Anomaly detection method, semiconductor detection device and semiconductor process device

Abstract

Provided in the present disclosure are an anomaly detection method, a semiconductor detection device and a semiconductor process device. The anomaly detection method comprises: in response to a detection instruction for a process file corresponding to a target device module, parsing target information comprised in the process file, wherein the target information comprises a retention duration of a processed object in the target device module; and on the basis of the target information and a preset retention threshold, determining whether there is a retention anomaly in the target device module. In this way, possible preparation anomalies and the positions where the anomalies occur can be promptly and quickly detected in a semiconductor process, and compared with a manual check, the detection time is greatly shortened, and the detection efficiency and the detection accuracy are improved, thereby providing a guarantee for improving the product quality and the product preparation efficiency.

Description

Abnormality detection method, semiconductor detection device and semiconductor process equipment TECHNICAL FIELD

[0001] The present application relates to the technical field of semiconductor preparation, in particular to an abnormality detection method, a semiconductor detection device and a semiconductor process equipment. BACKGROUND

[0002] With the continuous progress of scientific and technological productivity, the informatization and intelligentization of the whole society are becoming higher and higher, and the demand for semiconductors is becoming more and more vigorous. Among them, in the process of semiconductor preparation, timely detection of abnormal problems on the production line is of great significance to improve the preparation efficiency and product quality of semiconductors. SUMMARY

[0003] Therefore, the present application is committed to providing an abnormality detection method, a semiconductor detection device and a semiconductor process equipment, which can timely and quickly detect abnormalities in the semiconductor process, and improve product quality and product preparation efficiency.

[0004] A first aspect of the present application provides an abnormality detection method applied to a semiconductor process equipment, wherein the semiconductor process equipment has a plurality of device modules; the method comprises:

[0005] In response to a detection instruction for a process file corresponding to a target device module, target information included in the process file is parsed, the target information including a residence time length of a processing object in the target device module, the residence time length being used to represent a non-process processing time length of the processing object staying at the target device module, and the process file being used to record process information of the processing object in the target device module in a process of the target device module on the processing object;

[0006] Based on the target information and a preset residence threshold, it is determined whether the target device module has a residence abnormality.

[0007] In some embodiments, the determination process of the target device module comprises:

[0008] In response to a first user operation on an interactive interface, a device type to which the first user operation is directed is obtained;

[0009] According to the device type, a corresponding device module list is determined, and the device module list is displayed based on the interactive interface;

[0010] At least one target device module determined by the user based on the device module list displayed by the interactive interface is obtained; the target device module includes one device module or a group of device modules in the device module list; the group of device modules includes a plurality of mutually associated device modules.

[0011] In some embodiments, the determination process of the target equipment module comprises:

[0012] In response to a second user operation on the interactive interface, obtaining a device type and a detection time period to which the second user operation is directed;

[0013] In the process recorded in the process file corresponding to the device type, each equipment module corresponding to the process in the detection time period is determined as each target equipment module.

[0014] In some embodiments, the target information included in the process file comprises:

[0015] If the target equipment module is one equipment module, the residence time of the at least one processing object is obtained from the process file for the target equipment module;

[0016] If the target equipment module is a group of equipment modules, the residence time of the at least one processing object is obtained from the process file for each equipment module in the target equipment module, and the residence time of each processing object in each equipment module is summed up to obtain the residence time of each processing object in the target equipment module.

[0017] In some embodiments, the residence time of the at least one processing object comprises:

[0018] Based on the user-confirmed detection time period, the total time of the at least one processing object in the current equipment module is obtained from the process data corresponding to the device type, and the process time corresponding to the current equipment module is obtained; the total time is the time period between the processing object entering the current equipment module and leaving the current equipment module; the process time is the actual time period of the processing object experiencing process in the current equipment module;

[0019] The difference between the total time of each processing object in the current equipment module and the process time is determined as the residence time of each processing object in the current equipment module.

[0020] In some embodiments, the determination of whether the target equipment module has a residence abnormality based on the target information and a preset residence threshold comprises:

[0021] If the residence time of at least one processing object in the target equipment module is greater than the preset residence threshold, it is determined that the target equipment module has a residence abnormality; otherwise, it is determined that the target equipment module does not have a residence abnormality.

[0022] In some embodiments, after determining whether the target device module has the stagnation anomaly, the method further comprises:

[0023] If the target device module has the stagnation anomaly, a prompt information is sent; the prompt information is used to prompt that the target device module has the stagnation anomaly.

[0024] In some embodiments, the sending of the prompt information comprises:

[0025] storing the stagnation duration of the processing object in the target device module into a target file in a preset format, and marking the stagnation duration of which the stagnation anomaly is determined;

[0026] storing the target file into a preset address.

[0027] In some embodiments, the target device module comprises a plurality of;

[0028] Before the parsing of the target information included in the process file, the method further comprises:

[0029] determining threads consistent with the number of the target device modules;

[0030] The parsing of the target information included in the process file in response to the detection instruction for the process file corresponding to the target device module comprises:

[0031] The parsing of each target information included in the process file based on each thread in response to the detection instruction for the process file corresponding to the target device module.

[0032] The second aspect of the present application provides a semiconductor process detection device, comprising:

[0033] a processor, and a memory connected with the processor;

[0034] The memory is used to store a computer program;

[0035] The processor is used to call and execute the computer program in the memory, so as to execute the anomaly detection method as described in the first aspect of the present application.

[0036] The third aspect of the present application provides a semiconductor process device, comprising a plurality of device modules, and the semiconductor process detection device as described in the second aspect of the present application.

[0037] In the scheme of the present application, the abnormality detection method can be applied to a semiconductor process equipment having a plurality of equipment modules. In implementation, in response to a detection instruction for a process file corresponding to a target equipment module, target information included in the process file is parsed to provide information support for abnormality detection; the target information can include a residence time length of a processing object in the target equipment module; the residence time length can be used to represent a non-process processing time length of the processing object staying at the target equipment module; the process file is used to record process information of the processing object in the target equipment module in a process procedure of the processing object in the target equipment module; and then, based on the target information and a preset residence threshold, it is determined whether the target equipment module has a residence abnormality. In this way, based on the detection instruction and the preset residence threshold, automatic parsing of the target information and automatic detection of whether the target equipment module has a residence abnormality can be implemented, and compared with manual inspection, in the semiconductor process, possible preparation abnormality and a position of abnormality occurrence can be found more timely, quickly and accurately, the detection time is greatly saved, the detection efficiency and detection accuracy are improved, and a guarantee for improving product quality and product preparation efficiency is provided. BRIEF DESCRIPTION OF DRAWINGS

[0038] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained without creative labor on the basis of these drawings.

[0039] FIG. 1 is a structural schematic diagram of a semiconductor process equipment according to an embodiment of the present application.

[0040] FIG. 2 is a flow schematic diagram of an abnormality detection method according to an embodiment of the present application.

[0041] FIG. 3 is a flow schematic diagram of an abnormality detection method according to another embodiment of the present application.

[0042] FIG. 4 is a flow schematic diagram of an abnormality detection method according to another embodiment of the present application.

[0043] FIG. 5 is a structural schematic diagram of a semiconductor process equipment according to another embodiment of the present application.

[0044] FIG. 6 is a structural schematic diagram of a computing device according to an embodiment of the present application. DETAILED DESCRIPTION

[0045] Unless otherwise defined, technical terms or scientific terms used in the embodiments of the present specification shall have the meanings as understood by a person of ordinary skill in the art to which the embodiments of the present specification belong. The terms "first", "second", and similar terms used in the embodiments of the present specification do not denote any order, quantity, or importance, but are used to avoid confusion between the components.

[0046] Unless otherwise required by context, "plurality" in the specification means "at least two", "comprising" is to be interpreted as open, inclusive, meaning "including, but not limited to". In the description of the specification, the terms "one embodiment", "some embodiments", "exemplary embodiments", "example", "specific example" or "some examples" are intended to mean that the specific feature, structure, material or characteristic associated with that embodiment or example is included in at least one embodiment or example of the specification. The illustrative representation of the above terms does not necessarily mean the same embodiment or example.

[0047] The technical solutions in the embodiments of the present specification will be described clearly and completely in the following with reference to the drawings in the embodiments of the present specification. Obviously, the described embodiments are only part of the embodiments of the present specification, not all. Based on the embodiments in the present specification, all other embodiments obtained by a person of ordinary skill in the art without making creative efforts fall within the scope of protection of the present specification.

[0048] Referring to FIG. 1, taking a cluster tool as an example, FIG. 1 shows a structural schematic diagram of a semiconductor process equipment, which can have a plurality of equipment modules, including a first robot 10, a wafer loading and unloading station 21, a calibration module 22, a cooling disc 23, and a plurality of process chambers 11, etc.

[0049] Each wafer loading and unloading station 21 can place a wafer cassette, and each wafer cassette can place at least one wafer.

[0050] The calibration module 22 can include a slot, and the calibration module 22 can calibrate the wafer placed in the slot.

[0051] The process chamber 11 (Processing Module) has a plurality of slots, each of which can place a wafer for processing.

[0052] The cooling disc 23 (Cooler) is used to cool the wafer after processing.

[0053] The first robot 10 can be a double-arm robot, the two arms of the double-arm robot can be fixed at 180°, each arm has a slot, each slot can place a wafer, generally, the two arms cannot simultaneously perform the wafer taking and placing operation; the first robot 10 is responsible for transporting wafers between multiple process chambers 11.

[0054] In addition, in some embodiments, the semiconductor process equipment can further include a load lock chamber and a second robot, etc.; the load lock chamber can have two slots, each slot can place a wafer, the load lock chamber can be switched between an atmospheric state and a vacuum state, and when the load lock chamber is switched to the atmospheric state, the wafer on the second robot side can be sent into the load lock chamber; when the load lock chamber is switched to the vacuum state, the wafer on the first robot side can be sent into the load lock chamber. The second robot can be a single-arm robot, the second robot can have one slot, and the slot can place a wafer; the second robot can be responsible for transporting wafers between the wafer loading and unloading site 21, the calibration module 22 and the load lock chamber.

[0055] The process path of the wafer can include multiple process nodes and process time required by each process node that the wafer passes through in the semiconductor process equipment, which can be specifically formulated by process personnel according to the wafer process requirements and can be flexibly changed. For example, the wafer process path can include: wafer loading and unloading site -> second robot (3 seconds) -> calibration module (1 second) -> second robot (3 seconds) -> load lock chamber (3 seconds) -> first robot (3 seconds) -> first process chamber (60 seconds) -> first robot (3 seconds) -> second process chamber (120 seconds) -> first robot (3 seconds) -> third process chamber (60 seconds) -> first robot (3 seconds) -> fourth process chamber (60 seconds) -> first robot (3 seconds) -> load lock chamber (3 seconds) -> second robot (3 seconds) -> cooling disc (1 second) -> wafer loading and unloading site, each step can be called a process node, each process node has a time consumption, and the time length marked in the bracket can be the time length (i.e., process time) required by the process node.

[0056] In implementation, the semiconductor process equipment processes the wafer based on the process path, and the process information performed in each equipment module in the process is recorded in a process file for users (such as process personnel) to view.

[0057] The inventors have found that, due to the influence of semiconductor process equipment and preparation processes, wafers will have a residence time in each equipment module during the semiconductor manufacturing process. The length of the residence time can represent the efficiency of the semiconductor process equipment and provide a reference basis for abnormalities on the production line. In the current semiconductor industry, only when the semiconductor process equipment is abnormal, manual detection is used to calculate the residence time of the wafer in each equipment module from the process data recorded in the process file to further determine whether the corresponding equipment module caused the abnormality of the semiconductor process equipment.

[0058] For example, after determining that the semiconductor process equipment is down, the process personnel will usually analyze the alarm record to determine whether the cause of the down of the semiconductor process equipment is the residence time of a certain process node. Or, after determining that the semiconductor process equipment is down, the process personnel will determine a time range based on the alarm record, and then based on the time range, the process data of the related equipment module is preliminarily located and extracted from a large amount of process data recorded in the process file to check whether there is an abnormal residence time, so as to locate the equipment module with abnormal residence time. Or, after the semiconductor process equipment appears a down alarm, the process personnel manually screen the process data before the down, and export it to an Excel table. By operating the table, the transmission data is determined and analyzed piece by piece, and the residence time of each equipment module is manually calculated to determine the equipment module with abnormal residence time.

[0059] However, this manual detection and post-mortem approach not only requires a lot of manpower, but also is inefficient and has a high error rate, which cannot meet the rapid development of process requirements. Moreover, since human operation of the host computer is not allowed during the operation of the current semiconductor process equipment, real-time monitoring of the residence time corresponding to each equipment module in the semiconductor process equipment cannot be achieved, that is, abnormal problems cannot be discovered in time.

[0060] Therefore, an embodiment of the present application provides an abnormality detection method, which can be applied to a semiconductor process equipment having a plurality of equipment modules. As shown in FIG. 2, the abnormality detection method can at least include the following steps:

[0061] S201, in response to a detection instruction for a target equipment module corresponding process file, analyzing target information included in the process file, the target information including a residence time of a processing object in the target equipment module, the residence time being used to represent a non-process processing time of the processing object staying in the target equipment module, and the process file being used to record process information of the processing object in the target equipment module in a process of the target equipment module to the processing object.

[0062] The processing object can be a wafer or other object that needs to be processed in a semiconductor process equipment.

[0063] Specifically, the detection instruction for the process file corresponding to the target equipment module can be generated in response to the process file corresponding to the target equipment module recording process information of the processing object in the target equipment module, or can be a detection instruction for the process file corresponding to the target equipment module generated in response to operation information of the user (such as a process personnel) based on the interactive interface.

[0064] The detection instruction generated in response to the process file corresponding to the target equipment module recording process information of the processing object in the target equipment module refers to that in the semiconductor process, once it is detected that the process file records the residence time of the processing object at the target equipment module, a detection instruction for the process file corresponding to the target equipment module can be generated. In this way, real-time monitoring of each target equipment module in the process can be realized, which provides a basis and guarantee for timely and rapid discovery of abnormalities in the semiconductor process.

[0065] The detection instruction for the process file corresponding to the target equipment module generated in response to the operation information of the user based on the interactive interface refers to a detection instruction issued based on the interactive interface when the user has a detection requirement. In this way, non-real-time detection of each target equipment module in the semiconductor process equipment can be realized, which can help the user to find the problem cause in time when the semiconductor process equipment appears abnormal, and provides a guarantee for rapid positioning of the abnormality, saving troubleshooting time, improving production efficiency and product quality.

[0066] S202, determining whether the target equipment module has a residence abnormality based on the target information and a preset residence threshold.

[0067] The preset residence threshold, as an important standard for measuring whether the target equipment module has a residence abnormality, can be set according to actual needs, which is not limited here.

[0068] In implementation, the preset residence threshold can be a threshold carried by the detection instruction, that is, provided by the user according to the detection requirement; or can be a threshold stored in a preset position in advance, which can meet the needs of different detection scenarios and provide convenience for the implementation of detection.

[0069] After the target information is analyzed, the target information can be judged by using the preset residence threshold, so as to determine whether the target equipment module corresponding to the target information has a residence abnormality, which provides a guarantee for the accuracy of the detection result.

[0070] In the embodiments of the present application, in response to a detection instruction for a process file corresponding to a target device module, target information included in the process file is parsed to provide information support for anomaly detection; the target information can include a residence time of a processing object in the target device module; the residence time can be used to represent a non-process processing time during which the processing object stays at the target device module; the process file is used to record process information of the processing object in the target device module during a process of the processing object in the target device module; and then, based on the target information and a preset residence threshold, it is determined whether the target device module has a residence anomaly. In this way, based on the detection instruction and the preset residence threshold, automatic parsing of the target information and automatic detection of whether the target device module has a residence anomaly can be implemented. Compared with manual inspection, in a semiconductor process, possible preparation anomalies and positions of anomaly occurrence can be found more timely, quickly and accurately, the detection time is greatly saved, the detection efficiency and detection accuracy are improved, and the product quality and product preparation efficiency are guaranteed.

[0071] In application, in order to obtain an accurate residence time, the target device module needs to be determined before the target information included in the process file is parsed.

[0072] In some embodiments, the determination process of the target device module can include the following implementation steps:

[0073] S301, in response to a first user operation on an interactive interface, a device type to which the first user operation is directed is obtained.

[0074] The device type can refer to a model of a semiconductor process device. Different device types have different device modules.

[0075] It should be understood that each semiconductor process device has a unique device type.

[0076] In implementation, the first user operation can be an operation made by a user based on the interactive interface, which determines the device type.

[0077] For example, the interactive interface can display device types of a plurality of semiconductor process devices, and the user can select a device type of a semiconductor process device having a detection requirement therefrom; or the interactive interface can provide an editable area, and the user can fill in a device type of a semiconductor process device from the editable area according to a detection requirement, thereby providing a guide for subsequent determination of the target device module.

[0078] S302, according to the device type, a corresponding device module list is determined, and the device module list is displayed based on the interactive interface.

[0079] Each device type has a corresponding device module list, and the device module list has all the device modules of the semiconductor process equipment corresponding to the device type. The device module list is displayed through the interactive interface, which can be viewed and selected by the user, and also provides guidance for determining the target device module.

[0080] S303, obtaining at least one target device module determined by the user based on the device module list displayed through the interactive interface; the target device module includes one device module or a group of device modules in the device module list; the group of device modules includes a plurality of interrelated device modules.

[0081] In implementation, the user can select the device module to be detected according to the detection requirement based on the device module list displayed through the interactive interface, which can provide convenience for targeted detection of a certain device module or certain device modules.

[0082] When the device module list is displayed through the interactive interface, the device module list can be displayed in a tree structure to facilitate user viewing, selection and modification. In addition, the tree structure can more intuitively display the device modules that are associated, thereby providing convenience for the user to select a group of device modules.

[0083] Of course, the present application is only described by way of example in the form of a tree structure, but the present application is not limited thereto. In some other embodiments, the device module list can also be displayed in other forms, such as a list form, etc.

[0084] The target device module can include one device module or a group of device modules in the device module list, which can realize lotid detection of a single device module or a combination of multiple device modules, and is flexible in form and strong in practicality, and can meet more detection requirements.

[0085] In addition, in some embodiments, the target device module can be multiple, and therefore, the technical solution of the present application can meet simultaneous detection of one device module, multiple device modules or multiple groups of device modules, which can further improve the detection efficiency and provide protection for improving the production efficiency.

[0086] Correspondingly, before analyzing the target information included in the storage module, the abnormality detection method can further include determining a number of threads consistent with the number of target device modules. In response to a detection instruction for the process file corresponding to the target device module, the target information included in the process file is analyzed, which can specifically include: in response to the detection instruction for the process file corresponding to the target device module, based on each thread, each target information included in the process file is analyzed.

[0087] Specifically, the target information corresponding to the plurality of target device modules can be processed in parallel in the manner of a thread pool, that is, each thread calculates and detects whether the residence time of one target device module is abnormal. With the increase of the detection task of each new target device module, a new thread is created to process the detection task, so that the massive data can be processed efficiently and the detection efficiency is improved.

[0088] Of course, the present application is not limited to this, in some other embodiments, the determination process of the target device module can also include the following implementation steps:

[0089] S401, in response to the second user operation on the interactive interface, obtaining the device type and the detection time period to which the second user operation is directed.

[0090] In implementation, the second user operation is also an operation made by the user based on the interactive interface, which determines the device type and the detection time period.

[0091] For example, the interactive interface can display a plurality of device types of semiconductor process equipment and a plurality of time periods, and the user can select the device type of the semiconductor process equipment and the detection time period that needs to be detected from them; or the interactive interface can provide an editable area, and the user can fill in the device type of the semiconductor process equipment and the detection time period according to the detection requirement in the editable area, so as to provide guidance for subsequent determination of the target device module.

[0092] S402, determining each device module corresponding to the process in the detection time period as each target device module.

[0093] For example, the detection time period is from 13:00 on A month B day to 15:00 on A month B day, during this period, the first device module, the second device module and the third device module of the semiconductor process equipment S complete the process task, and the process file records the process information of the three device modules, so the first device module, the second device module and the third device module can be determined as three target device modules.

[0094] Among them, each device module corresponding to the process in the detection time period is determined as each target device module, which can first locate the corresponding process data in the process file according to the detection time period, and then locate the corresponding each device module according to the process data.

[0095] In this way, the target device module can be quickly determined according to the device type and the detection time period, which provides convenience for the detection in a certain detection time period.

[0096] It should be noted that the input detection of the detection time period can support two detection modes: one is real-time detection, that is, after the start time and the end time of the detection time period are provided by the user, real-time detection can be performed according to the detection time period. This mode is suitable for users who explicitly know the detection time period of the current semiconductor process equipment and can accurately locate the problem time period of the semiconductor process equipment. The other is timing detection, which can support three timing detection modes: monthly, daily, and hourly. The start time is the current time accumulated by month / day / hour, and the end time is the start time accumulated by month / day / hour. This mode does not require the user to set the detection time period and is suitable for use during the continuous operation of the semiconductor process equipment, which can realize real-time detection of the state of the semiconductor process equipment.

[0097] Specifically, the format of the time period can be set according to actual needs, which is not limited here. For example, the time period can support minutes, hours, days, months, and years, etc.

[0098] It should be noted that the detection conditions (such as device type, preset retention threshold, and / or detection time period) provided by the embodiments of the present application are set based on user needs and can be edited in real time. They can be based on historical process files to detect the semiconductor process equipment, or they can trigger detection after the current semiconductor process equipment finishes processing, which can realize non-real-time / real-time anomaly detection of the semiconductor process equipment.

[0099] In some embodiments, in order to improve the accuracy of detection, the target information included in the analysis of the process file can specifically include: if the target device module is one device module, the retention time of at least one processing object in the target device module is obtained from the process file; if the target device module is a group of device modules, the retention time of at least one processing object in each device module in the target device module is obtained from the process file, and the retention time of each processing object in each device module is summed to obtain the retention time of each processing object in the target device module.

[0100] Specifically, when the target device module is one device module, the retention time of each processing object in the device module can be directly obtained from the process file. When the target device module is a group of device modules, the retention time of each processing object in each device module in the group of device modules can be directly obtained from the process file, and for each processing object, the retention time of the processing object in each device module is added to determine the retention time of the processing object in the group of device modules. For example, a group of device modules includes device module a, device module b, and device module c, which are associated with each other, and the retention time of the processing object in device module a, device module b, and device module c is 10s, 15s, and 20s, respectively. The retention time of the processing object a in the group of device modules is 45s (10s+15s+20s).

[0101] In some embodiments, when obtaining the residence time of each processing object, the total time of each processing object in the current device module can be obtained from the process data corresponding to the device type based on the detection time period confirmed by the user, and the process time corresponding to the current device module can be obtained. The total time is the time period from when the processing object enters the current device module to when it leaves the current device module. The process time is the actual time period during which the processing object undergoes process treatment in the current device module. Then, the difference between the total time and the process time of each processing object in the current device module is determined as the residence time of each processing object in the current device module.

[0102] That is, the residence time of the processing object in the target device module is obtained by removing the process time from the total time. In the semiconductor process, after the processing object enters a device module and undergoes process treatment, it leaves and enters the device module corresponding to the next process node. That is, the shorter the residence time of the processing object in a device module, the better the performance of the semiconductor process equipment, the better the optimization of the scheduling algorithm, and the higher the utilization rate of the target device. The longer the residence time of the processing object in a device module, the worse the performance of the semiconductor process equipment, that is, the current device module of the semiconductor process equipment may have an abnormality.

[0103] In actual applications, the semiconductor process equipment of different device types records process data in different ways, that is, the process files exist in different forms. Specifically, the existence form of the process file mainly includes two forms: database storage form and file storage form. The ways of saving process data in the form of a database and in the form of a file are slightly different when parsing target information.

[0104] For semiconductor process equipment that records process data in the form of a database, the way to obtain process data through a detection time period is to query all tables related to the required process data, and to parse the relationship between the table structures through a keyword (such as the identification of the target device module, the identification of the processing object, etc.), and then to filter out the relevant process data of the detection time period.

[0105] For semiconductor process equipment recorded in the form of file storage, it is recorded in the form of date, so all files in the time period can be filtered first by detecting the time period, parsing multiple files related to each process task, establishing a mapping relationship table, and saving the process data. For example, the detection time period is between 2023-11-29 19:46:55 and 2023-11-29 20:04:00, first all process data files of 2023-11-29 19:46:55 to 2023-11-29 20:04:00 can be found from the folder of process data; then group according to the process task, and splice the process data files related to the processing object; finally, by analyzing the content of the spliced file, the names of all processing objects participating in the same process task are obtained, the processing objects related to the process task obtained are grouped according to the name, and the process data related to each processing object is obtained by analysis.

[0106] In some embodiments, when determining whether the target device module has a retention anomaly based on the target information and the preset retention threshold, the retention duration included in the target information can be detected using the preset retention threshold. If the retention duration of at least one processing object in the target device module is greater than the preset retention threshold, it is determined that the target device module has a retention anomaly. Otherwise, it is determined that the target device module does not have a retention anomaly.

[0107] In this way, the target device module with a retention anomaly can be accurately screened out, thereby improving the accuracy of detection and providing a theoretical basis for quickly finding and positioning the anomaly.

[0108] Taking a wafer as an example, when obtaining the related process data of the retention duration of the wafer in each device module, the following steps can be mainly divided:

[0109] 1) Obtain the process data of the semiconductor process equipment in the detection time period.

[0110] For semiconductor process equipment recording process data in the form of a database, the required process data can be obtained by automatically executing a series of related structured query languages (Structured Query Language, SQL). For semiconductor process equipment recording process data in the form of a file, all files are first spliced together, and then the required process data is obtained through a keyword. Among them, in order to facilitate subsequent analysis, all process data is recorded in a network virtual table (such as a DataTable structure).

[0111] 2) Obtain process data related to each Job (production task).

[0112] There can be multiple pieces of process data for a specified time period, and CJobID can identify and track a production process (i.e. a Job, where CJobID refers to a piece box task group corresponding to the materials in the same piece box). In order to subsequently detect the residence time at multiple target equipment modules in parallel, the process data can be grouped according to CJobID, and the grouping results can be recorded in the network virtual table.

[0113] 3) Obtain process data related to each wafer.

[0114] The wafers participating in a Job can be multiple or single. By traversing the process data of each group of Jobs, the process data related to each wafer in each Job can be obtained according to the wafer identification (such as the name of the wafer), and the results can be recorded in the network virtual table.

[0115] 4) Obtain process data of each wafer at each target equipment module.

[0116] Each wafer process path can include multiple target equipment modules. By analyzing the data between the wafer process data leaving the target equipment module and arriving at the target equipment module, the process data of each wafer at each target equipment module can be obtained.

[0117] 5) Calculate the residence time of the wafer at each target equipment module in parallel.

[0118] In implementation, the process data of the wafer at each target equipment module can be parsed in parallel through the thread pool, and the time of the specified wafer arriving at the target equipment module and the time of the wafer leaving the target equipment module can be quickly obtained. One thread calculates and detects whether the residence time of the first target equipment module is abnormal, two threads respectively calculate and detect whether the residence time of the first target equipment module and the second target equipment module is abnormal, and with the increase of each target equipment module to be detected, a new thread is created to calculate and detect whether the residence time of the added target equipment module is abnormal. At the same time, each thread processing the residence time of the target equipment module can include one or more sub-threads, and the abnormal detection of the residence time of each wafer at the target equipment module can be assigned to a sub-thread, and these sub-threads respectively calculate and detect whether the residence time of a wafer at the target equipment module is abnormal.

[0119] In the embodiment of the present application, the detection process of the whole target equipment module's residence time can be realized by the method of thread pool to achieve high concurrency. Through experiments, for the process data of ten thousand levels, the time required for the whole detection can be controlled within 30s, and the whole detection process does not need to rely on external tools such as Excel, all data can be recorded in the storage area, and the processing speed is fast, which can effectively realize the calculation and abnormal detection of the residence time of the target equipment module for massive process data.

[0120] That is, the residence time of the wafer in the equipment module = the time when the wafer leaves the equipment module - the time when the wafer arrives at the equipment module - the process time of the wafer in the equipment module.

[0121] Among them, the process time of the wafer in the target equipment module is divided into two categories: one is the fixed process time in the target equipment module, and for this, a unified treatment will be performed when calculating the residence time; the other is the process time in the target equipment module. For the process time of the wafer in the target equipment module, there are two forms of processing: one is to query and calculate the process time from the process data, and subtract the process time when calculating the residence time; the other is to divide the residence time of the target equipment module into two parts according to the start and end time of the process: one is to detect the time when the process starts and the wafer enters the target equipment module, and the time difference between the two is set as the first time length; two is to detect the time when the wafer leaves the target equipment module and the time when the process of the target equipment module ends, and the time difference between the two is set as the second time length; the first time length plus the second time length is the residence time.

[0122] In the embodiment of the present application, the whole target equipment module's residence time detection process can be realized by the method of thread pool to achieve high concurrency. Through experiments, for the process data of ten thousand levels, the time required for the whole detection can be controlled within 30s, and the whole detection process does not need to rely on external tools such as Excel, all data can be recorded in the storage area, and the processing speed is fast, which can effectively realize the calculation and abnormal detection of the residence time of the target equipment module for massive process data.

[0123] In some embodiments, after determining whether the target equipment module has a residence abnormality, the abnormality detection method can further include: if it is determined that the target equipment module has a residence abnormality, issuing a prompt information, the prompt information being used to prompt that the target equipment module has a residence abnormality.

[0124] Specifically, the specific manner and content of the prompt information can be set according to actual needs, which is not limited here.

[0125] For example, the prompt of the retention abnormality can be in the form of text, in the form of sound, in the form of sound and light, etc.

[0126] In some embodiments, the above-mentioned issuing of the prompt information can specifically include: storing the retention duration of the processing object in the target device module into a target file in a preset format, and marking the retention duration determined to be abnormal; and storing the target file into a preset address.

[0127] Specifically, before storing the retention duration of the processing object in the target device module into the target file in the preset format, the preset address and / or the preset format determined by the user based on the interactive interface can also be obtained. That is, the user can set the preset format and / or the preset address according to actual needs, and then store the retention duration of the processing object in the target device module into the target file in the preset format, and store the target file into the preset address.

[0128] The preset format and the preset address can both be set according to user needs, which is not limited here.

[0129] In addition, the data stored into the target file in the preset format can also include other data, for example, can also include a production task name (job name), an identifier of the processing object (such as a name of the processing object), a name of the target device module, a time when the processing object enters the target device module, and / or a time when the processing object leaves the target device module, etc.

[0130] In implementation, the preset format can be an Excel format. On the one hand, when storing data, the retention duration of each processing object in the target device module can be stored into a target file in the Excel format, which can facilitate the user to view each item of data and provide a basis for analyzing data. Moreover, marking the retention duration determined to be abnormal can be highlighting the retention duration determined to be abnormal, so that the abnormal retention duration can be more obviously presented, improving the viewing efficiency of the user, helping the user to discover abnormal problems in time and solve them, and improving the production efficiency of the device.

[0131] On the other hand, when storing data, the retention duration determined to be abnormal among the retention duration of each processing object in the target device module can also be stored into a target file in the Excel format, that is, only the abnormal data detected is stored, so as to more directly display the detection result for the user to view.

[0132] As another implementation form of the disclosure, the embodiments of the present application further provide an exception detection apparatus applied to a semiconductor process equipment, the semiconductor process equipment having a plurality of equipment modules, and the exception detection apparatus can comprise: an analysis module configured to analyze target information included in a process file corresponding to a target equipment module in response to a detection instruction for the process file, the target information comprising a residence time length of a processing object in the target equipment module, the residence time length being used to represent a non-process processing time length of the processing object staying at the target equipment module, and the process file being used to record process information of the processing object in the target equipment module in a process procedure of the processing object in the target equipment module; and a determination module configured to determine whether the target equipment module has a residence exception based on the target information and a preset residence threshold.

[0133] In some embodiments, the exception detection apparatus can further comprise a first acquisition module, which can be configured to: acquire a device type corresponding to a first user operation of an interaction interface in response to the first user operation; determine a corresponding equipment module list according to the device type, and display the equipment module list based on the interaction interface; and acquire at least one target equipment module determined by a user based on the equipment module list displayed based on the interaction interface; the target equipment module comprising one equipment module or a group of equipment modules in the equipment module list; and the group of equipment modules comprising a plurality of mutually associated equipment modules.

[0134] In some embodiments, the exception detection apparatus can further comprise a second acquisition module, which can be configured to: acquire a device type and a detection time period corresponding to a second user operation of an interaction interface in response to the second user operation; and determine each equipment module corresponding to a process procedure in a process procedure recorded by a process file corresponding to the device type and in the detection time period as each target equipment module.

[0135] In some embodiments, when analyzing the target information included in the process file, the analysis module can be specifically configured to: if the target equipment module is one equipment module, acquire the residence time length of at least one processing object from the process file for the target equipment module; and if the target equipment module is a group of equipment modules, acquire the residence time length of at least one processing object from the process file for each equipment module in the target equipment module, and sum the residence time lengths of each processing object in each equipment module to obtain the residence time length of each processing object in the target equipment module.

[0136] In some embodiments, when obtaining the residence time length of each processing object, the parsing module can be specifically configured to: based on the detection time period confirmed by the user, obtain the total time length of each processing object in the current device module from the process data corresponding to the device type, and obtain the process time length corresponding to the current device module; the total time length is the time length between the time when the processing object enters the current device module and the time when the processing object leaves the current device module; the process time length is the actual time length during which the processing object experiences the process in the current device module; and the difference between the total time length and the process time length of each processing object in the current device module is determined as the residence time length of each processing object in the current device module.

[0137] In some embodiments, the determining module can be specifically configured to: if the residence time length of at least one processing object in the target device module is greater than the preset residence threshold, it is determined that the target device module has a residence abnormality; otherwise, it is determined that the target device module does not have a residence abnormality.

[0138] In some embodiments, the abnormality detection apparatus can further include a prompting module, which can be configured to: if it is determined that the target device module has a residence abnormality, send a prompt information, and the prompt information is used to prompt that the target device module has a residence abnormality.

[0139] In some embodiments, the prompting module can be specifically configured to: store the residence time length of the processing object in the target device module into a target file in a preset format, and mark the residence time length for which the residence abnormality is determined; and store the target file into a preset address.

[0140] In some embodiments, the target device module can include a plurality of device modules; and the parsing module can be further configured to: determine a number of threads corresponding to the number of target device modules; and correspondingly, when responding to the detection instruction for the process file corresponding to the target device module, the parsing module can be specifically configured to: based on each thread, respectively parse each target information included in the process file in response to the detection instruction for the process file corresponding to the target device module.

[0141] The specific limitations of the abnormality detection apparatus can be referred to the limitations of the abnormality detection method described above, which will not be repeated here. Each module in the above abnormality detection apparatus can be realized by software, hardware, and combinations thereof, in whole or in part. Each module described above can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to each module.

[0142] As another implementation form of the disclosure, the embodiments of the present application further provide a semiconductor process detection device for detecting whether the residence time of a wafer in a target device module of a semiconductor process device is abnormal, which can include a processor and a memory connected to the processor; the memory is configured to store a computer program; and the processor is configured to invoke and execute the computer program in the memory to perform the above abnormality detection method provided by any of the above embodiments.

[0143] As another implementation form of the disclosure, the embodiments of the present application further provide a semiconductor process device, as shown in FIG. 5, the semiconductor process device 100 can include the semiconductor process detection device 30 and a plurality of device modules according to any of the above embodiments.

[0144] The plurality of device modules can include a first robot 10, a wafer loading and unloading station 21, a calibration module 22, a cooling disc 23, and a plurality of process chambers 11, etc.

[0145] The semiconductor process detection device 30 is configured to perform abnormality detection on the residence time of the wafer in the target device module.

[0146] In some embodiments, the semiconductor process detection device 30 is, for example, an upper computer of the semiconductor process device 100, which is not limited in the present specification and can be determined according to actual conditions.

[0147] As another implementation form of the disclosure, another embodiment of the present application further provides a computing device, as shown in FIG. 6, which can include a memory and a processor, the memory stores a computer program, and the processor executes the computer program to perform the steps of the abnormality detection method according to various embodiments of the present specification described in the above embodiments of the present application.

[0148] The internal structure of the computing device can be as shown in FIG. 6, which includes a processor, a memory, a network interface, and an input device connected through a system bus. The processor of the computing device is configured to provide computing and control capabilities. The memory of the computing device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The network interface of the computing device is configured to communicate with an external terminal through a network connection. The computer program is executed by the processor to perform the steps of the abnormality detection method according to various embodiments of the present specification described in the above embodiments of the present specification.

[0149] The processor can include a main processor, and can further include a baseband chip, a modem, etc.

[0150] The memory stores programs for implementing the technical solutions of the present application, and can also store operating systems and other key services. Specifically, the programs can include program codes, and the program codes include computer operation instructions. More specifically, the memory can include read-only memory (ROM), other types of static storage devices that can store static information and instructions, random access memory (RAM), other types of dynamic storage devices that can store information and instructions, disk storage, flash, and the like.

[0151] The processor can be a general-purpose processor, such as a general-purpose central processing unit (CPU), a microprocessor, or the like, an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of programs of the present application. It can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a ready-to-use programmable gate array (FPGA), or other programmable logic device, a discrete gate or transistor logic device, a discrete hardware component.

[0152] The input device can include a device that receives data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor, and the like.

[0153] The output device can include a device that allows information to be output to a user, such as a display screen, a printer, a speaker, and the like.

[0154] The communication interface can include a device using any transceiver to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), and the like.

[0155] The processor executes the programs stored in the memory and calls other devices, which can be used to implement each step of any of the abnormality detection methods provided by the above-mentioned embodiments of the present application.

[0156] The computing device can also include a display component and a voice component. The display component can be a liquid crystal display or an electronic ink display. The input device of the computing device can be a touch layer overlaid on the display component, or can be a key, trackball, or touchpad provided on the housing of the computing device. It can also be an external keyboard, touchpad, or mouse, and the like.

[0157] Those skilled in the art can understand that the structure shown in FIG. 6 is only a block diagram of part of the structure related to the scheme of the present specification, and does not constitute a limitation on the computing device to which the scheme of the present specification is applied. A specific computing device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0158] In addition to the method and device described above, the anomaly detection method provided by the embodiments of the present specification can also be a computer program product, which includes computer program instructions that, when executed by a processor, cause the processor to perform the steps of the anomaly detection method according to various embodiments of the present specification described in the "Exemplary Method" section of the present specification.

[0159] The computer program product can be written in any combination of one or more programming languages to perform the operations of the embodiments of the present specification, including object-oriented programming languages such as Java, C++, and conventional procedural programming languages such as "C" language or similar programming languages. Program code can be executed entirely on a user computing device, partially on a user device, as a separate software package, partially on a user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0160] In addition, the embodiments of the present specification also provide a computer readable storage medium having a computer program stored thereon, and the computer program causes a processor to perform the steps of the anomaly detection method according to various embodiments of the present specification described in the "Exemplary Method" section of the present specification.

[0161] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when executed, can include the processes of the above-mentioned embodiment methods. Any reference to memory, storage, databases, or other media in this specification shall include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM), or external cache memory. As an illustration but not limitation, RAM is available in many forms such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0162] Any combination of the technical features of the above-mentioned embodiments can be made, and in order to make the description simple, not all possible combinations of the technical features in the above-mentioned embodiments are described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present specification.

[0163] The above-mentioned embodiments only express several embodiments of the present specification, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the solutions provided by the embodiments of the present specification. It should be noted that for ordinary skilled in the art, without departing from the concept of the present specification, a number of modifications and improvements can be made, which are within the scope of the present specification. Therefore, the scope of protection of the present specification should be subject to the appended claims.

Claims

1. An anomaly detection method characterized by, The application is applied to a semiconductor process equipment having a plurality of equipment modules; the method comprises: In response to a detection instruction for a process file corresponding to a target equipment module, target information included in the process file is parsed, the target information including a residence time length of a processing object in the target equipment module, the residence time length being used to represent a non-process processing time length of the processing object staying at the target equipment module, the process file being used to record process information of the processing object in the target equipment module in a process of the target equipment module on the processing object; Based on the target information and a preset residence threshold, it is determined whether the target equipment module has a residence abnormality.

2. The method of claim 1, wherein, The determination process of the target equipment module comprises: In response to a first user operation on an interactive interface, an equipment type to which the first user operation is directed is acquired; According to the equipment type, a corresponding equipment module list is determined, and the equipment module list is displayed based on the interactive interface; At least one target equipment module determined by the user based on the equipment module list displayed on the interactive interface is acquired; the target equipment module includes one equipment module or a group of equipment modules in the equipment module list; the group of equipment modules includes a plurality of mutually associated equipment modules.

3. The method of claim 1, wherein, The determination process of the target equipment module comprises: In response to a second user operation on an interactive interface, an equipment type and a detection time period to which the second user operation is directed are acquired; Each equipment module corresponding to a process in a process recorded in a process file corresponding to the equipment type and in the detection time period is determined as each target equipment module.

4. The method of claim 2 or 3, wherein, The parsing of the target information included in the process file comprises: If the target equipment module is one equipment module, the residence time length of the at least one processing object is acquired from the process file for the target equipment module; If the target equipment module is a group of equipment modules, the residence time length of the at least one processing object is acquired from the process file for each equipment module in the target equipment module, and the residence time lengths of each processing object in each equipment module are summed to obtain the residence time length of each processing object in the target equipment module.

5. The method of claim 4, wherein, The acquisition of the residence time length of the at least one processing object comprises: Based on a user-confirmed detection time period, a total time length of the at least one processing object in a current equipment module is acquired from process data corresponding to the equipment type, and a process time length corresponding to the current equipment module is acquired; the total time length is a time length between when the processing object enters the current equipment module and when the processing object leaves the current equipment module; the process time length is an actual time length of the processing object experiencing process processing in the current equipment module; A difference between the total time length and the process time length of each processing object in the current equipment module is determined as the residence time length of each processing object in the current equipment module.

6. The method of claim 1, wherein, The determination of whether the target equipment module has a residence abnormality based on the target information and a preset residence threshold comprises: If there is at least one processing object in the target device module with a residence time greater than the preset residence threshold, it is determined that the target device module has a residence abnormality; otherwise, it is determined that the target device module does not have a residence abnormality.

7. The method of claim 1, wherein, After determining whether the target device module has a residence abnormality, the method further comprises: If the target device module has a residence abnormality, a prompt information is sent; the prompt information is used to prompt that the target device module has a residence abnormality.

8. The method of claim 7, wherein, The prompt information includes: The residence time of the processing object in the target device module is stored in a target file in a preset format, and the residence time of the determined residence abnormality is marked; The target file is stored in a preset address.

9. The method of claim 1, wherein, The target device module includes multiple; Before analyzing the target information included in the process file, the method further comprises: Determine the number of threads consistent with the number of target device modules; The target information included in the process file is analyzed based on each thread, respectively. It includes:

10. A semiconductor process inspection apparatus characterized by comprising: A processor, and a memory connected to the processor; The memory is used to store a computer program; The processor is used to call and execute the computer program in the memory to execute the abnormality detection method as claimed in any one of claims 1-9. It includes multiple device modules, and the semiconductor process detection device as claimed in claim 10.

11. A semiconductor process apparatus, characterized by comprising: ​

Images