Detection system and method for semiconductor process machine

Abstract

The invention provides a detection system and method for a semiconductor process machine, and particularly relates to the technical field of semiconductor manufacturing, and the system comprises an information obtaining module which is used for obtaining an information table of a to-be-detected machine, sorting each batch of information of the information table based on a processing sequence and grouping the information in sequence based on a statistical period, the category of the batch information comprises necessary inspection and non-necessary inspection; the information clearing module is used for clearing the preorder group corresponding to the target batch information of the detected product batch from the information table if random sampling inspection of any semiconductor product batch corresponding to the information table is completed; and the detection control module is used for determining a detection strategy of the remaining product batch corresponding to the information table based on the ranking of the target batch information in the current group and the category of the post-sequencing batch information in the current group, and the post-sequencing batch information is the batch information ranked behind the target batch information in the current group. According to the invention, the increase of detection machine and labor cost is avoided, and accurate and high-time-efficiency monitoring is carried out on key process machines.

Description

Technical Field

[0001] The present application relates to the field of semiconductor manufacturing technology, and in particular to a detection system and method for a semiconductor process machine. Background Art

[0002] Semiconductor chips and other products are essential components in modern electronic devices. Their quality and reliability have a significant impact on the performance and life of the equipment. Therefore, defect detection and electronic aging experiments on semiconductor products are important links to ensure product quality and troubleshoot abnormal machines. However, due to the wide variety of products on the production line and the complex processes, and the cost of manpower and testing machines, only random inspections can be used to monitor product health. The existing detection method mainly involves limited random inspections of products at process inspection sites to monitor whether the condition of the process machines is normal, such as Figure 1 As shown, product batches 1-3 are respectively transferred to machines B1-B3 after passing through machine A. After passing through machine C, product batch 1 is randomly sampled to achieve quality monitoring of machines A and B1. However, when there are machines to be inspected whose process conditions need to be monitored, such as machine B2, random sampling may lead to the omission of important machine products, and the sampling rate needs to be greatly increased to ensure that the products processed by the machines to be inspected are sampled. However, the above method will greatly increase the cost of manpower and inspection machines, and cannot guarantee that the machines to be inspected have a sufficient sampling rate. Summary of the invention

[0003] The present application provides a detection system and method for a semiconductor process tool, which can ensure the reliability of tool detection and avoid increased detection costs.

[0004] In one aspect, the present application provides a detection system for a semiconductor process tool, the system comprising:

[0005] An information acquisition module is used to acquire an information table of a machine to be inspected, wherein the information table is used to synchronously record batch information of a batch of semiconductor products processed by the machine to be inspected, wherein each batch information of the information table is sorted based on a processing sequence and grouped in sequence based on a statistical period, wherein the categories of the batch information include mandatory inspection and non-mandatory inspection, and the batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product, and each group of the statistical period includes at least one batch information of the mandatory inspection category;

[0006] An information clearing module, configured to clear the preceding group corresponding to the target batch information of the inspected product batch from the information table if any semiconductor product batch corresponding to the information table has completed random sampling inspection;

[0007] The detection control module is used to determine the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, wherein the subsequent batch information is the batch information that is ranked after the target batch information in the current group.

[0008] In a possible implementation manner, the detection control module is specifically used to:

[0009] If there is batch information of a required inspection category in the subsequent batch information, and the target batch information is ranked in the front section of the current group, the current group is retained and the semiconductor product batch of the required inspection category in the current group is inspected.

[0010] In a possible implementation manner, the detection control module is further specifically used for:

[0011] If there is batch information of a required inspection category in the subsequent batch information, and the intra-group ranking of the target batch information is located in the latter section of the current group, each batch information of the current group is cleared from the information table.

[0012] In a possible implementation manner, the detection control module is specifically used to:

[0013] If there is batch information of the mandatory inspection category in the subsequent batch information, based on the intra-group ranking of the target batch information and the intra-group ranking of the batch information of the mandatory inspection category, determine the ranking ratio of the target batch information in the target segment, where the target segment refers to the segment starting from the first batch information of the current group to the batch information of the mandatory inspection category;

[0014] If the ranking ratio does not exceed the preset ratio, the current group is retained and the semiconductor product batches of the required inspection category in the current group are inspected.

[0015] In a possible implementation manner, the detection control module is further specifically used for:

[0016] If the ranking ratio exceeds the preset ratio, each batch of information of the current group is cleared from the information table.

[0017] In a possible implementation manner, the detection control module is specifically used to:

[0018] If there is no batch information of the required inspection category in the subsequent batch information, the current grouping is cleared, the next batch information of the target batch information in the order is taken as the start of the statistical period, and new grouping is performed starting from the next batch information.

[0019] In a possible implementation manner, the system further includes:

[0020] An interval time detection module, used for obtaining the remaining transmission time of the semiconductor product batch, wherein the remaining transmission time is used for indicating the remaining consumable time before the semiconductor product batch is transmitted to the next process node;

[0021] The information category determination module is used to determine the category of the batch information as non-mandatory inspection if the remaining transmission time does not exceed a preset time and / or the semiconductor product batch is non-inspected products.

[0022] In a possible implementation manner, the information category determination module is further used to:

[0023] If the remaining transmission time of multiple semiconductor product batches in the statistical period exceeds the preset time and the semiconductor product batches are inspectable, obtaining batch attribute data of each of the semiconductor product batches;

[0024] A semiconductor product batch whose batch information category is required to be inspected is determined from each of the semiconductor product batches based on the batch attribute data.

[0025] In a possible implementation manner, the batch attribute data includes at least one of the grouping quantity, site distance, estimated transmission time and pre-stored information of the detection program of the semiconductor product batch, the grouping quantity is used to indicate the number of tables of the information table to which the batch information of the semiconductor product batch belongs, each of the groupings corresponds to a machine to be inspected, the site distance is used to indicate the transmission distance between the current position of the semiconductor product batch and the detection site, the estimated transmission time is used to indicate the time required for the semiconductor product batch to be transported from the current position to the detection site, and the pre-stored information of the detection program is used to indicate whether the detection site has pre-stored detection programs for the semiconductor product batch;

[0026] The higher the grouping volume, the shorter the site distance, the shorter the estimated transmission time, or the detection program pre-stored information indicates that it has been pre-stored, the higher the probability that the batch information category is mandatory.

[0027] On the other hand, the present application provides a detection method for a semiconductor process tool, the method comprising:

[0028] Obtaining an information table of the machine to be inspected, the information table being used to synchronously record batch information of a batch of semiconductor products processed by the machine to be inspected, each batch information of the information table being sorted based on a processing sequence and grouped in sequence based on a statistical period, the categories of the batch information including mandatory inspection and non-mandatory inspection, the batch information of the mandatory inspection category indicating that the semiconductor product batch is a mandatory inspection product, and each group of the statistical period including at least one batch information of the mandatory inspection category;

[0029] If any semiconductor product batch corresponding to the information table completes random sampling, clear the preceding group corresponding to the target batch information of the inspected product batch from the information table;

[0030] Based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, the detection strategy for the remaining product batches corresponding to the information table is determined, and the subsequent batch information is the batch information ranked after the target batch information in the current group.

[0031] In a possible implementation manner, the detection strategy for the remaining product batches corresponding to the information table is determined based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, wherein the subsequent batch information is the batch information in the current group that is ranked after the target batch information and includes:

[0032] If there is batch information of a required inspection category in the subsequent batch information, and the target batch information is ranked in the front section of the current group, the current group is retained and the semiconductor product batch of the required inspection category in the current group is inspected.

[0033] In a possible implementation manner, the method further includes:

[0034] If there is batch information of a required inspection category in the subsequent batch information, and the target batch information is ranked in the latter section of the current group, each batch information of each batch information of the current group is cleared from the information table.

[0035] In a possible implementation manner, the detection strategy for the remaining product batches corresponding to the information table is determined based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, wherein the subsequent batch information is the batch information in the current group that is ranked after the target batch information and includes:

[0036] If there is batch information of the mandatory inspection category in the subsequent batch information, based on the intra-group ranking of the target batch information and the intra-group ranking of the batch information of the mandatory inspection category, determine the ranking ratio of the target batch information in the target segment, where the target segment refers to the segment starting from the first batch information of the current group to the batch information of the mandatory inspection category;

[0037] If the ranking ratio does not exceed the preset ratio, the current group is retained and the semiconductor product batches of the required inspection category in the current group are inspected.

[0038] In a possible implementation manner, the method further includes:

[0039] If the ranking ratio exceeds the preset ratio, each batch of information of the current group is cleared from the information table.

[0040] In a possible implementation manner, the method further includes:

[0041] If there is no batch information of the required inspection category in the subsequent batch information, the current grouping is cleared, the next batch information of the target batch information in the order is taken as the start of the statistical period, and new grouping is performed starting from the next batch information.

[0042] In a possible implementation manner, the method for determining the category of the batch information includes:

[0043] Obtaining a remaining transmission time of the semiconductor product batch, where the remaining transmission time is used to indicate a remaining consumable time before the semiconductor product batch is transmitted to a next process node;

[0044] If the remaining transmission time does not exceed the preset time and / or the semiconductor product batch is non-inspection products, it is determined that the category of the batch information is non-mandatory inspection.

[0045] In a possible implementation manner, the method further includes:

[0046] If the remaining transmission time of multiple semiconductor product batches in the statistical period exceeds the preset time and the semiconductor product batches are inspectable, obtaining batch attribute data of each of the semiconductor product batches;

[0047] A semiconductor product batch whose batch information category is required to be inspected is determined from each of the semiconductor product batches based on the batch attribute data.

[0048] In a possible implementation manner, the batch attribute data includes at least one of the grouping quantity, site distance, estimated transmission time and pre-stored information of the detection program of the semiconductor product batch, the grouping quantity is used to indicate the number of tables of the information table to which the batch information of the semiconductor product batch belongs, each of the groupings corresponds to a machine to be inspected, the site distance is used to indicate the transmission distance between the current position of the semiconductor product batch and the detection site, the estimated transmission time is used to indicate the time required for the semiconductor product batch to be transported from the current position to the detection site, and the pre-stored information of the detection program is used to indicate whether the detection site has pre-stored detection programs for the semiconductor product batch;

[0049] The higher the grouping volume, the shorter the site distance, the shorter the estimated transmission time, or the detection program pre-stored information indicates that it has been pre-stored, the higher the probability that the batch information category is mandatory.

[0050] On the other hand, a computer device is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the detection method for a semiconductor process tool as described above.

[0051] On the other hand, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored. The at least one instruction or the at least one program is loaded and executed by a processor to implement the above-mentioned detection method for a semiconductor process tool.

[0052] On the other hand, a server is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the detection method for a semiconductor process tool as described above.

[0053] On the other hand, a terminal is provided, which includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the detection method for a semiconductor process tool as described above.

[0054] On the other hand, a computer program product is provided. The computer program product includes computer instructions. When the computer instructions are executed by a processor, the detection method for a semiconductor process tool as described above is implemented.

[0055] The detection system, method, device, storage medium, server, terminal, and computer program product for a semiconductor process machine provided by the present application have the following technical effects:

[0056] The semiconductor process machine inspection system of the present application obtains an information table of the machine to be inspected, which synchronously records the batch information of the semiconductor product batch processed by the machine to be inspected. The batch information of each batch in the information table is sorted based on the processing sequence and grouped in sequence based on the statistical period. The categories of batch information include mandatory inspection and non-mandatory inspection. The batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product, and the grouping of each statistical period includes at least one batch information of the mandatory inspection category, so as to ensure that the key product marking and inspection of the machine to be inspected are realized in each statistical period, and the machine quality monitoring of the data period is completed; at the same time, if any semiconductor product batch corresponding to the information table is completed To complete random sampling, the information clearing module clears the preceding grouping corresponding to the target batch information of the inspected product batch from the information table, i.e., clears the data of the statistical period before the target batch information, and the detection control module determines the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information in the current group to which it belongs and the category of the subsequent batch information in the current group, and then removes the statistical period for which quality supervision has been achieved based on the "forward clearing" mechanism, thereby ensuring the sampling rate of the machines to be inspected and avoiding redundant detection. There is no need to increase the sampling volume of random sampling to improve the sampling rate of the machines to be inspected, thus avoiding an increase in manpower and machine costs. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present application or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0058] Figure 1 It is a schematic diagram of a process of random batch testing of semiconductor products provided by the prior art;

[0059] Figure 2 It is a schematic diagram of a framework of a detection system for a semiconductor process machine provided in an embodiment of the present application;

[0060] Figure 3 It is a schematic diagram of a line axis of an information table and statistical period grouping provided in an embodiment of the present application;

[0061] Figure 4 It is a schematic diagram of another information table and a line axis of statistical period grouping provided in an embodiment of the present application;

[0062] Figure 5 It is a schematic diagram of another information table and a line axis of statistical period grouping provided in an embodiment of the present application;

[0063] Figure 6 It is a flow chart of a detection method for a semiconductor process machine provided by an embodiment of the present application;

[0064] Figure 7 It is a hardware structure block diagram of an electronic device for a detection method of a semiconductor process machine provided in an embodiment of the present application. DETAILED DESCRIPTION

[0065] 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 ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0066] It should be noted that in the description of the present application, for the following defined terms, unless a different definition is given in the claims or elsewhere in this specification, these definitions should be applied. All numerical values, whether or not explicitly indicated, are defined herein as being modified by the term "about". The term "about" generally refers to a numerical range that a person of ordinary skill in the art would consider to be equivalent to the stated value to produce substantially the same properties, functions, results, etc. A numerical range indicated by a low value and a high value is defined to include all numerical values ​​included in the numerical range and all subranges included in the numerical range.

[0067] It should be noted that the terms "first", "second", etc. in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product or server comprising a series of steps or submodules is not necessarily limited to those steps or submodules clearly listed, but may include other steps or submodules that are not clearly listed or inherent to these processes, methods, products or devices.

[0068] In the embodiments of the present application, the terminal may include physical devices such as a controller, a smart phone, a desktop computer, a tablet computer, a laptop computer, a digital assistant, an augmented reality (AR) / virtual reality (VR) device, an intelligent voice interaction device, and a smart wearable device, and may also include software running in the physical device, such as an application program, etc.; the machine may be any machine used for processing devices in the processing process of semiconductor devices.

[0069] In the embodiments of the present application, the server may be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. Specifically, the server involved above may include physical devices, which may specifically include network communication submodules, processors and memories, etc., and may also include software running in physical devices, which may specifically include applications, etc.

[0070] The following describes a detection system for a semiconductor process machine of the present application. The embodiments of the present application can be applied to the scene of semiconductor manufacturing and can be applied to the detection of any machine in the semiconductor device processing process to locate the problem machine. Please refer to Figure 2 , Figure 2 : is a schematic diagram of a framework of a detection system for a semiconductor process machine provided by an embodiment of the present application. The system may include the following information acquisition module, information clearing module and detection control module:

[0071] The information acquisition module is used to obtain the information table of the machine to be inspected.

[0072] Specifically, the machine to be inspected refers to the processing machine that needs to perform product inspection, such as a key process machine or a machine with frequent problems. A corresponding information table is created and stored for each machine to be inspected, which is used to synchronously record the batch information of the semiconductor product lot processed by the machine to be inspected. The batch information is used to identify the semiconductor product lot, such as a batch barcode.

[0073] Specifically, the categories of batch information include mandatory inspection and non-mandatory inspection, and the batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product. It can be understood that when the semiconductor product batch passes through the machine to be inspected in the processing order, some semiconductor product batches processed by it are selected as key products (key Lot), so that the category of its batch information is marked as mandatory inspection, and then it is used as a mandatory inspection product batch to be transported to the inspection site for defect detection or quality testing, etc., so as to ensure the sampling rate of the machine to be inspected and effectively monitor the health of the machine to be inspected.

[0074] Specifically, each batch of information in the information table is sorted based on the processing sequence and grouped in sequence based on the statistical cycle. The batch information in the information table is sorted from first to last according to the processing sequence, and each statistical cycle group includes at least one batch information of a required inspection category. The statistical cycle can be set based on actual inspection requirements. The statistical cycle can be a preset time period, a preset quantity period, etc. For example, 30 minutes is a statistical cycle, or N valid semiconductor product batches are a statistical cycle, etc. Take one statistical cycle as a group, and group each batch of information in the information table from first to last according to the processing sequence. It can be understood that as the semiconductor product batch passes through the machine to be inspected, its batch information is added to the information table in near real time and combined into the group corresponding to the latest statistical cycle.

[0075] Specifically, at least one key product is selected from each statistical period group, and the category of its batch information is marked as mandatory inspection, so that the semiconductor product batch is transmitted to the matching inspection site for corresponding product inspection. In one example, the statistical period is a preset time period, and a group of batch information is formed every time a preset time period is reached, and a semiconductor product batch is selected as a key product, and the batch information category is marked as mandatory inspection; in another example, the statistical period is a preset quantity period, and a batch information group is formed every time a preset number of valid product batches are passed through the inspection machine, and the batch information of a semiconductor product batch is selected and marked as mandatory inspection category.

[0076] Specifically, in addition to marking key products on the machines to be inspected, random inspections are also carried out on the semiconductor products on the production line for each process machine for semiconductor processing to monitor the processing quality of each machine.

[0077] The information clearing module is used to clear the preceding group corresponding to the target batch information of the inspected product batch from the information table if any semiconductor product batch corresponding to the information table completes random sampling.

[0078] It can be understood that the preceding group refers to other groups that are before the group to which the target batch information belongs in the order of the information table. In the batch manufacturing process of semiconductor products, any product batch of each semiconductor product batch corresponding to the information table may be randomly sampled and sent to the inspection site and completed the inspection before other semiconductor product batches that have passed the goods. Correspondingly, each semiconductor product batch currently recorded in the information table of the machine to be inspected has completed the quality monitoring of the corresponding cycle, that is, the purpose of monitoring the processing health of the machine to be inspected in the corresponding cycle is achieved. Even if there are key products that are processed before the inspected product batch, there is no need for redundant testing. Based on the "forward clearing" logic, the statistical cycles before the statistical cycle to which the above-mentioned randomly sampled inspected product batch belongs are cleared to update the data in the information table, ensuring the inspection sampling rate of the machine to be inspected while avoiding redundant inspection, thereby avoiding increasing the burden on the defect detection machine.

[0079] The detection control module is used to determine the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group.

[0080] Specifically, the subsequent batch information is the batch information that is sorted after the target batch information in the current group, and the remaining product batch is the semiconductor product batch corresponding to the remaining batch information after the previous group is deleted from the information table.

[0081] In summary, the semiconductor process machine inspection system of the present application obtains the information table of the machine to be inspected, which synchronously records the batch information of the semiconductor product batch processed by the machine to be inspected. The batch information of each batch in the information table is sorted based on the processing order and grouped in sequence based on the statistical period. The categories of batch information include mandatory inspection and non-mandatory inspection. The batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product, and the grouping of each statistical period includes at least one batch information of the mandatory inspection category, so as to ensure that the key product marking and inspection of the machine to be inspected are realized in each statistical period, and the machine quality monitoring of the data period is completed; at the same time, if any semiconductor product batch corresponding to the information table After completing the random inspection, the information clearing module clears the preceding grouping corresponding to the target batch information of the inspected product batch from the information table, i.e., clears the data of the statistical period before the target batch information, and the detection control module determines the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, and then removes the statistical period for which quality supervision has been achieved based on the "forward clearing" mechanism, ensuring the sampling rate of the machines to be inspected and avoiding redundant detection. There is no need to increase the sampling volume of random sampling to improve the inspection rate of the machines to be inspected, thus avoiding an increase in manpower and machine costs.

[0082] Based on some or all of the above implementation methods, in some embodiments, the detection control module is specifically used to: if there is no batch information of the must-inspected category in the subsequent batch information, clear the current grouping, take the next batch of information in the sorting of the target batch information as the starting point of the statistical period, and re-group from the next batch of information.

[0083] It is understandable that the statistical cycle corresponding to the inspected product batch may not have ended yet, and the grouping of the statistical cycle has not ended. New batches of semiconductor products will continue to be added to the current grouping until the end of the current statistical cycle. If key products are not screened out from the semiconductor product batches that have been added after the inspected product batches in the current statistical cycle, that is, there is no batch information of the must-inspected category after the target batch information in the current grouping, it means that the next must-inspected product batch has not been added, and there is no need to continue the screening of key products in the current statistical cycle. Clear all batch information that is sorted before the target batch information in the information table, start with the next semiconductor product batch of the inspected product batch in the current statistical cycle, restart a new round of statistical cycle, and start regrouping with the batch information of the next semiconductor product batch, where the next semiconductor product batch is adjacent to the inspected product batch in processing order and later than the inspected product batch. In this way, based on the combination of key product marking and random sampling strategies, if a product in the statistical information table of the machine to be inspected completes the sampling inspection first, and no new key products are added afterwards, not only will the "forward clearing" be performed, but the starting point of the statistical period will be updated at the same time, and the inspection cycle of the next period will be started. This can ensure the effective monitoring of the machine to be inspected and maintain the overall random sampling rate unchanged. At the same time, it can avoid the problem of an increase in defect detection sites caused by too many key products, balance random sampling and key product marking strategies, and improve the reliability and timeliness of monitoring the health of the machine.

[0084] For example, reference Figure 3 In this embodiment, the statistical cycle is taken as a preset number cycle as an example, and the preset number of valid product batches is 4. In each statistical cycle, a key product is screened, that is, a batch information of a must-inspect category is screened. The data axis in the figure records the semiconductor product batch (Lot) based on the processing sequence (that is, the order of goods passing through the machine to be inspected). Lot i Representing batch information, the batch information category of the red marked points is non-mandatory inspection, and the batch information category of the yellow marked points is mandatory inspection. The batch information recorded in the information table includes Lot1-Lot7, group A of statistical period A includes Lot1-Lot4, and the current group B of statistical period B includes Lot5-Lot7, and the batch information of key products is not yet included.

[0085] Assume that when Lot7 is processed, Lot6 is randomly sampled as Lot k And as the sampling product batch, it is transmitted to the testing site in advance to complete the sampling inspection. However, Lot1-Lot5 have not been sampled and the required inspection Lot4 has not arrived at the testing site yet. k and the batch information before it is cleared and replaced with Lot kThe first batch of Lots after that starts a new statistical cycle and continues counting, that is, delete all batch information of statistical cycle A and batch information Lot5-Lot6 of statistical cycle B (push forward and clear to zero), and start counting of statistical cycle C with Lot7 as the starting point of the next statistical cycle.

[0086] Based on some or all of the above implementations, in some embodiments, the detection control module is further specifically used for:

[0087] If there is batch information of the mandatory inspection category in the subsequent batch information, and the ranking of the target batch information in the group is in the front section of the current group, the current group is retained and the semiconductor product batch of the mandatory inspection category in the current group is inspected;

[0088] If there is batch information of the required inspection category in the subsequent batch information, and the intra-group ranking of the target batch information is located in the latter section of the current group, the batch information of the current group is cleared from the information table.

[0089] Specifically, if key products have been screened out in the current statistical period and their batch information categories are marked as mandatory inspection, determine whether to retain the batch information of the current grouping based on the interval in which the target batch information ranks within the group in the current statistical period, so as to flexibly adapt the inspection strategy based on the ranking of the inspected product batches, selectively inspect key products in the current period, balance the sampling rate and the inspection volume of key products, improve the timeliness of important machine monitoring and avoid rising costs of inspection sites.

[0090] Specifically, the front section refers to the grouping section corresponding to the batch information of the front preset proportion of the statistical period, and the back section refers to the grouping section after the front preset proportion of the statistical period. The preset proportion can be, for example, 60% of the number of batch information in the statistical period, etc. It can be understood that the preset proportion can be set based on actual needs and is not limited to the above example. If the ranking of the target batch information in the group is in the front section of the current group, such as in the front 60%, it indicates that the delivery time of the inspected product batch is relatively early and is not enough to represent the overall quality of the current statistical period. By retaining the current group to keep the batch information of the must-inspect category in the remaining batch information, the quality of the machines in the remaining sections of the current statistical period can be further monitored to avoid missed inspections of machine problems. If the ranking of the target batch information in the group is in the back section of the current group, it indicates that the delivery time of the inspected product batch is relatively late, which has characterized the overall quality of the current statistical period. The batch information and the must-inspect mark of the current group are deleted, and key product marking and random sampling are carried out from the next statistical period to reduce the amount of redundant inspections and avoid rising inspection costs.

[0091] For example, reference Figure 4, the statistical cycle is a preset number cycle, the preset ratio is 60%, the preset number of valid product batches is 4, the mandatory inspection batch information of statistical cycle A is Lot4, and the mandatory inspection batch information of statistical cycle B is Lot8. When Lot9 is processed on the machine to be inspected, Lot1~Lot8 have not been transmitted to the inspection site for inspection; then, in one case, if Lot6 is randomly sampled as Lot k If the product batch is transferred to the inspection site in advance as a sample inspection product batch to complete the sampling inspection, the statistical cycle A is deleted based on the forward clearing mechanism, and the mandatory inspection mark of Lot4 is cancelled; it is determined that Lot6 ranks 50% in the group of statistical cycle B and is in the top 60% of the cycle, then the grouping of statistical cycle B is maintained, and the mandatory inspection mark of Lot8 is retained so that it can be inspected accordingly when it passes the inspection site; in another case, if Lot7 is randomly sampled as Lot k And as a sample inspection product batch, it is transmitted to the inspection site in advance to complete the sampling inspection. It is determined that Lot7 ranks 75% in the group of statistical period B and does not belong to the top 60% of the period. Therefore, not only the batch information of statistical period A is cleared and the mandatory inspection mark of Lot4 is cancelled, but also statistical period B is deleted, and the mandatory inspection mark of Lot8 is cancelled. A new round of random sampling and key product marking starts from statistical period C.

[0092] Based on some or all of the above implementations, in some other embodiments, the detection control module is further specifically used for:

[0093] If there is batch information of the mandatory inspection category in the subsequent batch information, the ranking ratio of the target batch information in the target section is determined based on the intra-group ranking of the target batch information and the intra-group ranking of the batch information of the mandatory inspection category;

[0094] If the ranking ratio does not exceed the preset ratio, the current grouping is retained and the semiconductor product batches of the mandatory inspection category in the current grouping are inspected;

[0095] If the ranking ratio exceeds the preset ratio, the batches of information in the current group are cleared from the information table.

[0096] Specifically, the target segment refers to the segment starting from the first batch information of the current group to the batch information of the required inspection category, and the ranking ratio refers to the ratio of the ranking of the target batch information in the target segment to the overall ranking of the target segment, that is, the ratio of the total number of the preceding batch information of the target batch information in the target segment to the total number of batch information in the target segment. In this way, the batch information of the required inspection category in the remaining batch information of the current group is used as a node to determine whether the ranking ratio of the target batch information exceeds the preset ratio, and then selectively inspect the key products in the current cycle to ensure the comprehensiveness of the monitoring of the current cycle and avoid excessive inspection.

[0097] Specifically, if the ranking ratio of the target batch information is within the preset ratio, it indicates that the inspected product batch is too far away from the key products that must be inspected in the current statistical period, and is not sufficient to represent the overall quality of the current statistical period. Retaining the batch information and mandatory inspection mark of the current group can improve the reliability of machine quality monitoring. If the ranking ratio of the target batch information is outside the preset ratio, it indicates that the inspected product batch is close to the key products that must be inspected in the current statistical period, which has characterized the overall quality of the current statistical period. Delete the batch information and mandatory inspection mark of the current group, and start marking and random sampling of key products from the next statistical period to reduce redundant inspections and avoid rising inspection costs.

[0098] For example, reference Figure 5 , the statistical cycle is the preset number cycle, the preset number is 5, the preset ratio is 60%, the preset number of valid product batches is 4, the mandatory inspection batch information of statistical cycle A is Lot4, and the mandatory inspection batch information of statistical cycle B is Lot9. When Lot9 is processed on the machine to be inspected, Lot1~Lot8 have not been transmitted to the inspection site for inspection; then, in one case, if Lot7 is randomly sampled as Lot k And as a sampled product batch, it is transmitted to the testing site in advance to complete the sampling inspection. Then, based on the forward clearing mechanism, the statistical cycle A is deleted, and the mandatory inspection mark of Lot4 is cancelled; the target segment is [Lot6, Lot9], and it is determined that the ranking of Lot7 in the target segment accounts for 50%, which is in the top 60% of the target segment. Then the grouping of statistical cycle B is maintained, and the mandatory inspection mark of Lot9 is retained to perform corresponding inspections when it passes the testing site; in another case, if Lot8 is randomly sampled as Lot k And it is transmitted to the inspection site in advance as a random inspection product batch to complete the random inspection. It is determined that Lot8 ranks 75% in the target segment and does not belong to the top 60% of the target segment. Therefore, not only the batch information of statistical period A is cleared and the mandatory inspection mark of Lot4 is cancelled, but also statistical period B is deleted and the mandatory inspection mark of Lot9 is cancelled. A new round of random inspection and key product marking starts from statistical period C.

[0099] Based on some or all of the above embodiments, in some embodiments, the system also includes an interval duration detection module and an information category determination module: the interval duration detection module is used to obtain the remaining transmission duration of the semiconductor product batch; the information category determination module is used to determine the category of the batch information as non-mandatory inspection if the remaining transmission duration does not exceed the preset duration and / or the semiconductor product batch is non-inspected.

[0100] Specifically, the remaining transmission time is used to indicate the remaining consumable time before the semiconductor product batch is transmitted to the next process node. It can be understood that, according to the process characteristics, there is a time limit between two adjacent processing nodes, and the semiconductor product batch needs to be transmitted from the previous processing node to the next adjacent node within the limited interval time, otherwise it will cause product defects. In view of this, when screening key products to mark batch information as a mandatory inspection category, semiconductor product batches with longer remaining transmission times are given priority, and product batches with a remaining transmission time lower than the preset time are avoided, so as to avoid product inspection causing processing timeouts, thereby reducing product defect rates. In addition, due to various reasons, there may be some semiconductor product batches that do not require defect detection, and accordingly, they will not be selected as key products, and their batch information categories will be marked as non-mandatory inspections.

[0101] Specifically, the preset duration can be set based on actual detection requirements, such as the set interval time, the detection site defect detection duration and the estimated transmission duration, and no specific numerical value is limited here.

[0102] In some cases, if the current statistical period reaches a preset time period or the number of product batches that have passed through the machine to be inspected reaches a preset number, but the remaining transmission time of each semiconductor product batch in the current statistical period is lower than the preset time, then the next batch of semiconductor product batches is preferably selected for remaining transmission time evaluation. If it exceeds the preset time, the category of the batch information is marked as must-inspect, and the batch information is used as the last element in the current grouping; if it does not exceed, continue to evaluate the next semiconductor product batch, and so on, until the key product is determined, and the batch information of the key product is used as the last element in the grouping of the current statistical period.

[0103] In some embodiments, the information category determination module is also used to obtain batch attribute data of each semiconductor product batch if the remaining transmission time of multiple semiconductor product batches in the statistical period exceeds a preset time and they are inspectable products; and determine the semiconductor product batches whose batch information category is a must-inspection batch from each semiconductor product batch based on the batch attribute data.

[0104] Understandably, there may be multiple semiconductor product batches that meet the time conditions in the same statistical period, and their number may exceed the rated number N of key products to be screened in each statistical period. In this case, the priority of each semiconductor product batch to be inspected is determined according to the batch attribute data, and the top N semiconductor product batches with higher priority to be inspected are selected as key products and marked as mandatory inspection categories, so that the inspected product batches are more representative of quality and the reliability of machine inspection is further improved. N is a positive integer greater than or equal to 1, preferably 1.

[0105] In some embodiments, the batch attribute data includes at least one of the grouping quantity, site distance, estimated transmission time and pre-stored information of the inspection program of the semiconductor product batch. Specifically, the same semiconductor product batch may pass through multiple machines to be inspected and correspond to the statistical cycle of more than one machine to be inspected, that is, it is recorded in the information tables of different machines to be inspected. The grouping quantity is used to indicate the number of information tables to which the batch information of the semiconductor product batch belongs. Each information table corresponds to a machine to be inspected, that is, the information table of the machines to be inspected in which the batch information of the semiconductor product batch is currently recorded. The site distance is used to indicate the transmission distance between the current position of the semiconductor product batch and the inspection site. The estimated transmission time is used to indicate the time required for the semiconductor product batch to be transported from the current position to the inspection site. The pre-stored information of the inspection program is used to indicate whether the inspection site has pre-stored inspection programs for the semiconductor product batch, and the inspection program is used to indicate the defect detection operation of the inspection site on the semiconductor product batch.

[0106] Accordingly, the higher the grouping volume, the shorter the site distance, the shorter the estimated transmission time, or the detection program pre-stored information indicates that it has been pre-stored, the higher the inspection priority of the semiconductor product batch, and the higher the probability that the batch information category is mandatory inspection. Conversely, the lower the inspection priority of the semiconductor product batch, the higher the probability that the batch information category is non-mandatory inspection. In this way, priority is given to product batches that have established programs at defect detection sites, are closer to the matching detection sites, have shorter transmission times to the detection sites, and correspond to multiple statistical cycles, taking into account the reliability and information volume of key product screening and improving the quality of machine monitoring.

[0107] In summary, compared with the prior art, the detection system of the present application only needs to select key products of the machine to be inspected and conduct normal random inspections. It can automatically realize the health monitoring of the machine to be inspected without changing the random sampling rate. After random sampling, it avoids redundant inspection of key products in each cycle that has been counted, avoids adding defect detection machines and manpower configuration, can greatly save costs, and does not affect the overall detection rate, ensuring the timeliness of abnormality detection.

[0108] The present application also provides a detection method for a semiconductor process machine, such as Figure 6 As shown, Figure 6 A flow chart of a detection method for a semiconductor process machine provided by an embodiment of the present application is shown. This specification provides method operation steps such as the embodiment or flow chart, but may include more or fewer operation steps based on conventional or non-creative labor. The order of steps listed in the embodiment is only one way of executing the steps among many orders, and does not represent the only order of execution. When the actual system or server product is executed, it can be executed in the order of the method shown in the embodiment or the accompanying drawings or in parallel (for example, in a parallel processor or multi-threaded processing environment). Specifically, as Figure 2As shown, the method may include the following steps S201-S205:

[0109] S201: Acquire an information table of the machine to be inspected, the information table is used to synchronously record batch information of semiconductor product batches processed by the machine to be inspected, each batch information in the information table is sorted based on the processing sequence and grouped in sequence based on the statistical period, the categories of batch information include mandatory inspection and non-mandatory inspection, the batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product, and each statistical period group includes at least one batch information of the mandatory inspection category;

[0110] S203: If any semiconductor product batch corresponding to the information table has completed random sampling, clear the preceding group corresponding to the target batch information of the inspected product batch from the information table;

[0111] S205: Determine the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information within the current group and the category of the subsequent batch information in the current group. The subsequent batch information is the batch information ranked after the target batch information in the current group.

[0112] In some embodiments, S205 may include S301: if there is batch information of a must-inspection category in the subsequent batch information, and the target batch information is ranked in the front section of the current group, retain the current group and inspect the semiconductor product batch of the must-inspection category in the current group.

[0113] In some embodiments, S205 may further include S302: if there is batch information of a required inspection category in the subsequent batch information, and the intra-group ranking of the target batch information is located in the latter section of the current group, clearing each batch information of the current group from the information table.

[0114] In some embodiments, S205 may further include:

[0115] S401: If there is batch information of the mandatory inspection category in the subsequent batch information, determine the ranking ratio of the target batch information in the target segment based on the intra-group ranking of the target batch information and the intra-group ranking of the batch information of the mandatory inspection category. The target segment refers to the segment starting from the first batch information of the current group to the batch information of the mandatory inspection category.

[0116] S402: If the ranking ratio does not exceed the preset ratio, the current group is retained and the semiconductor product batches of the mandatory inspection category in the current group are inspected.

[0117] In some embodiments, S205 may further include S403: if the ranking ratio exceeds a preset ratio, clearing each batch of information of the current group from the information table.

[0118] In some embodiments, S205 may further include S501: if there is no batch information of the required inspection category in the subsequent batch information, clear the current grouping, take the next batch information of the target batch information in the sorting as the start of the statistical period, and regroup from the next batch information.

[0119] In some embodiments, the method for determining the category of batch information includes S601-S603:

[0120] S601: Obtain the remaining transmission time of the semiconductor product batch, where the remaining transmission time is used to indicate the remaining consumable time before the semiconductor product batch is transmitted to the next process node;

[0121] S603: If the remaining transmission time does not exceed the preset time and / or the semiconductor product batch is a non-inspection product, determine the category of the batch information as non-mandatory inspection.

[0122] In some embodiments, the method for determining the category of batch information further includes S605-S607:

[0123] S605: If the remaining transmission time of multiple semiconductor product batches in the statistical period exceeds the preset time and the semiconductor product batches are inspectable, obtain batch attribute data of each semiconductor product batch;

[0124] S607: Determine semiconductor product batches whose batch information categories are required to be inspected from among the semiconductor product batches based on the batch attribute data.

[0125] In some embodiments, the batch attribute data includes at least one of the grouping quantity, site distance, estimated transmission time and pre-stored information of the detection program of the semiconductor product batch, the grouping quantity is used to indicate the number of tables of the information table to which the batch information of the semiconductor product batch belongs, each information table corresponds to a machine to be inspected, the site distance is used to indicate the transmission distance between the current position of the semiconductor product batch and the detection site, the estimated transmission time is used to indicate the time required for the semiconductor product batch to be transported from the current position to the detection site, and the pre-stored information of the detection program is used to indicate whether the detection site has pre-stored detection programs for the semiconductor product batch;

[0126] The higher the grouping volume, the shorter the site distance, the shorter the estimated transmission time, or the detection program pre-stored information indicates that it has been pre-stored, the higher the probability that the batch information category is mandatory inspection.

[0127] It should be noted that the above system embodiment and method embodiment are based on the same implementation method.

[0128] An embodiment of the present application provides a detection device for a semiconductor process machine, which may be a terminal or a server, and includes a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement a detection method for a semiconductor process machine as provided in the above method embodiment.

[0129] The memory can be used to store software programs and modules. The processor executes various functional applications and is used for the detection of semiconductor process machines by running the software programs and modules stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, application programs required for functions, etc.; the data storage area can store data created according to the use of the device, etc. In addition, the memory can include a high-speed random access memory and can also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device. Accordingly, the memory can also include a memory controller to provide the processor with access to the memory.

[0130] The method embodiments provided in the embodiments of the present application can be executed in electronic devices such as mobile terminals, computer terminals, servers or similar computing devices. Figure 7 1 is a hardware structure block diagram of an electronic device for a detection method for a semiconductor process machine provided in an embodiment of the present application. Figure 7 As shown, the electronic device 900 may have relatively large differences due to different configurations or performances, and may include one or more central processing units (CPU) 910 (the processor 910 may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 930 for storing data, and one or more storage media 920 (such as one or more mass storage devices) for storing application programs 923 or data 922. Among them, the memory 930 and the storage medium 920 can be short-term storage or permanent storage. The program stored in the storage medium 920 may include one or more modules, each of which may include a series of instruction operations in the electronic device. Furthermore, the central processing unit 910 can be configured to communicate with the storage medium 920 and execute a series of instruction operations in the storage medium 920 on the electronic device 900. The electronic device 900 may also include one or more power supplies 960, one or more wired or wireless network interfaces 950, one or more input and output interfaces 940, and / or, one or more operating systems 921, such as Windows Server TM , Mac OS X TM , Unix TM , LinuxTM, FreeBSDTM, etc.

[0131] The input / output interface 940 may be used to receive or send data via a network. The specific example of the network may include a wireless network provided by a communication provider of the electronic device 900. In one example, the input / output interface 940 includes a network adapter (Network Interface Controller, NIC), which may be connected to other network devices via a base station so as to communicate with the Internet. In one example, the input / output interface 940 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0132] It can be understood by those skilled in the art that Figure 7 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 7 More or fewer components as shown, or with Figure 7 Different configurations are shown.

[0133] An embodiment of the present application also provides a computer-readable storage medium, which can be set in an electronic device to store at least one instruction or at least one program related to a detection method for a semiconductor process tool in an implementation method embodiment. The at least one instruction or the at least one program is loaded and executed by the processor to implement the detection method for a semiconductor process tool provided in the above-mentioned method embodiment.

[0134] Optionally, in this embodiment, the storage medium may be located in at least one of the multiple network servers of the computer network. Optionally, in this embodiment, the storage medium may include, but is not limited to, various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk, or an optical disk.

[0135] According to one aspect of the present application, a computer program product or a computer program is provided, the computer program product or the computer program comprising computer instructions, the computer instructions being stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the methods provided in the above-mentioned various optional implementations.

[0136] It can be seen from the embodiments of the detection system, device, equipment, server, terminal, storage medium and program product for semiconductor process machines provided by the present application that the semiconductor process machine detection system of the present application obtains an information table of the machine to be inspected, which synchronously records the batch information of the semiconductor product batch processed by the machine to be inspected. The batch information of each batch in the information table is sorted based on the processing sequence and grouped in sequence based on the statistical period. The categories of batch information include mandatory inspection and non-mandatory inspection. The batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product, and the grouping of each statistical period includes at least one batch information of the mandatory inspection category, so as to ensure that the key product marking and inspection of the machine to be inspected are realized in each statistical period, and the data cycle is completed. Machine quality monitoring; at the same time, if any semiconductor product batch corresponding to the information table completes random sampling, the preceding group corresponding to the target batch information of the inspected product batch is cleared from the information table, and the detection control module determines the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information in the current group and the category of the subsequent batch information in the current group. The subsequent batch information is the batch information that is sorted after the target batch information in the current group, and then based on the "forward clearing" mechanism, the statistical cycle of the achieved quality monitoring is removed to ensure the sampling rate of the machine to be inspected and avoid redundant detection. There is no need to increase the sampling volume of random sampling to improve the inspection rate of the machine to be inspected, thereby avoiding an increase in manpower and machine costs.

[0137] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0138] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0139] A person skilled in the art will understand that all or part of the steps to implement the above embodiments may be accomplished by hardware, or may be accomplished by instructing the relevant hardware through a program, and the program may be stored in a computer-readable storage medium, and the above-mentioned storage medium may be a read-only memory, a disk or an optical disk, etc.

[0140] The above are only preferred embodiments of the present application and are not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A detection system for a semiconductor process machine, characterized in that: The system comprises: An information acquisition module is used to acquire an information table of a machine to be inspected, wherein the information table is used to synchronously record batch information of a batch of semiconductor products processed by the machine to be inspected, wherein each batch information of the information table is sorted based on a processing sequence and grouped in sequence based on a statistical period, wherein the categories of the batch information include mandatory inspection and non-mandatory inspection, and the batch information of the mandatory inspection category indicates that the semiconductor product batch is a mandatory inspection product, and each group of the statistical period includes at least one batch information of the mandatory inspection category; An information clearing module, configured to clear the preceding group corresponding to the target batch information of the inspected product batch from the information table if any semiconductor product batch corresponding to the information table has completed random sampling inspection; The detection control module is used to determine the detection strategy for the remaining product batches corresponding to the information table based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, wherein the subsequent batch information is the batch information that is ranked after the target batch information in the current group.

2. The system according to claim 1, characterized in that The detection control module is specifically used for: If there is batch information of a required inspection category in the subsequent batch information, and the target batch information is ranked in the front section of the current group, the current group is retained and the semiconductor product batch of the required inspection category in the current group is inspected.

3. The system according to claim 2, characterized in that The detection control module is also specifically used for: If there is batch information of a required inspection category in the subsequent batch information, and the intra-group ranking of the target batch information is located in the latter section of the current group, each batch information of the current group is cleared from the information table.

4. The system according to claim 1, characterized in that The detection control module is specifically used for: If there is batch information of the mandatory inspection category in the subsequent batch information, based on the intra-group ranking of the target batch information and the intra-group ranking of the batch information of the mandatory inspection category, determine the ranking ratio of the target batch information in the target segment, where the target segment refers to the segment starting from the first batch information of the current group to the batch information of the mandatory inspection category; If the ranking ratio does not exceed the preset ratio, the current group is retained and the semiconductor product batches of the required inspection category in the current group are inspected.

5. The system according to claim 4, characterized in that The detection control module is also specifically used for: If the ranking ratio exceeds the preset ratio, each batch of information of the current group is cleared from the information table.

6. The system according to claim 2, characterized in that The detection control module is specifically used for: If there is no batch information of the required inspection category in the subsequent batch information, the current grouping is cleared, the next batch information of the target batch information in the order is taken as the start of the statistical period, and new grouping is performed starting from the next batch information.

7. The system according to any one of claims 1 to 6, characterized in that: The system further comprises: An interval time detection module, used for obtaining the remaining transmission time of the semiconductor product batch, wherein the remaining transmission time is used for indicating the remaining consumable time before the semiconductor product batch is transmitted to the next process node; The information category determination module is used to determine the category of the batch information as non-mandatory inspection if the remaining transmission time does not exceed a preset time and / or the semiconductor product batch is non-inspected products.

8. The system according to claim 7, characterized in that The information category determination module is also used for: If the remaining transmission time of multiple semiconductor product batches in the statistical period exceeds the preset time and the semiconductor product batches are inspectable, obtaining batch attribute data of each of the semiconductor product batches; A semiconductor product batch whose batch information category is required to be inspected is determined from each of the semiconductor product batches based on the batch attribute data.

9. The system according to claim 8, characterized in that The batch attribute data includes at least one of the grouping quantity, site distance, estimated transmission time and pre-stored information of the semiconductor product batch, the grouping quantity is used to indicate the number of tables of the information table to which the batch information of the semiconductor product batch belongs, each of the grouping corresponds to a machine to be inspected, the site distance is used to indicate the transmission distance between the current position of the semiconductor product batch and the inspection site, the estimated transmission time is used to indicate the time required for the semiconductor product batch to be transported from the current position to the inspection site, and the pre-stored information of the inspection program is used to indicate whether the inspection site has pre-stored inspection programs for the semiconductor product batch; The higher the grouping volume, the shorter the site distance, the shorter the estimated transmission time, or the detection program pre-stored information indicates that it has been pre-stored, the higher the probability that the batch information category is mandatory.

10. A detection method for a semiconductor process tool, applied to a detection system for a semiconductor process tool, characterized in that: The method comprises: Obtaining an information table of the machine to be inspected, the information table being used to synchronously record batch information of a batch of semiconductor products processed by the machine to be inspected, each batch information of the information table being sorted based on a processing sequence and grouped in sequence based on a statistical period, the categories of the batch information including mandatory inspection and non-mandatory inspection, the batch information of the mandatory inspection category indicating that the semiconductor product batch is a mandatory inspection product, and each group of the statistical period including at least one batch information of the mandatory inspection category; If any semiconductor product batch corresponding to the information table completes random sampling, clear the preceding group corresponding to the target batch information of the inspected product batch from the information table; Based on the ranking of the target batch information within the current group to which it belongs and the category of the subsequent batch information in the current group, the detection strategy for the remaining product batches corresponding to the information table is determined, and the subsequent batch information is the batch information ranked after the target batch information in the current group.

Images