the art of the technical field of this specification. The terms used in this specification are only for the purpose of describing specific embodiments and are not intended to limit the scope of this specification. The term "and / or" used in this specification includes any and all combinations of one or more related listed items. The singular forms of "a", "above", and "the" used in the embodiments of this specification and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0109] It can be understood that the processor of the embodiment of this specification can be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method implementation can be completed by the hardware integrated logic circuit or software instructions in the processor. The above processor can be a general processor, a digital signal processor (Digital Signal Processor, DSP), an application specific integrated circuit (Application Specific Integrated Circuit, ASIC), a field programmable gate array (Field Programmable Gate Array, FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiment of this specification can be implemented or executed. The general processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiment of this specification can be directly embodied as a hardware decoding processor to perform, or the hardware and software modules in the decoding processor are combined and executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0110] It is understood that the memory in the embodiments of this specification may be a volatile memory or a non-volatile memory, or may include both volatile and non-volatile memory. Among them, the non-volatile memory may be a read-only memory (ROM), a programmable read-only memory (programmable ROM, PROM), an erasable programmable read-only memory (erasablePROM, EPROM), an electrically erasable programmable read-only memory (EEPROM) or a flash memory. The volatile memory may be a random access memory (RAM). It should be noted that the memory of the systems and methods described herein is intended to include, but is not limited to, these and any other suitable types of memory.

[0111] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this specification.

[0112] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method implementation methods and will not be repeated here.

[0113] In the several embodiments provided in this specification, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device implementation described above is only schematic, for example, the division of units is only a logical function division, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0114] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0115] In addition, each functional unit in each embodiment of the present specification may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0116] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this specification, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of each implementation method of this specification. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0117] The above is only a specific implementation of this specification, but the protection scope of the present invention is not limited thereto. Any person skilled in the art who is familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in this specification, which should be included in the protection scope of this specification. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A method for determining a machine, characterized in that: The method comprises: Obtaining parameter values ​​of a plurality of machines respectively corresponding to a plurality of quality parameters; wherein the plurality of machines correspond to a specified processing technology; The parameter values ​​of the multiple quality parameters are standardized to obtain standard values ​​corresponding to the multiple quality parameters; wherein the standard values ​​of the specified quality parameters among the multiple quality parameters are divided into multiple standard value sets, the multiple standard value sets include a first standard value set and a second standard value set, the standard values ​​in the second standard value set are greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms; wherein the specified quality parameters include defect count increments, and the parameter values ​​of the multiple quality parameters are standardized to obtain standard values ​​corresponding to the multiple quality parameters, including: for at least some of the quality parameters The parameter values ​​of the specified quality parameters are forward processed to obtain positive values ​​corresponding to at least some quality parameters; wherein the at least some quality parameters include the specified quality parameters; the positive values ​​of the specified quality parameters are sorted to obtain a positive value sequence; a boundary value as a segment boundary is determined in the positive value sequence; wherein the boundary value divides the positive value sequence into a plurality of positive value sets, the plurality of positive value sets include a first positive value set and a second positive value set, and the positive values ​​in the second positive value set are greater than the positive values ​​in the first positive value set; the first positive value set and the second positive value set are respectively standardized to obtain the first standard value set and the second standard value set; Based on the standard values ​​of the multiple quality parameters, a preferred machine is determined from the multiple machines; wherein the quality of the process product obtained by the preferred machine performing the specified processing technology is better than the quality of the process product obtained by the non-preferred machine performing the specified processing technology.

2. The method according to claim 1, characterized in that The step of determining a boundary value as a segment boundary in the forward value sequence comprises: Performing a second-order difference operation on the forward value sequence to obtain a second-order difference value sequence; The positive value corresponding to the difference value greater than the specified threshold in the second-order difference value sequence is used as the boundary value.

3. The method according to claim 1, characterized in that The steps of performing standardization processing on the first positive value set and the second positive value set respectively to obtain the first standard value set and the second standard value set include: Performing standardization processing on the first positive value set based on a first standardization algorithm to obtain a first standard value set corresponding to the first positive value set; The second positive value set is standardized based on a second standardization algorithm to obtain a second standard value set corresponding to the second positive value set; wherein the second standardization algorithm includes using the first standardization algorithm to calculate the result value corresponding to the positive value in the second positive value set, and adding the result value to the last standard value in the first standard value set to obtain the standard value corresponding to the positive value in the second positive value set.

4. The method according to claim 1, characterized in that: The multiple quality parameters include: the defect count increase value, film thickness uniformity, over-specification ratio, quality abnormality handling system trigger rate, normal operation time ratio and maintenance cycle stage score; wherein, the defect count increase value is the increase in the number of defects after the test workpiece is subjected to the specified processing technology by the machine relative to the number of defects before processing, and the film thickness uniformity is used to indicate the uniformity of the film on the process product after the machine is processed; the over-specification ratio is used to indicate the ratio of the number of process products whose parameter values ​​exceed the upper limit or are less than the lower limit among the process products processed by the machine to the total number of process products processed by the machine; the quality abnormality handling system trigger rate is used to indicate the ratio of the number of process products processed by the machine that trigger the quality abnormality handling system to the total number of process products processed by the machine; the normal operation time ratio is used to indicate the ratio of the actual normal operation time of the machine in a specified time period to the specified time period; and the maintenance cycle stage score is used to indicate the stage in the maintenance cycle where the machine is.

5. The method according to claim 4, characterized in that The step of determining a preferred machine from among the plurality of machines based on the standard values ​​of the plurality of quality parameters comprises: Based on the standard value of the defect count increase value and the standard value of the film thickness uniformity, a machine performance value corresponding to each machine is constructed; wherein the machine performance value is used to represent the evaluation of the machine during process testing; The production quality value corresponding to each machine is constructed based on the standard value of the over-specification ratio and the standard value of the quality abnormality processing system trigger rate; wherein the production quality value is used to indicate the quality stability of the machine in executing the specified processing technology; Constructing an operation stability evaluation value corresponding to each machine based on the standard value of the normal operation time ratio and the standard value of the maintenance cycle stage score; wherein the operation stability evaluation value is used to represent the evaluation of the operation stability of the machine; The quality evaluation value is obtained by using the entropy weight method according to the machine performance value, the production quality value and the operation stability evaluation value; wherein the quality evaluation value is used to characterize the quality of the process product obtained by the machine; According to the quality evaluation values ​​representing the quality from high to low, a specified number of machines are determined as the preferred machines.

6. The method according to claim 1, characterized in that The method further comprises: Acquire a machine information set and machine status information corresponding to the specified processing technology; wherein the machine information set includes machine information of multiple machines corresponding to the specified processing technology; For a machine whose machine status information indicates that the machine is in an abnormal state, if the machine information of the machine is associated with a maximum process interval duration, the machine information is removed from the machine information set; wherein the abnormal state includes: downtime state, maintenance state or repair state; For a machine whose machine status information indicates that the machine is in an abnormal state, if the machine information of the machine is not associated with a maximum process interval duration and the duration of being in the abnormal state exceeds a specified duration, the machine information of the machine is removed from the machine information set, and the machine information remaining in the machine information set indicates that the machine is in a state in which the specified processing process can be executed; Correspondingly, the step of obtaining parameter values ​​of the plurality of machines respectively corresponding to the plurality of quality parameters includes: obtaining parameter values ​​of the machines respectively corresponding to the plurality of quality parameters represented by the machine information in the machine information set.

7. A method for dispatching semiconductor processing tasks, characterized in that: The method comprises: Allocate a semiconductor processing task with high quality requirements to a preferred tool determined by the tool determination method according to any one of claims 1 to 6.

8. A work dispatching system, characterized in that: The dispatching system comprises: An acquisition unit, used for acquiring parameter values ​​of a plurality of machines respectively corresponding to a plurality of quality parameters; wherein the plurality of machines correspond to a specified processing technology; a processing unit, configured to perform standardization processing on the parameter values ​​of the multiple quality parameters to obtain standard values ​​corresponding to the multiple quality parameters; wherein the standard values ​​of a specified quality parameter among the multiple quality parameters are divided into multiple standard value sets, the multiple standard value sets include a first standard value set and a second standard value set, the standard values ​​in the second standard value set are greater than the standard values ​​in the first standard value set, and the standard values ​​in the first standard value set and the standard values ​​in the second standard value set are generated using different standardization algorithms; wherein the specified quality parameter includes a defect count increase value, and performing standardization processing on the parameter values ​​of the multiple quality parameters to obtain standard values ​​corresponding to the multiple quality parameters includes: for at least part of The parameter values ​​of the quality parameters are forward processed to obtain positive values ​​corresponding to at least some of the quality parameters; wherein the at least some of the quality parameters include the specified quality parameters; the positive values ​​of the specified quality parameters are sorted to obtain a positive value sequence; a boundary value as a segment boundary is determined in the positive value sequence; wherein the boundary value divides the positive value sequence into a plurality of positive value sets, the plurality of positive value sets include a first positive value set and a second positive value set, and the positive values ​​in the second positive value set are greater than the positive values ​​in the first positive value set; the first positive value set and the second positive value set are respectively standardized to obtain the first standard value set and the second standard value set; A determination unit is used to determine a preferred machine among the multiple machines based on the standard values ​​of the multiple quality parameters; wherein the quality of the process product obtained by the preferred machine performing the specified processing technology is better than the quality of the process product obtained by the non-preferred machine performing the specified processing technology.

9. An electronic device, characterized in that: The electronic device comprises: a memory, and one or more processors communicatively coupled to the memory; The memory stores instructions that can be executed by the one or more processors, and the instructions are executed by the one or more processors to enable the one or more processors to implement the method for determining the machine as described in any one of claims 1 to 6, or to enable the one or more processors to implement the method for dispatching semiconductor processing tasks as described in claim 7.

10. A computer storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the method for determining a machine as described in any one of claims 1 to 6, or implements the method for dispatching semiconductor processing tasks as described in claim 7.