Data processing method and device, equipment and storage medium

Abstract

A data processing method, comprising: obtaining a production record corresponding to each sample in a plurality of samples; the production record comprising process information, a production time corresponding to the process information, and an index value; determining a high-incidence time period of defects according to the index value in the obtained production record and the time corresponding to the process information; and determining an influence degree of the process information on the sudden defects according to the high-incidence time period of defects and the obtained production record.

Description

Technical Field

[0001] This disclosure relates to the field of data processing technology, and in particular to data processing methods, apparatus, devices and storage media. Background Technology

[0002] During product manufacturing, the technological steps and corresponding process parameters all affect product performance, potentially leading to substandard performance (also known as defects). These technological steps include the equipment used in the production process. Therefore, for products that fail to meet performance standards, it is necessary to identify the causes of these sudden defects by examining the technological steps and parameters. Summary of the Invention

[0003] On the one hand, a data processing method is provided, including: acquiring production records corresponding to each sample in multiple samples; the production records include process information, production time corresponding to the process information, and indicator values; the process information is process parameters and / or process steps; the indicator values ​​are used to characterize the degree of defect of the sample belonging to a preset defect type; the multiple samples include defective samples, which are samples with indicator values ​​greater than a first threshold; based on the indicator values ​​in the acquired production records and the time corresponding to the process information, a high-incidence period for defects is determined, which is the period when the distribution probability of defective samples is greater than a second threshold; based on the high-incidence period for defects and the acquired production records, the degree of influence of process information on sudden defects is determined.

[0004] In some embodiments, when the process information is a process step, the above-mentioned determination of the degree of influence of the process information on the sudden defect based on the high defect incidence period and the obtained production records includes: determining the target distribution of the index values ​​of the samples in the high defect incidence period on the production time corresponding to the process step; determining the difference value between the target distribution and the preset distribution; the difference value is used to characterize the distribution probability of defective samples after the process step; and determining the degree of influence of the process step on the sudden defect based on the difference value.

[0005] In other embodiments, determining the target distribution of the index values ​​of samples within the high-incidence period of defects on the production time corresponding to the process step includes: converting the production time corresponding to the process step into a time value corresponding to the process step; and determining the target distribution of the index values ​​of samples within the high-incidence period of defects on the time value corresponding to the process step.

[0006] In other embodiments, determining the target distribution of the index values ​​of samples within the high-incidence period of defects on the time values ​​corresponding to the process steps includes: using a polynomial curve fitting method to fit the time values ​​corresponding to the process steps into fitted index values; and determining the distribution of the fitted index values ​​on the time values ​​as: the target distribution of the index values ​​of samples within the high-incidence period of defects on the time values ​​corresponding to the process steps.

[0007] In other embodiments, the preset distribution is a standard normal distribution; the target distribution is a multinomial distribution; determining the difference between the target distribution and the preset distribution includes: using a significance test to obtain the difference between the target distribution and the standard normal distribution.

[0008] In other embodiments, determining the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information includes: dividing multiple samples into good samples and defective samples based on a first threshold and the indicator values ​​in the acquired production records; determining the period in which the ratio of the number of defective samples to the total number of samples in the production records is greater than a second threshold as the high-incidence period of defects; the period in question is the time corresponding to the process information.

[0009] In other embodiments, when the process information is process parameters, the degree of influence of the process information on sudden defects is determined based on the high-incidence period of defects and the acquired production records. This includes: obtaining a first production time using mutation point detection; the first production time is the mutation time point of the indicator value; the first production time is a time point within the high-incidence period of defects; obtaining the critical change point of the process parameters in the production records, and determining the time corresponding to the critical change point as the second production time. The difference between the first production time and the second production time is determined, and the degree of influence of the process parameters on sudden defects is determined based on this difference.

[0010] In other embodiments, the above-mentioned method of obtaining the critical change point of the process parameter in the production record includes: obtaining the Gini coefficient of the process parameter in the production record; and determining the value of the process parameter with the smallest Gini coefficient as the critical change point of the process parameter.

[0011] In other embodiments, the Gini coefficient of process information in the production records is obtained; the Gini coefficient of process information is used to characterize the degree of correlation between process information and the index value of the sample; based on the Gini coefficient of process information, the degree of influence of process information on sudden adverse events is determined.

[0012] In other embodiments, the production record also includes a sample identifier. When the process information is a process parameter, the above-mentioned acquisition of the Gini coefficient of the process information in the production record includes: acquiring the process parameter and index value corresponding to the sample identifier from the production record; and acquiring the Gini coefficient of the process parameter based on the process parameter and index value corresponding to the sample identifier.

[0013] In other embodiments, the production record also includes a sample identifier. When the process information is a process step, obtaining the Gini coefficient of the process information in the production record includes: obtaining the process step and index value corresponding to the sample identifier from the production record; and obtaining the Gini coefficient of the process step based on the process step and index value corresponding to the sample identifier.

[0014] In other embodiments, the method further includes: performing a chi-square test on the process steps in the production record to obtain a chi-square test value of the process steps on the index values ​​of the sample, wherein the chi-square test value is used to characterize the degree of influence of the process steps on the index values ​​of the sample; and determining the degree of influence of the process steps on the sudden defects based on a first preset weight, the chi-square test value, and the Gini coefficient of the process steps.

[0015] In other embodiments, the method further includes: performing a correlation test on the process parameters in the production record and the index values ​​of the sample to obtain the influence parameter of the process parameter; the influence parameter is used to characterize the degree of influence of the process parameter on the index value of the sample; and obtaining the degree of influence of the process parameter on the sudden defect based on the second preset weight, the influence parameter and the Gini coefficient of the process parameter.

[0016] In other embodiments, the above-mentioned acquisition of the production record corresponding to each sample in the plurality of samples includes: acquiring a first correspondence between the sample identifier and the indicator value of each sample in the plurality of samples, and acquiring a second correspondence between the sample identifier, process information and the production time corresponding to the process information of each sample; and establishing a third correspondence between the process information, the production time corresponding to the process information and the indicator value of each sample based on the sample identifier, the first correspondence and the second correspondence.

[0017] On the other hand, a data processing method is provided, comprising: receiving sample screening conditions input by a user on a condition selection interface; acquiring production records for each sample among multiple samples corresponding to the sample screening conditions; the production records include process information, production time corresponding to the process information, and indicator values; the process information includes process parameters and / or process steps; the indicator values ​​are used to characterize the degree of defect of a sample belonging to a preset defect type; the multiple samples include defective samples, which are samples with indicator values ​​greater than a first threshold; determining the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information, wherein the high-incidence period of defects is the period during which the distribution probability of defective samples is greater than a second threshold; determining the degree of influence of process information on sudden defects based on the high-incidence period of defects and the acquired production records; and displaying the degree of influence of process information on sudden defects on an analysis result display interface.

[0018] In some embodiments, the above-mentioned display of the impact of process information on sudden defects on the analysis results display interface includes: sorting the impact of multiple pieces of process information on sudden defects; and displaying the sorted process information on the impact of sudden defects on the analysis results display interface.

[0019] On another front, a data processing device is provided, comprising: an acquisition module, a first determination module, and a second determination module. The acquisition module is used to acquire production records corresponding to each sample in a plurality of samples. The production records include process information, production time corresponding to the process information, and indicator values. The process information includes process parameters and / or process steps. The indicator values ​​are used to characterize the degree of defect of a sample belonging to a preset defect type. The plurality of samples includes defective samples, which are samples whose indicator values ​​are greater than a first threshold. The first determination module is used to determine the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. The high-incidence period of defects is the period in which the distribution probability of defective samples is greater than a second threshold. The second determination module is used to determine the degree of influence of process information on sudden defects based on the high-incidence period of defects and the acquired production records.

[0020] In some embodiments, when the process information is a process step, the second determining module is specifically used to: determine the target distribution of the index values ​​of the samples during the high-incidence period of defects on the production time corresponding to the process step; determine the difference value between the target distribution and the preset distribution; the difference value is used to characterize the distribution probability of defective samples after the process step; and determine the degree of influence of the process step on the sudden defect based on the difference value.

[0021] In other embodiments, the second determining module is specifically used to: convert the production time value corresponding to the process step into the time value corresponding to the process step; and determine the target distribution of the index value of the sample in the time value corresponding to the process step during the period of high defect incidence.

[0022] In other embodiments, the second determining module is specifically used to: use a polynomial curve fitting method to fit the time values ​​corresponding to the process steps into fitting index values; and determine the distribution of the fitting index values ​​on the time values ​​as: the target distribution of the index values ​​of the samples in the high-incidence period of defects on the time values ​​corresponding to the process steps.

[0023] In other embodiments, the preset distribution is a standard normal distribution; the target distribution is a multinomial distribution; the second determining module is specifically used to: obtain the difference value between the target distribution and the standard normal distribution using a significance test.

[0024] In other embodiments, the first determining module is specifically used to: divide multiple samples into good samples and bad samples according to a first threshold and the indicator values ​​in the acquired production records; determine the time period in which the ratio of the number of bad samples in the production records to the total number of samples is greater than a second threshold as the high-incidence time period of defects; the time period is the time period corresponding to the process information.

[0025] In other embodiments, when the process information is process parameters, the acquisition module is further configured to: acquire a first production time by mutation point detection; the first production time is the mutation time point of the index value; the first production time is a time point in the period of high incidence of defects; acquire the critical change point of the process parameters in the production record, and determine the time corresponding to the critical change point as the second production time; the second determination module is specifically configured to determine the difference between the first production time and the second production time, and determine the degree of influence of the process parameters on the sudden defect based on the difference.

[0026] In other embodiments, the acquisition module is further configured to: acquire the Gini coefficient of the process parameters in the production record; and determine the value of the process parameter with the smallest Gini coefficient as the critical change point of the process parameter.

[0027] In other embodiments, the acquisition module is further configured to: acquire the Gini coefficient of process information in the production record; the Gini coefficient of process information is used to characterize the degree of correlation between process information and the index value of the sample; the second determination module is specifically configured to: determine the degree of influence of process information on sudden adverse events based on the Gini coefficient of process information.

[0028] In other embodiments, the production record also includes a sample identifier. When the process information is a process parameter, the acquisition module is specifically used to: obtain the process parameter and index value corresponding to the sample identifier from the production record; and obtain the Gini coefficient of the process parameter based on the process parameter and index value corresponding to the sample identifier.

[0029] In other embodiments, the production record also includes a sample identifier. When the process information is a process step, the acquisition module is specifically used to: acquire the process step and index value corresponding to the sample identifier from the production record; and acquire the Gini coefficient of the process step based on the process step and index value corresponding to the sample identifier.

[0030] In other embodiments, the data processing device further includes an inspection module for performing a chi-square test on the process steps in the production record to obtain a chi-square test value of the process step on the index value of the sample. The chi-square test value is used to characterize the degree of influence of the process step on the index value of the sample. The second determination module is specifically used to determine the degree of influence of the process step on the sudden defect based on the first preset weight, the chi-square test value and the Gini coefficient of the process step.

[0031] In other embodiments, the inspection module is further configured to: perform correlation inspection on the process parameters and the index values ​​of the samples in the production records to obtain the influence parameters of the process parameters; the influence parameters are used to characterize the degree of influence of the process parameters on the index values ​​of the samples; the second determination module is specifically configured to: obtain the degree of influence of the process parameters on sudden defects based on the second preset weight, the influence parameters and the Gini coefficient of the process parameters.

[0032] In other embodiments, the acquisition module is specifically used to acquire a first correspondence between the sample identifier and the index value of each sample in a plurality of samples, and to acquire a second correspondence between the sample identifier, process information and the production time corresponding to the process information of each sample; and to establish a third correspondence between the process information, the production time corresponding to the process information and the index value of each sample based on the sample identifier, the first correspondence and the second correspondence of each sample.

[0033] On another front, a data processing device is provided, comprising: a receiving module, an acquiring module, a determining module, and a display module. The receiving module receives sample screening conditions input by a user on a condition selection interface. The acquiring module acquires production records for each of multiple samples corresponding to the sample screening conditions. The production records include process information, production time corresponding to the process information, and indicator values. The process information consists of process parameters or process steps. The indicator values ​​characterize the degree of defect of a sample belonging to a preset defect type. The multiple samples include defective samples, which are samples with indicator values ​​greater than a first threshold. The determining module determines high-incidence periods for defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. The high-incidence periods for defects are periods in which the distribution probability of defective samples is greater than a second threshold. Based on the high-incidence periods for defects and the acquired production records, the module determines the degree of influence of process information on sudden defects. The display module displays the degree of influence of process information on sudden defects on an analysis result display interface.

[0034] In some embodiments, the data processing apparatus further includes: a sorting module for sorting the degree of influence of multiple acquired process information on the sudden defect; and a display module specifically for displaying the degree of influence of the sorted process information on the sudden defect on the analysis result display interface.

[0035] In another aspect, an electronic device is provided, including a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the data processing method described in any of the preceding embodiments.

[0036] In another aspect, a computer-readable storage medium is provided. The computer-readable storage medium stores computer program instructions that, when executed on a processor, cause the processor to perform one or more steps of the data processing method as described in any of the above embodiments.

[0037] In another aspect, a computer program product is provided. The computer program product includes computer program instructions that, when executed on a computer, cause the computer to perform one or more steps of the data processing method as described in any of the above embodiments.

[0038] In another aspect, a computer program is provided. When the computer program is executed on a computer, it causes the computer to perform one or more steps in the data processing method as described in any of the above embodiments. Attached Figure Description

[0039] To more clearly illustrate the technical solutions in this disclosure, the accompanying drawings used in some embodiments of this disclosure will be briefly described below. Obviously, the drawings described below are only drawings of some embodiments of this disclosure, and those skilled in the art can obtain other drawings based on these drawings. In addition, the drawings described below can be regarded as schematic diagrams and are not intended to limit the actual size of the product, the actual flow of the method, the actual timing of the signals, etc. involved in the embodiments of this disclosure.

[0040] Figure 1 This is a structural diagram of a data processing system according to some embodiments;

[0041] Figure 2 This is a structural diagram of a data processing system combined with data processing according to some embodiments;

[0042] Figure 3 This is a structural diagram of an electronic device according to some embodiments;

[0043] Figure 4 This is a flowchart of a data processing method according to some embodiments;

[0044] Figure 5 This is a distribution diagram of positive and negative samples according to some embodiments;

[0045] Figure 6 A distribution of index values ​​of samples according to some embodiments over production time;

[0046] Figure 7 A comparison chart of the target distribution and the standard normal distribution according to some embodiments;

[0047] Figure 8 This is a flowchart of a data processing method according to some embodiments;

[0048] Figure 9 This is a flowchart of another data processing method according to some embodiments;

[0049] Figure 10 A structural diagram of a condition selection interface based on some embodiments;

[0050] Figure 11 This is a structural diagram of the cause variable input interface according to some embodiments;

[0051] Figure 12This is a structural diagram of the interface based on the analysis results of some embodiments;

[0052] Figure 13 This is a structural diagram of a data processing apparatus 70 according to some embodiments;

[0053] Figure 14 This is a structural diagram of another data processing apparatus 80 according to some embodiments. Detailed Implementation

[0054] Unless the context otherwise requires, throughout the specification and claims, the term "comprise" and its other forms, such as the third-person singular "comprises" and the present participle "comprising," are interpreted as open-ended and encompassing, meaning "including, but not limited to." In the description of the specification, terms such as "one embodiment," "some embodiments," "exemplary embodiments," "example," "specific example," or "some examples," etc., are intended to indicate that a particular feature, structure, material, or characteristic associated with that embodiment or example is included in at least one embodiment or example of this disclosure. The illustrative representations of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics mentioned may be included in any suitable manner in any one or more embodiments or examples.

[0055] Hereinafter, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of embodiments of this disclosure, unless otherwise stated, "a plurality of" means two or more.

[0056] In describing some embodiments, the terms "coupled" and "connected," and their derivative expressions, may be used. For example, the term "connected" may be used in describing some embodiments to indicate that two or more components have direct physical or electrical contact with each other. Similarly, the term "coupled" may be used in describing some embodiments to indicate that two or more components have direct physical or electrical contact. However, the terms "coupled" or "communicatively coupled" may also refer to two or more components that do not have direct contact with each other but still cooperate or interact with each other. The embodiments disclosed herein are not necessarily limited to the content of this document.

[0057] As used herein, depending on the context, the term “if” may optionally be interpreted as meaning “when”, “in the event of”, “in response to determination”, or “in response to detection”. Similarly, depending on the context, the phrase “if it is determined that…” or “if [the stated condition or event] is detected” may optionally be interpreted as meaning “in the event of determination that…”, “in response to determination that…”, “when [the stated condition or event] is detected”, or “in response to the detection of [the stated condition or event]”.

[0058] The use of “applies to” or “configured to” in this article implies an open and inclusive language that does not preclude applicability to or configuration to devices that perform additional tasks or steps.

[0059] In addition, the use of “based on” implies openness and inclusivity, because processes, steps, calculations or other actions “based on” one or more of the stated conditions or values ​​may in practice be based on additional conditions or values ​​beyond those stated.

[0060] As used herein, “about” or “approximately” includes the stated value and the average value within an acceptable range of deviation from the given value, wherein the acceptable range of deviation is determined by a person skilled in the art taking into account the measurement under discussion and the error associated with the measurement of the given quantity (i.e., the limitations of the measurement system).

[0061] In related technologies, during the manufacturing process, any production process the product undergoes, the equipment involved in that process, and the equipment's configuration parameters (also known as process parameters) will affect the product's performance, potentially leading to substandard performance (also known as defects). Due to the complexity of the production processes and the large quantity of products produced, manually identifying the causes of substandard performance is difficult, and the timeliness and accuracy of data processing are limited, making it difficult to meet the ever-increasing production demands. Based on this, this disclosure provides a data processing method that uses data mining for automatic diagnostic analysis. It utilizes data generated from each production process in the entire factory to obtain production records corresponding to each sample from multiple samples. Based on the indicator values ​​of the samples in the obtained production records and the time corresponding to the process information, it determines the high-incidence period of defects. Based on the high-incidence period of defects and the obtained production records, it determines the degree of influence of process information on sudden defects and converts it into quantitative judgment indicators (such as correlation quantification values), thereby improving detection efficiency and enabling users to make comprehensive and rapid decisions to locate the causes of sudden defects.

[0062] The technical solutions in some embodiments of this disclosure will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this disclosure, and not all embodiments. All other embodiments obtained by those skilled in the art based on the embodiments provided in this disclosure are within the scope of protection of this disclosure.

[0063] The data processing methods provided in the embodiments of this disclosure are applicable to, for example, Figure 1 The data processing system 10 shown includes a data processing device 100, a display device 200, and a distributed storage device 300. The data processing device 100 is coupled to both the display device 200 and the distributed storage device 300.

[0064] The distributed storage device 300 is configured to store production data generated by multiple devices (or factory equipment). For example, the production data generated by the multiple devices includes production records of the multiple devices; for example, the production records include the identifiers of the devices that multiple samples passed through during the production process, the environmental parameters corresponding to the devices, the index values, and the production time, with each sample passing through at least one device during the production process.

[0065] The distributed storage device 300 stores relatively complete data (such as a database). The distributed storage device 300 may include multiple hardware storage devices, which are distributed in different physical locations (such as in different factories or on different production lines) and exchange information with each other through wireless transmission (such as networks). Thus, the data is distributed, but logically constitutes a database based on big data technology.

[0066] A large amount of raw data from different devices is stored in relational databases (such as Oracle and MySQL) of corresponding production and manufacturing systems, such as Yield Management System (YMS), Fault Detection & Classification (FDC), and Manufacturing Execution System (MES). This raw data can be extracted from the original tables using data extraction tools (such as Sqoop and Kettle) and transmitted to distributed storage device 300 (such as Hadoop Distributed File System (HDFS)) to reduce the load on the devices and production and manufacturing systems and facilitate subsequent data processing device 100 to read the data.

[0067] refer to Figure 2The data in the distributed storage device 300 can be stored using Hive or HBase database formats. For example, using Hive, the raw data is first stored in the database; then, preprocessing such as data cleaning and transformation can be performed in Hive to obtain a sample production record data warehouse. The data warehouse can then connect to the display device 200, data processing device 100, etc., through different API interfaces to achieve data interaction with these devices. The display device 200 displays a selection page for users to select filtering conditions, including result variables, cause variables, and filtering conditions (e.g., sample category and preset time period). The data processing device 100 performs sudden defect time dimension analysis and / or intelligent mining for defect diagnosis analysis. The analysis results obtained by the data processing device 100 after defect diagnosis analysis are displayed to the user on the analysis result display page of the display device 200.

[0068] Because this involves multiple factories and multiple pieces of equipment, the amount of raw data is very large. For example, the raw data generated by all the equipment every day may be several hundred gigabytes, and the data generated every hour may be tens of gigabytes.

[0069] For example, there are two main solutions for storing and computing massive amounts of structured data: one is a big data solution using a distributed file system (DFS); the other is to use a relational database for data storage and distributed computing for data computation.

[0070] Distributed file systems (DFS) are a foundation for big data technologies that allow the construction of large clusters using multiple inexpensive hardware devices to process massive amounts of data. For example, Hive is a data warehouse tool based on Hadoop, used for data extraction, transformation, and loading (ETL). Hive defines a simple SQL-like query language and also allows for complex analysis tasks that the default tool cannot handle through custom MapReduce mappers and reducers. Hive does not have a specific data storage format or indexes; users can freely organize the tables and process the data in the database. Therefore, the parallel processing of distributed file management can meet the storage and processing requirements of massive amounts of data. Users can process simple data through SQL queries, while complex processing can be achieved using custom functions. Thus, when analyzing massive amounts of data from a factory, it is necessary to extract the data from the factory database into a distributed file system. This avoids damage to the original data and improves data analysis efficiency.

[0071] Relational databases can be any of Oracle, DB2, MySQL, Microsoft SQL Server, or Microsoft Access. Distributed computing breaks down a computing task into multiple subtasks, distributes these subtasks to multiple computer devices for simultaneous processing, and finally aggregates the processing results from each computer device into the final result.

[0072] For example, the distributed storage device 300 can be a single memory, multiple memories, or a collective term for multiple storage elements. For instance, the memory may include: Random Access Memory (RAM), Double Data Rate Synchronous Dynamic Random Access Memory (DDR SRAM), or non-volatile memory, such as disk storage, flash memory, etc.

[0073] The data processing device 100 can be any terminal device, server, virtual machine, or server cluster.

[0074] Display device 200 may be a monitor or a product that includes a monitor, such as a television, computer (all-in-one or desktop), computer, tablet computer, mobile phone, electronic display, etc. Exemplarily, the display device may be any device that displays images, whether moving (e.g., video) or fixed (e.g., still images), and whether text or images. More specifically, the embodiments described are contemplated to be implemented in or associated with a variety of electronic devices, such as (but not limited to) game consoles, television monitors, flat panel displays, computer monitors, automotive displays (e.g., odometer displays, etc.), navigators, cockpit controllers and / or displays, electronic photographs, electronic billboards or signs, projectors, architectural structures, packaging and aesthetic structures (e.g., a display of an image of a piece of jewelry), etc.

[0075] For example, the display device 200 described herein may include one or more displays, including one or more terminals with display functions, so that the data processing device 100 can send its processed data (e.g., influencing parameters) to the display device 200, which then displays it. In other words, through the interface (i.e., user interface) of the display device 200, the user can fully interact with the data processing system 10 (control and receive results).

[0076] It is understood that the functions of the aforementioned data processing device 100, display device 200, and distributed storage device 300 can be integrated into one or two electronic devices, or they can be implemented separately by different devices. This disclosure does not limit this.

[0077] The functions of the aforementioned data processing device 100, display device 200, and distributed storage device 300 can all be derived from, for example: Figure 3 The electronic device 30 shown is implemented. Figure 3 The electronic device 30 includes, but is not limited to, a processor 301, a memory 302, an input unit 303, an interface unit 304, and a power supply 305. Optionally, the electronic device 30 includes a display 306.

[0078] Processor 301 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 302, and by calling data stored in memory 302, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Processor 301 may include one or more processing units; optionally, processor 301 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 301.

[0079] The memory 302 can be used to store software programs and various data. The memory 302 may primarily include a program storage area and a data storage area, wherein the program storage area may store the operating system, application programs required by at least one functional unit, etc. Furthermore, the memory 302 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Optionally, the memory 302 may be a non-transitory computer-readable storage medium, such as read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage devices.

[0080] The input unit 303 can be a keyboard, touch screen, or other similar device.

[0081] Interface unit 304 serves as an interface for connecting external devices to electronic device 30. For example, external devices may include a wired or wireless headphone port, an external power supply (or battery charger) port, a wired or wireless data port, a memory card port, a port for connecting a device with an identification module, an audio input / output (I / O) port, a video I / O port, a headphone port, and so on. Interface unit 304 can be used to receive input (e.g., data information) from external devices and transmit the received input to one or more components within electronic device 30, or it can be used to transmit data between electronic device 30 and external devices.

[0082] The power supply 305 (e.g., a battery) can be used to power various components. Optionally, the power supply 305 can be logically connected to the processor 301 through a power management system, thereby enabling functions such as charging, discharging, and power consumption management through the power management system.

[0083] Display 306 is used to display information input by the user or information provided to the user (e.g., data processed by processor 301). Display 306 may include a display panel, which may be configured as a liquid crystal display (LCD), organic light-emitting diode (OLED), or similar device. When electronic device 30 is a display device 200, electronic device 30 includes display 306.

[0084] Optionally, the computer instructions in the embodiments of this disclosure may also be referred to as application code or system, and the embodiments of this disclosure do not specifically limit them.

[0085] It should be noted that, Figure 3 The electronic device shown is merely an example and does not constitute a limitation on the electronic devices applicable to the embodiments of this disclosure. In actual implementation, the electronic device may include more than […]. Figure 3 More or fewer devices or components as shown.

[0086] like Figure 4 The diagram shown is a flowchart of a data processing method provided in an embodiment of this disclosure. This method can be applied to... Figure 3 The electronic device shown, Figure 4 The method shown may include the following steps:

[0087] S100: The electronic device acquires the production record corresponding to each of the multiple samples; the production record includes process information, the corresponding production time, and indicator values. The process information consists of process parameters and / or process steps, and the indicator values ​​characterize the degree of defect of the sample belonging to a preset defect type. The multiple samples include defective samples, which are samples whose indicator values ​​are greater than a first threshold.

[0088] The first threshold can be preset based on experience, or the electronic device can determine the first threshold based on the distribution of index values ​​for each sample across multiple samples. For example, suppose the sample is glass used to produce panels, and the index value for the sample is the defect rate of the glass belonging to a preset defect type. The defect rate is the ratio of the number of defective panels produced from this glass to the total number of panels produced from this glass. If 90% of the glass in these multiple samples has a defect rate of 10%, then the electronic device determines the first threshold to be 10%.

[0089] Process parameters include at least one of temperature, pressure, or flow rate. Process steps can be identified by process identifiers and / or equipment identifiers.

[0090] In one possible implementation, the memory or distributed storage system stores a first correspondence between sample identifiers and indicator values, and a second correspondence between sample identifiers, process information, and production time corresponding to the process information. The electronic device retrieves the first and second correspondences from the memory or distributed storage system, and associates the indicator values ​​in the first correspondence, the process information in the second correspondence, and the production time corresponding to the process information with the sample identifier to obtain a third correspondence between the sample's process information, the production time corresponding to the process information, and the indicator value, thus obtaining the production records for the multiple samples.

[0091] For example, an electronic device retrieves the identifier of a specific model of display panel from the HBase database, and obtains the production record corresponding to each display panel based on the retrieved display panel identifier.

[0092] It should be noted that the sample in this embodiment can be a display panel from a display panel production line; of course, the sample in this embodiment can also be other products. The production record corresponding to the sample may also include a display panel motherboard (glass), which can be processed into multiple display panels.

[0093] The preset defect type refers to the type of quality defect in the sample, which may cause the sample's performance to fall below the performance threshold. This disclosure does not limit the method of classifying sample quality defects (also known as defects). For example, defects can be classified into different types as needed. For instance, they can be classified according to their direct impact on sample performance, such as bright line defects, dark line defects, and hot spot defects; or they can be classified according to their specific causes, such as signal line short circuit defects and alignment defects; or they can be classified according to their general causes, such as array process defects and color filter process defects; or they can be classified according to their severity, such as defects that lead to scrapping or defects that reduce quality; or, the type of defect can be disregarded, meaning that if a sample has any defect, it is considered defective, and vice versa. In this application, the defect type of each sample in multiple samples is the same.

[0094] In another possible implementation, the electronic device receives the production record corresponding to each of the multiple samples.

[0095] In one example, some data from the production records acquired by the electronic device is shown in Table 1 below. Table 1 uses statistical indicators such as thickness or electrical parameters as examples for illustration:

[0096] Table 1

[0097]

[0098] In Table 1, GlassID1 is the sample identifier, Step 1 is the process step that the sample represented by GlassID1 went through during the production process, VTH is the defect type of the sample represented by GlassID1, -2.14833 is the index value, and 2020-03-25 12:18:13 is the production time when the sample represented by GlassID1 went through Step 1 during the production process. Equipment 1 represents the equipment that the sample represented by GlassID1 went through during Step 1 during the production process. Where n is a positive integer. The rest are similar and will not be elaborated further.

[0099] In another example, some data from the production records acquired by the electronic device is shown in Table 2 below:

[0100] Table 2

[0101]

[0102] In Table 2, GlassID1 is the sample identifier, Step 1 is the process step that the sample represented by GlassID1 goes through during the production process, Parameter 1 is the configuration parameter of the sample represented by GlassID1 when it goes through Step 1, 457 is the value of Parameter 1, the index value 0.022 is the index value of the sample represented by GlassID1, and 2020-05-07 05:49:55 is the production time of the sample represented by GlassID1 when it goes through Step 1 during the production process. The rest are similar and will not be repeated. It should be noted that the values ​​of the process parameters and their corresponding production times can be collected based on a certain event trigger. In the embodiments of this disclosure, the values ​​of the process parameters and their corresponding production times of the sample can be: the value of one of the multiple process parameters and their corresponding production times of the sample collected, along with its corresponding production time.

[0103] It is understood that the production records acquired by the electronic device can be data already integrated into the above-described form. The electronic device can also, after receiving the original production data of the sample, integrate the sample's original production data into the above-described production record form based on the sample's identifier. This disclosure does not limit this aspect. It should be noted that the initial sources of the above-described indicator values ​​and process information are usually different. When the indicator values ​​and process information (such as process steps or process parameters) come from different data sources, the electronic device can associate the indicator values ​​with the process information through the sample identifier.

[0104] S101: The electronic equipment determines the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. The high-incidence period of defects is the period in which the probability of the distribution of defective samples is greater than the second threshold.

[0105] Specifically, when the process information is a process step, the electronic device classifies multiple samples into good samples and defective samples based on a first threshold and the indicator values ​​in the acquired production records. Then, the electronic device determines the time period in which the ratio of the number of defective samples to the total number of samples in the acquired production records is greater than a second threshold as a high-incidence period for defects, where the time period is the time period corresponding to the process information. The second threshold can be preset based on experience, or the electronic device can determine the second threshold based on the distribution of defective samples.

[0106] For example, the positive and negative samples after the electronic device is divided are as follows: Figure 5 As shown: Figure 5 The horizontal axis represents the time corresponding to each process step, and the vertical axis represents the index value of the sample. The first threshold is 0.1. It is understood that the horizontal axis can also represent process steps. This disclosure does not limit this aspect.

[0107] based on Figure 5 The period during which the example electronic devices were identified as having the highest incidence of malfunctions was from April 30, 2020 to May 1, 2020.

[0108] When the process information is process parameters, the electronic equipment obtains the first production time based on mutation point detection; the first production time is the mutation point of the indicator value in the obtained production record. The first production time is a time point in the period of high defect incidence.

[0109] For example, the electronic device obtains the time series x1, x2, x3, ..., x corresponding to the process parameters from the acquired production records. n The first production time was obtained using Pettitt mutation point detection. Pettitt mutation point detection is a non-parametric test method that not only identifies mutation points but also quantifies their statistical significance. This method directly utilizes rank-sum sequences to detect mutation points.

[0110] First, the statistical quantity U of electronic devices t，n U t，n Satisfy the following formula:

[0111]

[0112] Among them, U t，n Let x be a statistical measure, where n is the number of times corresponding to the process parameters in the obtained production records, and x is the number of times. i Let x1, x2, x3, ..., x n For each time interval, t is an integer greater than 2 and less than or equal to n. i is a positive integer greater than 1 and less than or equal to n. If there exists a time t that satisfies k t =max 1≤t＜n |U t，n | Then point t is the mutation point, k t For |U 1，n |to|U n，n The value with the largest absolute value in | If P ≤ 0.05, the detected mutation point is considered statistically significant. The production time corresponding to point t in electronic equipment is defined as the first production time. The first production time is the mutation point of the indicator value (also known as the high-incidence time point of defects).

[0113] For example, such as Figure 6 The indicator value shown suddenly decreased to below the third threshold of -2.5 on March 21, 2020. Samples with an indicator value below -2.5 are considered defective samples. The electronic equipment determined March 21, 2020, as the point of sudden change in the indicator value.

[0114] S102: Electronic equipment determines the degree of impact of process information on sudden defects based on the high-incidence period of defects and the obtained production records.

[0115] When the process information is defined as process steps, the electronic equipment determines the degree of impact of the process information on sudden defects through the following steps:

[0116] Step 1: Determine the target distribution of the index values ​​of samples in the production time corresponding to the process steps during the period of high incidence of defects in electronic equipment.

[0117] Specifically, the electronic equipment converts the production time values ​​corresponding to the process steps within the high-defect period into corresponding time values ​​for each process step. Then, the electronic equipment determines the target distribution of the indicator values ​​of the samples within the high-defect period across the corresponding time values ​​of the process steps.

[0118] Optionally, the electronic equipment uses a polynomial curve fitting method to fit the time values ​​corresponding to the process steps into fitting index values, and determines the distribution of the fitting index values ​​on the time values ​​as: the target distribution of the index values ​​of the samples in the process steps on the time values ​​during the period of high incidence of defects.

[0119] Optionally, the electronic device acquires the first difference value between the fitted index value and the index value of the sample. If the first difference value is less than or equal to the fourth threshold, step two is performed as follows. The first difference value is the largest difference value among the differences between the fitted index value and the corresponding sample index value. The fourth threshold can be set empirically.

[0120] For example, the fourth threshold is 0.6. The electronic device quantifies the production time corresponding to the process steps as t1, t2, t3, ..., tm, and uses a fourth-order polynomial curve fitting method to obtain x′1, x′2, x′3, ..., x′ for t1, t2, t3, ..., tm. m The index values ​​for the samples corresponding to t1, t2, t3, ..., tm are index values ​​x1, x2, x3, ..., xm, respectively. The corresponding x′ and t satisfy the formula x′=a0+a1t+a2t. 2 +a3t 3 If x′ i If the maximum error with the corresponding xi is greater than 0.6, it indicates that the analysis is not within the range of sudden adverse events. xi is any index value among x1, x2, x3, ..., xm. If x′ i If the maximum error with the corresponding xi is less than or equal to 0.6, then proceed to step two as follows.

[0121] Step 2: The electronic device determines a second difference value between the target distribution and the preset distribution; the second difference value is used to characterize the distribution probability of defective samples after this process step.

[0122] It is understandable that the preset distribution is a distribution derived from experience, and the preset distribution can be a standard normal distribution. Electronic devices use significance tests to obtain the difference between the target distribution and the standard normal distribution.

[0123] In one example, the electronic device transforms the standard normal distribution of the same time series into a probability density function, obtaining s1, s2, s3, ..., s m s1, s2, s3, ..., s m With x′1, x′2, x′3, ..., x′ m Significance tests were performed. The Mann-Whitney U test (a nonparametric test method) was used to determine the standard normal distribution (s1, s2, s3, ..., s...). m ) and the target distribution (x′1, x′2, x′3, ..., x′) m The difference between the two samples is calculated. Specifically, assuming two samples come from two identical populations except for their population means, the goal is to test whether there is a significant difference between the means of these two populations. First, the two sets of data (s1, s2, s3, ..., s...) are mixed. m ) and (x′1, x′2, x′3, ..., x′) m Sort all data and assign a rank to each set of data based on its numerical value. Then calculate the sum of the ranks of each of the two sets of data (s1, s2, s3, ..., s). m The rank sum of (x′1, x′2, x′3, ..., x′) is W1, (x′1, x′2, x′3, ..., x′). m The rank sum of the two sets of data is W2. Calculate the statistics U1, U2, U1, U2 and their corresponding W1, W2, satisfying the following formula:

[0124]

[0125]

[0126] Where m is the number of time points corresponding to the process steps in the production record, and W1 is s1, s2, s3, ..., s m The rank sum of W2 is x′1, x′2, x′3, ..., x′. m The electronic device selects the smaller of U1 and U2 as the threshold value between U and the preset threshold U. a Comparison, when U < U a When U is greater than or equal to U0, the above assumption is rejected, i.e., the difference between the target distribution and the standard normal distribution is large. a If we accept the above assumption that the two samples come from the same population, it means that the difference between the target distribution and the standard normal distribution is small.

[0127] like Figure 7 The image shows a comparison between the target distribution and the standard normal distribution. Figure 7 In the left-middle graph, the difference between the target distribution and the standard normal distribution is smaller than that in the right-middle graph.

[0128] Step 3: The electronic equipment determines the degree of impact of the process step on the sudden defect based on the difference value.

[0129] Specifically, based on the U determined by the electronic device in step two, the electronic device determines the degree of influence (p-value) of the process step on the sudden defect based on U. For example, the electronic device converts U into a value between 0 and 1 as the p-value. The larger the p-value, the less likely the above hypothesis can be rejected, and the difference is not statistically significant, that is, the two sets of data have the same distribution. Correspondingly, if there are no samples with low defect incidence rates interspersed during the sudden defect period, then the degree of influence of the process step on the sudden defect is greater.

[0130] Figure 7 The process steps in the left-middle diagram have a greater impact on sudden defects than the process steps in the right-middle diagram.

[0131] It should be noted that the fitted index values ​​obtained using the fourth-order polynomial curve fitting method yield more accurate results in judging the degree of influence of process steps on sudden defects. The preset distribution is a summary of the distribution law of the index values ​​of the samples under the condition of sudden defects. The preset distribution can be a standard normal distribution, or an exponential distribution, or other distribution types. This disclosure does not limit the types of distributions.

[0132] It is understood that the method for determining the impact of a process step on a sudden defect in this disclosure is based on the principle of consistency of the sample's index values ​​during the high-incidence period of a certain process step. That is, within the high-incidence period of a certain process step, the index values ​​of samples undergoing that process step show a high degree of concentration of variation. For example, if there are no samples with low defect rates interspersed within the high-incidence period of a first process step, but there are samples with low defect rates interspersed within the high-incidence period of a second process step, then the impact of the first process step on the sudden defect is greater than the impact of the second process step.

[0133] When the process information is process parameters, the electronic equipment determines the degree of impact of the process parameters on sudden defects through the following steps:

[0134] Step 1: The electronic device acquires the critical change point of the process parameters in the production record and determines the time corresponding to the critical change point as the second production time.

[0135] In one possible implementation, the electronic device acquires the Gini coefficient of the process parameters in the production record, determines the value of the process parameter with the smallest Gini coefficient as the critical change point of the process parameter, and determines the time corresponding to the critical change point as the second production time.

[0136] Specifically, the electronic equipment uses each value of the process parameter in the production record as a cutpoint, calculates the Gini coefficient corresponding to each cutpoint, obtains multiple Gini coefficients, and determines the value of the process parameter with the smallest Gini coefficient as the critical change point of the process parameter, and determines the time corresponding to the critical change point as the second production time.

[0137] In one example, the electronic device is sorted by the values ​​of the target process parameters, resulting in an array effect_data = [x1, x2, x3, ..., x...]. n The index value corresponding to the sample for each target process parameter is obtained as cause_data = [y1, y2, y3, ..., y]. n ]; Electronic devices access y1, y2, y3, ..., y in cause_data n Calculate the Gini coefficient separately, take the value of the process parameter with the smallest Gini coefficient as the mutation point, and take the time corresponding to the mutation point as the second production time.

[0138] Step 2: The electronic equipment determines the difference between the first production time and the second production time, and determines the degree of influence of process parameters on sudden defects based on this difference.

[0139] For example, suppose the absolute value of the difference between the first production time and the second production time of the first process parameter is 0.5 hours, and the absolute value of the difference between the first production time and the second production time of the second process parameter is 8 hours. Then, the influence of the first process parameter on sudden defects is greater than the influence of the second process parameter. In practical applications, electronic devices can preset time thresholds. If the difference between the first and second production times is greater than the time threshold, the influence of the process parameter of the second production time on sudden defects is determined to be 0, meaning that the process parameter has no effect on sudden defects. If the absolute value of the difference between the first and second production times is less than or equal to the time threshold, the electronic device determines the influence of the process parameter of the second production time on sudden defects to be 1, meaning that the process parameter has an influence on sudden defects.

[0140] It should be noted that in the process of determining the influence of process parameters on sudden defects in the embodiments of this disclosure, the electronic device can analyze each process parameter, or it can be done as follows: First, the electronic device determines the process step to be analyzed based on the influence of the process step on the sudden defect as determined above. The electronic device then analyzes the process parameters under the process step to be analyzed to determine the influence of multiple process parameters on the sudden defect. In this way, the influence of fewer process parameters on the sudden defect can be determined, thereby improving the efficiency of locating the cause of the sudden defect.

[0141] Optionally, S103: The electronic device acquires the Gini coefficient of process information from the production records. The Gini coefficient of process information is used to characterize the degree of correlation between process information and the index values ​​of the sample; based on the Gini coefficient of process information, the degree of influence of process information on sudden defects is determined.

[0142] When the process information is a process step, the electronic device retrieves the process step and indicator value corresponding to the sample identifier from the production record, and obtains the Gini coefficient of that process step based on the process step and indicator value. The electronic device then determines the degree of impact of the process step on the sudden defect based on the Gini coefficient of the process step.

[0143] Assuming the first process step is a child node in the decision tree, representing a binary classification feature attribute, its negative impact on the sample is either "affected" or "unaffected." Electronic devices can use the Gini coefficient, a measure of impurities in CART trees, to calculate the degree of influence of each process step on the resulting sample's index value. A smaller Gini coefficient indicates less uncertainty and a greater degree of influence. In a K-class classification problem, for a given set of samples D, the Gini coefficient is... C K These are samples belonging to class K in D. This embodiment of the disclosure is a binary classification problem, where the total number of samples after the first process step is D, C. K Gini(D) represents the number of defective samples in D. Gini(D) reflects, to some extent, the impact of the first process step on sample defects.

[0144] Optionally, the electronic device performs a chi-square test on the process step in the production record to obtain the chi-square test value of the process step on the index value of the sample. The chi-square test value is used to characterize the degree of influence of the process step on the index value of the sample. Then, the electronic device determines the degree of influence of the process step on the sudden defect based on the first preset weight, the chi-square test value and the Gini coefficient of the process step.

[0145] Understandably, in statistics, the chi-square test measures the deviation between the actual observed values ​​and the theoretically predicted values ​​of a statistical sample. The degree of deviation determines the size of the chi-square value; a larger chi-square value indicates a greater discrepancy between the actual and theoretical values, while a smaller chi-square value indicates a smaller deviation and a closer alignment between the actual and theoretical values. The fundamental idea of ​​the chi-square test is to determine the correctness of a theory by observing the deviation between the actual and theoretical values. The chi-square test value satisfies the formula... This formula represents the degree of deviation between the theoretical value E and the actual value x in n samples. For the embodiments of this disclosure, for device 1 represented by a certain device identifier, it is assumed that device 1 has no impact on the defects of the samples; they are independent and uncorrelated. The actual index values ​​of the samples processed by device 1 are shown in Table 3 below. Therefore, the theoretical value can be calculated based on the overall sample defect rate, and the chi-square test value can be obtained from the above formula. Substituting the chi-square test value into the probability density function for calculating the chi-square distribution yields pValue.

[0146] Table 3

[0147]

[0148]

[0149] In Table 3, subbad represents the number of defective samples that passed through equipment 1, subgood represents the number of good samples that passed through equipment 1, totalbad-subbad represents the number of defective samples that did not pass through equipment 1, and totalgood-subgood represents the number of good samples that passed through equipment 1.

[0150] It is understandable that the electronic device can use the chi-square test value or the Gini coefficient corresponding to process step 1 as the degree of influence of process step 1 on the sample's index value. Alternatively, the electronic device can determine the degree of influence of the process step on the sudden defect based on the first preset weight, the chi-square test value, and the Gini coefficient of the process step. For example, the first preset weight is 0.5 and 0.5. The electronic device obtains the first product of the chi-square test value and 0.5, and the electronic device obtains the second product of the Gini coefficient and 0.5. The sum of the first product and the second product is used as the degree of influence of the process step on the sudden defect.

[0151] When the process information is process parameters, the electronic device obtains the process parameters and index values ​​corresponding to the sample identifier from the production record, and obtains the Gini coefficient of the process parameters based on the process parameters and index values ​​corresponding to the sample identifier. Then, the electronic device determines the degree of influence of the process parameters on the sudden defect based on the Gini coefficient of the process parameters.

[0152] Specifically, the method for obtaining the Gini coefficient of the process parameters is described above and will not be repeated here.

[0153] Optionally, the electronic device performs a correlation test on the process parameters and sample index values ​​in the production record to obtain the influence parameter of the process parameter. The influence parameter is used to characterize the degree of influence of the process parameter on the sample index value. Then, the electronic device obtains the degree of influence of the process parameter on the sudden defect based on the second preset weight, the influence parameter and the Gini coefficient of the process parameter. The correlation test can be at least one of the following: normality test, homogeneity of variance test or T-test.

[0154] For example, the second preset weight of the influencing parameter is 0.4 and the second preset weight of the Gini coefficient of the process parameter is 0.6. The electronic device obtains the third product of the influencing parameter and 0.4, and the electronic device obtains the fourth product of the Gini coefficient of the process parameter and 0.6. The sum of the third product and the fourth product is used as the degree of influence of the process parameter on the sudden defect.

[0155] like Figure 8 The diagram shows a flowchart from S100 to S102 in the above embodiment of this disclosure. The electronic device obtains the result variables (i.e., the aforementioned index values) based on the acquired production records. Then, the electronic device obtains the causal variables and divides them into continuous causal variables (e.g., the aforementioned process parameters) and discrete causal variables (e.g., the aforementioned process steps). For continuous causal variables, the electronic device uses mutation point detection to determine the high-incidence time points of defects in the result variables and the critical change points in the continuous causal variables. Based on the high-incidence time points and critical change points, the influence of continuous causal variables on sudden defects is determined. For discrete causal variables, the electronic device locates the time periods of high defect incidence and fits the result variables and causal variables within the high-incidence time periods. The fitting results are then compared with a standard normal distribution for significance testing to obtain the influence of discrete causal variables on sudden defects. The diagram comprehensively displays the influence of discrete causal variables on sudden defects and the influence of continuous causal variables on sudden defects.

[0156] It is understood that the final result determined in this embodiment is the degree of influence of each process parameter among multiple process parameters on the sudden defect, and / or the degree of influence of each process step among multiple process steps on the sudden defect. The electronic device displays the determined result, so that the user can judge one or more process information with the greatest influence on the sudden defect from the displayed result in order to locate the cause of the sudden defect.

[0157] It is understood that, in this embodiment of the disclosure, the electronic device may acquire the source production information of each of the multiple samples only once (e.g., the sample identifier and the index value represented by the sample identifier stored in one device, and the sample identifier and the process information corresponding to the sample identifier stored in several other devices), and store it on the electronic device or other intermediate device. In the above-described different steps, during the data acquisition process (e.g., acquiring production records, process steps, process parameters, production time, etc.), the electronic device can acquire data from the electronic device or other devices storing the production information of the multiple samples, thus accelerating the data processing speed. This embodiment of the disclosure does not limit the data storage format; for example, the data storage can be in Parquet format.

[0158] In this embodiment of the disclosure, the electronic device determines the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. Then, based on the high-incidence period of defects and the acquired production records, the electronic device determines the degree of influence of the process information on the sudden defects. This allows the device to mine the correlation influence of the time trend of the sudden defects in the sample and quantify it into a numerical value. This provides users with more accurate and comprehensive data to locate the cause of the defects.

[0159] like Figure 9 The diagram shown is a flowchart of another data processing method provided in an embodiment of this disclosure. This method can be applied to... Figure 3 The electronic device shown, Figure 9 The method shown may include the following steps:

[0160] S200: The electronic device receives sample screening conditions input by the user on the condition selection interface. These conditions include at least one of the following: product model, testing site, production time period, process identifier, equipment identifier, process parameters, or defect type.

[0161] For example, the condition selection interface displayed on the electronic device is as follows: Figure 10 As shown, Figure 10 The A section includes input boxes for time periods, testing sites, product models, and processes (i.e., technological steps). Figure 10 B is the input box for the defect type interface. Figure 10The raw materials can be panel master sheets. The testing station can be selected by the user. The testing station includes at least six defect types: Type 1 defect number can be selected by the user as the defect number of samples of Type 1; Type 1 defect rate can be selected by the user as the defect rate of samples of Type 1; Type 1 raw material defect rate can be selected by the user as the defect rate of raw material of Type 1; Type 2 defect number can be selected by the user as the defect number of samples of Type 2; Type 2 defect rate can be selected by the user as the defect rate of samples of Type 2; Type 2 raw material defect rate can be selected by the user as the defect rate of raw material of Type 2.

[0162] Optionally, the filtering criteria may also include causal variables. For example, the causal variable input interface displayed on the electronic device may look like this: Figure 11 As shown. Figure 11 The raw materials used can be panel master plates. Figure 11 The testing sites in the document are those that can be selected by the user, and the product can be the product model that the user can select. Figure 11 The process identifier can be used by users to select the corresponding process; one process corresponds to at least one process step. Figure 11 Both process step identifier 1 and process step identifier 2 can be used by users to select process steps. Figure 11 The process step identified as process step 2 corresponds to at least three pieces of equipment. Specifically, equipment 1 corresponds to one piece of equipment, equipment 2 corresponds to one piece of equipment, and equipment 3 corresponds to one piece of equipment.

[0163] S201: The electronic device acquires the production record of each sample among multiple samples corresponding to the sample screening conditions; the production record includes process information, the production time corresponding to the process information, and the index value; the process information is process parameters or process steps; the index value is used to characterize the degree of defect of the sample belonging to the preset defect type; the multiple samples include defective samples, and defective samples are samples whose index values ​​are greater than the first threshold.

[0164] Specifically, refer to the method of obtaining production records by electronic devices in S100 above, which will not be repeated here.

[0165] In this embodiment of the disclosure, the indicator value can be the defect rate or the number of defects of the defect type. This embodiment of the disclosure can use Qtest measurement data (such as thickness and electrical parameters) to determine whether a sample is good or defective based on whether the data meets the standards.

[0166] S202: The electronic equipment determines the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. The high-incidence period of defects is the period in which the probability of the distribution of defective samples is greater than the second threshold.

[0167] For details, please refer to the description in S101 above and will not be repeated here.

[0168] S203: Electronic equipment determines the degree of impact of process information on sudden defects based on the high-incidence period of defects and the obtained production records.

[0169] For details, please refer to the description in S102 above, and will not be repeated here.

[0170] S204: Electronic equipment displays the degree of impact of process information on sudden defects in the analysis results.

[0171] Optionally, firstly, the electronic device sorts the impact of multiple acquired process information on the sudden defect, and then displays the sorted process information on the analysis results display interface to show the impact of the sudden defect.

[0172] For example, the electronic device sorts the impact of multiple pieces of process information on sudden defects in descending order and displays the sorted impact of the process information on sudden defects. In this way, the information with the greatest impact on sudden defects will be listed first for easy viewing by the user.

[0173] Understandably, the electronic device can determine and display a quantified value of the impact of a particular process step on the sudden defect based on preset weights and quantified values ​​of the impact of multiple process steps on the sudden defect. Alternatively, the electronic device can display the quantified value of the impact of each process step on the sudden defect separately. Similarly, the electronic device can determine and display a quantified value of the impact of a particular process parameter on the sudden defect based on preset weights and quantified values ​​of the impact of multiple process parameters on the sudden defect. Alternatively, the electronic device can display the quantified value of the impact of each process parameter on the sudden defect separately.

[0174] like Figure 12 The figure shows the quantitative value of the impact of the device identifier displayed by the electronic device in the analysis results display interface on the degree of impact of the sudden failure. Figure 12 The number 16 below the serial number indicates the serial number of this row of data, and "device 1" is the device identifier. The first impact quantification value of 0.9397 is the quantification value of the impact of device 1 on the sudden failure. The second impact quantification value of 0.012293 is another quantification value of the impact of device 1 on the sudden failure, obtained from the time dimension analysis. The rest are similar and will not be described in detail.

[0175] The foregoing primarily describes the solutions provided by the embodiments of this disclosure from a methodological perspective. To achieve the aforementioned functions, it includes corresponding hardware structures and / or software modules for executing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this disclosure can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0176] This disclosure embodiment can divide the electronic device in the above embodiments into functional modules according to the above method examples. For example, each function can be divided into a separate functional module, or two or more functions can be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this disclosure embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0177] like Figure 13 The diagram shows the structure of a data processing device 70 provided in an embodiment of this disclosure. The data processing device 70 includes: an acquisition module 701, a first determination module 702, and a second determination module 703. The acquisition module 701 acquires the production record corresponding to each sample from a plurality of samples; the production record includes process information, the corresponding production time, and an indicator value; the process information is process parameters and / or process steps; the indicator value characterizes the degree of defect of a sample belonging to a preset defect type; the plurality of samples includes defective samples, which are samples with indicator values ​​greater than a first threshold; the first determination module 702 determines a high-incidence period for defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information, where the high-incidence period is the period when the distribution probability of defective samples is greater than a second threshold; the second determination module 703 determines the degree of influence of process information on sudden defects based on the high-incidence period for defects and the acquired production records. For example: combined with... Figure 4 The acquisition module 701 can be used to execute S100, the first determination module 702 can be used to execute S101, and the second determination module 703 can be used to execute S102.

[0178] In some embodiments, when the process information is a process step, the second determining module 703 is specifically used to: determine the target distribution of the index values ​​of the samples in the production time corresponding to the process step during the high-incidence period of defects; determine the difference value between the target distribution and the preset distribution; the difference value is used to characterize the distribution probability of defective samples after the process step; and determine the degree of influence of the process step on the sudden defect based on the difference value.

[0179] In other embodiments, the second determining module 703 is specifically used to: convert the production time value corresponding to the process step into the time value corresponding to the process step; and determine the target distribution of the index value of the sample in the time value corresponding to the process step during the period of high defect incidence.

[0180] In other embodiments, the second determining module 703 is specifically used to: use a polynomial curve fitting method to fit the time values ​​corresponding to the process steps into fitting index values; and determine the distribution of the fitting index values ​​on the time values ​​as: the target distribution of the index values ​​of the samples in the process steps on the time values ​​during the period of high incidence of defects.

[0181] In other embodiments, the preset distribution is a standard normal distribution; the target distribution is a multinomial distribution; the second determining module 703 is specifically used to: obtain the difference value between the target distribution and the standard normal distribution using a significance test.

[0182] In other embodiments, the first determining module 702 is specifically used to: divide multiple samples into good samples and bad samples according to a first threshold and the indicator values ​​in the acquired production records; determine the time period in which the ratio of the number of bad samples in the production records to the total number of samples is greater than a second threshold as the high-incidence time period of defects; the time period is the time period corresponding to the process information.

[0183] In other embodiments, when the process information is process parameters, the acquisition module 701 is further configured to: acquire a first production time by mutation point detection; the first production time is the mutation time point of the index value; the first production time is a time point in the period of high incidence of defects; acquire the critical change point of the process parameters in the production record, and determine the time corresponding to the critical change point as the second production time; the second determination module 703 is specifically configured to determine the difference between the first production time and the second production time, and determine the degree of influence of the process parameters on the sudden defect based on the difference.

[0184] In other embodiments, the acquisition module 701 is further configured to: acquire the Gini coefficient of the process parameters in the production record; and determine the value of the process parameter with the smallest Gini coefficient as the critical change point of the process parameter.

[0185] In other embodiments, the acquisition module 701 is further configured to: acquire the Gini coefficient of process information in the production record; the Gini coefficient of process information is used to characterize the degree of correlation between process information and the index value of the sample; the second determination module 703 is specifically configured to: determine the degree of influence of process information on sudden adverse events based on the Gini coefficient of process information.

[0186] In other embodiments, the production record also includes a sample identifier. When the process information is a process parameter, the acquisition module 701 is specifically used to: acquire the process parameter and index value corresponding to the sample identifier from the production record; and acquire the Gini coefficient of the process parameter based on the process parameter and index value corresponding to the sample identifier.

[0187] In other embodiments, the production record also includes a sample identifier. When the process information is a process step, the acquisition module 701 is specifically used to: acquire the process step and index value corresponding to the sample identifier from the production record; and acquire the Gini coefficient of the process step based on the process step and index value corresponding to the sample identifier.

[0188] In other embodiments, the data processing device further includes an inspection module 704, which performs a chi-square test on the process steps in the production record to obtain the chi-square test value of the process step on the index value of the sample. The chi-square test value is used to characterize the degree of influence of the process step on the index value of the sample. The second determination module 703 is specifically used to determine the degree of influence of the process step on the sudden defect based on the first preset weight, the chi-square test value and the Gini coefficient of the process step.

[0189] In other embodiments, the inspection module 704 is further configured to: perform correlation inspection on the process parameters and the index values ​​of the samples in the production record to obtain the influence parameters of the process parameters; the influence parameters are used to characterize the degree of influence of the process parameters on the index values ​​of the samples; the second determination module 703 is specifically configured to: obtain the degree of influence of the process parameters on the sudden defects based on the second preset weight, the influence parameters and the Gini coefficient of the process parameters.

[0190] In some embodiments, the acquisition module 701 is specifically used to: acquire a first correspondence between the sample identifier and the indicator value of each sample in a plurality of samples, and acquire a second correspondence between the sample identifier, process information and the production time corresponding to the process information of each sample; and establish a third correspondence between the process information, the production time corresponding to the process information and the indicator value of each sample based on the sample identifier, the first correspondence and the second correspondence of each sample.

[0191] In one example, see Figure 3 The receiving function of the aforementioned acquisition module 701 can be provided by Figure 3The interface unit 304 in the above-mentioned acquisition module 701, the first determination module 702, the second determination module 703, and the verification module 704 can be implemented by... Figure 3 The processor 301 calls the computer program stored in the memory 302 to implement it.

[0192] For a detailed description of the above-mentioned optional methods, please refer to the foregoing method embodiments, which will not be repeated here. Furthermore, the explanation of the data processing apparatus 70 in any of the application examples provided above, as well as the description of its beneficial effects, can be found in the corresponding method embodiments above, and will not be repeated here.

[0193] It should be noted that the actions performed by each module mentioned above are merely specific examples; the actual actions performed by each unit should refer to the above examples. Figure 4 The actions or steps mentioned in the description of the embodiments.

[0194] like Figure 14 The diagram shows the structure of another data processing device 80 provided in this embodiment of the present disclosure. The data processing device 80 includes a receiving module 801, an acquisition module 802, a determining module 803, and a display module 804. The receiving module 801 receives sample screening conditions input by a user on a condition selection interface. The acquisition module 802 acquires the production record of each sample among multiple samples corresponding to the sample screening conditions. The production record includes process information, the corresponding production time, and an indicator value. The process information includes process parameters and / or process steps. The indicator value characterizes the degree of defect of a sample belonging to a preset defect type. The multiple samples include defective samples, which are samples with an indicator value greater than a first threshold. The determining module 803 determines the high-incidence period of defects based on the indicator value in the acquired production record and the time corresponding to the process information. The high-incidence period of defects is the period when the distribution probability of defective samples is greater than a second threshold. Based on the high-incidence period of defects and the acquired production record, the module determines the degree of influence of process information on sudden defects. The display module 804 displays the degree of influence of process information on sudden defects on the analysis result display interface. For example, combined with… Figure 9 The receiving module 801 can be used to execute S200, the acquiring module 802 can be used to execute S201, the determining module 803 can be used to execute S202 to S203, and the display module 804 can be used to execute S204.

[0195] In some embodiments, the data processing apparatus further includes: a sorting module 805, used to sort the degree of influence of multiple acquired process information on sudden defects; and a display module 804 specifically used to: display the degree of influence of the sorted process information on sudden defects on the analysis result display interface.

[0196] In one example, see Figure 3The receiving functions of the aforementioned receiving module 801 and acquiring module 802 can be provided by... Figure 3 The interface unit 304 in the above is used for implementation. The processing functions of the acquisition module 802, the determination module 803, and the sorting module 805 can be implemented by... Figure 3 The processor 301 calls the computer program stored in the memory 302 to implement this. The display module 804 can be... Figure 3 The display 306 is implemented in the middle.

[0197] For a detailed description of the above-mentioned optional methods, please refer to the foregoing method embodiments, which will not be repeated here. Furthermore, the explanation of the data processing apparatus 80 in any of the application examples provided above, as well as the description of its beneficial effects, can be found in the corresponding method embodiments above, and will not be repeated here.

[0198] It should be noted that the actions performed by each module mentioned above are merely specific examples; the actual actions performed by each unit should refer to the above examples. Figure 9 The actions or steps mentioned in the description of the embodiments.

[0199] This disclosure also provides an electronic device, including: a processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the data processing method described in any of the above embodiments.

[0200] Some embodiments of this disclosure provide a computer-readable storage medium (e.g., a non-transitory computer-readable storage medium) storing computer program instructions that, when executed on a processor, cause the processor to perform one or more steps of a data processing method as described in any of the above embodiments.

[0201] For example, the aforementioned computer-readable storage media may include, but are not limited to: magnetic storage devices (e.g., hard disks, floppy disks, or magnetic tapes), optical discs (e.g., CDs (Compact Disks), DVDs (Digital Versatile Disks), etc.), smart cards, and flash memory devices (e.g., EPROMs (Erasable Programmable Read-Only Memory), cards, sticks, or key drives, etc.). The various computer-readable storage media described in this disclosure may represent one or more devices for storing information and / or other machine-readable storage media. The term "machine-readable storage media" may include, but is not limited to, wireless channels and various other media capable of storing, containing, and / or carrying instructions and / or data.

[0202] Some embodiments of this disclosure also provide a computer program product. This computer program product includes computer program instructions that, when executed on a computer, cause the computer to perform one or more steps of the data processing method as described in the above embodiments.

[0203] Some embodiments of this disclosure also provide a computer program. When executed on a computer, the computer program causes the computer to perform one or more steps of the data processing method as described in the above embodiments.

[0204] The beneficial effects of the aforementioned computer-readable storage medium, computer program product, and computer program are the same as the beneficial effects of the data processing methods described in some of the above embodiments, and will not be repeated here.

[0205] The above description is merely a specific embodiment of this disclosure, but the scope of protection of this disclosure is not limited thereto. Any variations or substitutions conceived by those skilled in the art within the scope of the technology disclosed in this disclosure should be included within the scope of protection of this disclosure. Therefore, the scope of protection of this disclosure should be determined by the scope of the claims.

Claims

1. A data processing method, characterized in that, include: Obtain the production record for each sample from multiple samples; the production record includes process information, the corresponding production time for the process information, and indicator values; The process information includes process parameters and / or process steps; the index value is used to characterize the degree of defect of a sample belonging to a preset defect type; the multiple samples include defective samples, and the defective samples are those whose index values ​​are greater than a first threshold. Based on the indicator values ​​in the obtained production records and the time corresponding to the process information, the high-incidence period of defects is determined. The high-incidence period of defects is the period when the distribution probability of defective samples is greater than the second threshold. Based on the high-incidence period of the defect and the obtained production records, determine the degree of impact of the process information on the sudden defect; When the process information is the process step, determining the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records includes: Determine the target distribution of the index values ​​of the samples during the high-incidence period of defects over the production time corresponding to the process step; Determine the difference between the target distribution and the preset distribution; the difference is used to characterize the distribution probability of defective samples after the process step; The degree of impact of the process step on the sudden defect is determined based on the difference value; When the process information is the process parameter, determining the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records includes: The first production time is obtained by mutation point detection; the first production time is the mutation time point of the indicator value; the first production time is a time point within the period of high defect incidence. Obtain the critical change point of the process parameter in the production record, and determine the time corresponding to the critical change point as the second production time; The difference between the first production time and the second production time is determined, and the degree of influence of the process parameters on sudden defects is determined based on the difference.

2. The data processing method according to claim 1, characterized in that, Determining the target distribution of the index values ​​of samples within the high-incidence period of defects over the production time corresponding to the process step includes: The production time corresponding to the process step is converted into the time value corresponding to the process step. Determine the target distribution of the index values ​​of the samples during the high-incidence period of defects on the time values ​​corresponding to the process steps.

3. The data processing method according to claim 2, characterized in that, Determining the target distribution of the index values ​​of samples within the high-incidence period of defects over the time values ​​corresponding to the process steps includes: The time values ​​corresponding to the process steps are fitted to fitting index values ​​using a polynomial curve fitting method. The distribution of the fitted index values ​​over time is defined as: the target distribution of the index values ​​of the samples during the high-incidence period of defects over the time values ​​corresponding to the process steps.

4. The data processing method according to claim 1, characterized in that, The preset distribution is a standard normal distribution; the target distribution is a multinomial distribution; determining the difference between the target distribution and the preset distribution includes: The difference between the target distribution and the standard normal distribution is obtained by using a significance test.

5. The data processing method according to claim 1, characterized in that, The step of determining the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information includes: Based on the first threshold and the indicator values ​​in the acquired production records, the multiple samples are divided into good samples and bad samples. The time period in which the ratio of the number of defective samples to the total number of samples in the production records is greater than the second threshold is defined as the high-incidence period of defects.

6. The data processing method according to claim 1, characterized in that, The step of obtaining the critical change point of the process parameter in the production record includes: Obtain the Gini coefficient of the process parameters in the production record; The value of the process parameter that minimizes the Gini coefficient is determined as the critical change point of the process parameter.

7. The data processing method according to claim 1, characterized in that, The method further includes: Obtain the Gini coefficient of the process information in the production record; the Gini coefficient of the process information is used to characterize the degree of correlation between the process information and the index value of the sample; The degree of influence of the process information on the sudden defect is determined based on the Gini coefficient of the process information.

8. The data processing method according to claim 7, characterized in that, The method further includes: A chi-square test is performed on the process steps in the production record to obtain the chi-square test value of the process step on the index value of the sample. The chi-square test value is used to characterize the degree of influence of the process step on the index value of the sample. The degree of influence of the process step on the sudden defect is determined based on the first preset weight, the chi-square test value, and the Gini coefficient of the process step.

9. The data processing method according to claim 7, characterized in that, The method further includes: A correlation test is performed on the process parameters and sample index values ​​in the production records to obtain the influence parameters of the process parameters; the influence parameters are used to characterize the degree of influence of the process parameters on the sample index values. The degree of influence of the process parameters on sudden defects is obtained based on the second preset weight, the influence parameter, and the Gini coefficient of the process parameters.

10. The data processing method according to any one of claims 1-9, characterized in that, The step of obtaining the production record corresponding to each sample among multiple samples includes: Obtain the first correspondence between the sample identifier and the indicator value for each sample in the multiple samples, and obtain the second correspondence between the sample identifier, process information, and the production time corresponding to the process information for each sample; Based on the sample identifier of each sample, the first correspondence, and the second correspondence, a third correspondence is established for the process information, the production time corresponding to the process information, and the index value of each sample.

11. A data processing method, characterized in that, include: Receive sample filtering conditions entered by the user in the condition selection interface; Obtain the production record for each sample from multiple samples corresponding to the sample selection criteria; the production record includes process information, the production time corresponding to the process information, and indicator values; The process information includes process parameters and / or process steps; the index value is used to characterize the degree of defect of a sample belonging to a preset defect type; the multiple samples include defective samples, and the defective samples are those whose index values ​​are greater than a first threshold. Based on the indicator values ​​in the obtained production records and the time corresponding to the process information, the high-incidence period of defects is determined. The high-incidence period of defects is the period when the distribution probability of defective samples is greater than the second threshold. Based on the high-incidence period of the defect and the obtained production records, determine the degree of impact of the process information on the sudden defect; When the process information is the process step, determining the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records includes: Determine the target distribution of the index values ​​of the samples during the high-incidence period of defects over the production time corresponding to the process step; Determine the difference between the target distribution and the preset distribution; the difference is used to characterize the distribution probability of defective samples after the process step; The degree of impact of the process step on the sudden defect is determined based on the difference value; When the process information is the process parameter, determining the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records includes: The first production time is obtained by mutation point detection; the first production time is the mutation time point of the indicator value; the first production time is a time point within the period of high defect incidence. Obtain the critical change point of the process parameter in the production record, and determine the time corresponding to the critical change point as the second production time; Determine the difference between the first production time and the second production time, and determine the degree of influence of the process parameters on sudden defects based on the difference; The analysis results display interface shows the degree of impact of the process information on sudden defects.

12. The data processing method according to claim 11, characterized in that, The analysis results display interface shows the degree of impact of the process information on sudden defects, including: The impact of the acquired process information on the sudden defect is ranked. The analysis results display interface shows the degree of impact of the sorted process information on sudden defects.

13. A data processing apparatus, characterized in that, include: The acquisition module is used to acquire the production record corresponding to each sample among multiple samples; Production records include process information, the corresponding production time for the process information, and indicator values; The process information includes process parameters and / or process steps; the index value is used to characterize the degree of defect of a sample belonging to a preset defect type; the multiple samples include defective samples, and the defective samples are those whose index values ​​are greater than a first threshold. The first determining module is used to determine the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. The high-incidence period of defects is the period in which the distribution probability of defective samples is greater than a second threshold. The second determining module is used to determine the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records; When the process information is the process step, determining the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records includes: Determine the target distribution of the index values ​​of the samples during the high-incidence period of defects over the production time corresponding to the process step; Determine the difference between the target distribution and the preset distribution; the difference is used to characterize the distribution probability of defective samples after the process step; The degree of impact of the process step on the sudden defect is determined based on the difference value; When the process information is the process parameter, determining the degree of impact of the process information on the sudden defect based on the high-incidence period of the defect and the obtained production records includes: The first production time is obtained by mutation point detection; the first production time is the mutation time point of the indicator value; the first production time is a time point within the period of high defect incidence. Obtain the critical change point of the process parameter in the production record, and determine the time corresponding to the critical change point as the second production time; The difference between the first production time and the second production time is determined, and the degree of influence of the process parameters on sudden defects is determined based on the difference.

14. A data processing apparatus, characterized in that, include: The receiving module is used to receive the sample filtering conditions entered by the user in the condition selection interface; The acquisition module is used to acquire the production record of each sample among multiple samples corresponding to the sample screening conditions; the production record includes process information, the production time corresponding to the process information, and indicator values; The process information includes process parameters and / or process steps; the index value is used to characterize the degree of defect of a sample belonging to a preset defect type; the multiple samples include defective samples, and the defective samples are those whose index values ​​are greater than a first threshold. The determination module is used to determine the high-incidence period of defects based on the indicator values ​​in the acquired production records and the time corresponding to the process information. The high-incidence period of defects is the period in which the distribution probability of defective samples is greater than a second threshold. Based on the high-incidence period of defects and the acquired production records, the module determines the degree of influence of the process information on sudden defects. When the process information is the process step, determining the degree of influence of the process information on the sudden defect based on the high-incidence period of defects and the acquired production records includes: determining the target distribution of the index values ​​of the samples within the high-incidence period of defects on the production time corresponding to the process step; determining the difference between the target distribution and the preset distribution; the difference is used to characterize the distribution probability of defective samples after the process step; determining the degree of influence of the process step on the sudden defect based on the difference; when the process information is the process parameter, determining the degree of influence of the process information on the sudden defect based on the high-incidence period of defects and the acquired production records includes: using mutation point detection to obtain a first production time; the first production time is the mutation time point of the index value; the first production time is a time point within the high-incidence period of defects; obtaining the critical change point of the process parameter in the production records, and determining the time corresponding to the critical change point as the second production time; determining the difference between the first production time and the second production time, and determining the degree of influence of the process parameter on the sudden defect based on the difference; The display module is used to show the degree of impact of the process information on the sudden adverse event on the analysis results display interface.

15. An electronic device, characterized in that, include: A processor and a memory for storing processor-executable instructions; wherein the processor is configured to execute the executable instructions to implement the data processing method as claimed in any one of claims 1-10, or to implement the data processing method as claimed in claim 11 or 12.

16. A computer-readable storage medium, characterized in that, When the instructions in the computer-readable storage medium are executed by the processor of the electronic device, the electronic device is able to perform the data processing method as described in any one of claims 1-10, or perform the data processing method as described in claim 11 or 12.

17. A computer program product, characterized in that, The computer program product includes computer instructions that, when executed on a computer device, cause the computer device to perform the data processing method as described in any one of claims 1-10, or to perform the data processing method as described in claim 11 or 12.

Images