Data monitoring method, device, electronic device and storage medium

Abstract

The present application discloses a data monitoring method, device, electronic device and storage medium. The monitoring method includes: obtaining the original data of the detection process and preprocessing the original data of the detection process to obtain multiple groups of defect data, establishing a data monitoring model and using the data monitoring model to monitor the multiple groups of defect data, and determining the defect fluctuation data according to the monitoring results of the data monitoring model. In the data monitoring method of the present application, the original data of the detection process is processed to obtain multiple groups of defect data, and the multiple groups of defect data are monitored by the data monitoring model, so that the defect fluctuation data in the production process can be monitored in a timely and comprehensive manner, and the timeliness of the factory defect monitoring is improved. In this way, the overall product quality and production capacity can be effectively improved, and the competitiveness of the enterprise can be enhanced.

Description

Technical Field

[0001] The present application relates to the field of big data, and in particular to a data monitoring method, a monitoring device, an electronic device and a storage medium. Background Art

[0002] The manufacturing industry needs to monitor product defects in the inspection process to achieve control over the product production process, timely discover problems and correct them, thereby improving the overall quality of the product. However, the traditional system management method is limited by the problem of poor system computing power, and can only monitor a small number of known defects, making it difficult to conduct root cause analysis based on the known small number of defects, making it difficult for relevant personnel to quickly determine the cause of the defect and correct it. Therefore, how to comprehensively monitor product defect fluctuations to improve the overall quality of the product has become an urgent problem to be solved. Summary of the invention

[0003] In view of this, the present application provides a data monitoring method, a monitoring device, an electronic device and a storage medium.

[0004] The data monitoring method of this application includes:

[0005] Acquiring original data of the inspection process and preprocessing the original data of the inspection process to obtain multiple groups of bad defect data;

[0006] Establishing a data monitoring model and using the data monitoring model to monitor multiple groups of the bad defect data; and

[0007] Determine the bad fluctuation data according to the monitoring result of the data monitoring model.

[0008] In some embodiments, acquiring the original data of the detection process and preprocessing the original data of the detection process to obtain multiple groups of defect data includes:

[0009] According to the ETL tool, the original data of the inspection process is preprocessed according to the preset logic to obtain multiple groups of defect data. The original data of the inspection process includes the production batch number, the identity of the production raw materials, the inspection time, the defect type, and the defect location. The defect data includes the factory, process, production batch number, the identity of the production raw materials, time, defect type, defect number, and defect ratio.

[0010] In some embodiments, establishing a data monitoring model and using the data monitoring model to monitor multiple groups of bad defect data includes:

[0011] Establish the data monitoring model using one-way analysis of variance technique and / or multi-way analysis of variance technique;

[0012] Optimizing the defect data according to the inspection site information;

[0013] The bad defect data is monitored in chronological order by a computing engine.

[0014] In some embodiments, the data monitoring method further comprises:

[0015] Sending an adverse fluctuation notification according to the adverse fluctuation data.

[0016] In some embodiments, the data monitoring method further comprises:

[0017] Perform production history analysis, process parameter analysis and equipment timing status analysis based on the defect data and the defect fluctuation data;

[0018] The analysis results are pushed to users separately.

[0019] In certain embodiments, the performing of production history analysis, process parameter analysis, and equipment timing state analysis based on the defect data and the defect fluctuation data includes:

[0020] Determine that the bad fluctuation data is bad sample data, and the bad defect data other than the bad fluctuation data is good sample data;

[0021] Performing the production history analysis on the bad sample data according to the good sample data to determine the problem factors, wherein the problem factors include production equipment problems, process processing time problems, and waiting time problems;

[0022] Performing process parameter analysis based on problem factors to determine problem parameters, wherein the problem parameters include process parameters, measurement parameters and / or electrical parameters, and / or performing equipment timing status analysis based on problem factors to determine problem status.

[0023] In certain embodiments, the production history analysis includes processing time, waiting time, equipment differences, unit differences, room / layer differences, equipment continuity, process routes, transport paths, and equipment parameter differences.

[0024] The monitoring device of the embodiment of the present application includes:

[0025] A processing module, which can be used to obtain raw data of the detection process and pre-process the raw data of the detection process to obtain multiple groups of bad defect data;

[0026] A monitoring module, wherein the monitoring module can be used to establish a data monitoring model and use the data monitoring model to monitor multiple groups of the bad defect data; and

[0027] A determination module, which can be used to determine bad fluctuation data according to the monitoring results of the data monitoring model.

[0028] The data monitoring device of the present application includes:

[0029] A processing module, which can be used to obtain vehicle usage data related to vehicle charging and pre-process the vehicle usage data to obtain data to be detected;

[0030] A monitoring module, which can be used to detect the data to be detected according to the trained detection model; and

[0031] A determination module, which can be used to determine bad fluctuation data according to the monitoring results of the data monitoring model.

[0032] The electronic equipment of this application includes:

[0033] one or more processors, memory; and

[0034] One or more programs, wherein the one or more programs are stored in the memory and executed by the one or more processors, and the programs include instructions for executing any one of the data monitoring methods described above.

[0035] The present application also provides a non-volatile computer-readable storage medium of a computer program, which, when executed by one or more processors, enables the processors to execute any of the above-mentioned data monitoring methods.

[0036] In the data monitoring method, monitoring device, electronic device and computer storage medium of the implementation mode of the present application, multiple groups of defect data are obtained by processing the original data of the detection process, and the multiple groups of defect data are monitored by the data monitoring model. Thus, the defect fluctuation data in the production process can be monitored in a timely and comprehensive manner, and the timeliness of factory defect monitoring is improved. In this way, the overall product quality and production capacity can be effectively improved, and the competitiveness of the enterprise can be enhanced.

[0037] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0039] Figure 1 is a flow chart of a data monitoring method of certain embodiments of the present application;

[0040] Figure 2 is a schematic diagram of a module of a data monitoring device in certain embodiments of the present application;

[0041] Figure 3 is a schematic diagram of a module of an electronic device according to some embodiments of the present application;

[0042] Figure 4 It is a schematic diagram of a module in which a storage medium and a processor are connected in certain embodiments of the present application;

[0043] Figure 5 It is a schematic diagram of preprocessing the raw data of the detection process in certain embodiments of the present application;

[0044] Figure 6 is a flow chart of a data monitoring method of certain embodiments of the present application;

[0045] Figure 7 is a flow chart of a data monitoring method of certain embodiments of the present application;

[0046] Figure 8 It is a flowchart of a data monitoring method according to certain embodiments of the present application.

[0047] Description of main component symbols:

[0048] Monitoring device 10 , processing module 12 , monitoring module 14 , determination module 16 , analysis module 18 , push module 19 , electronic device 100 , processor 20 , memory 30 , program 32 , storage medium 40 , computer program 42 , communication module 50 . DETAILED DESCRIPTION

[0049] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0050] See also Figure 1 The present application provides a data monitoring method, the monitoring method comprising the steps of:

[0051] S12, acquiring the original data of the inspection process and preprocessing the original data of the inspection process to obtain multiple groups of defect data;

[0052] S14, establishing a data monitoring model and using the data monitoring model to monitor multiple groups of bad defect data; and

[0053] S16, determining the bad fluctuation data according to the monitoring result of the data monitoring model.

[0054] See also Figure 2 The embodiment of the present application provides a data monitoring device 10. The monitoring device 10 includes a processing module 12, a monitoring module 14, and a determining module 16.

[0055] S12 may be implemented by the processing module 12 , S14 may be implemented by the monitoring module 14 , and S16 may be implemented by the determining module 16 .

[0056] In other words, the processing module 12 can be used to obtain the original data of the detection process and pre-process the original data of the detection process to obtain multiple groups of defect data.

[0057] The monitoring module 14 can be used to establish a data monitoring model and use the data monitoring model to monitor multiple groups of bad defect data.

[0058] The determination module 16 can be used to determine the bad fluctuation data according to the monitoring results of the data monitoring model.

[0059] See also Figure 3 The electronic device 100 of the present application also includes one or more processors 20, a memory 30; and one or more programs 32, wherein the one or more programs 32 are stored in the memory 30 and executed by one or more processors 20, and the program 32 is executed by the processor 20 to execute the instructions of the above-mentioned data monitoring method.

[0060] See also Figure 4 The embodiment of the present application also provides a non-volatile computer-readable storage medium 40, which stores a computer program 42. When the computer program 42 is executed by one or more processors 20, the processor 20 executes the above-mentioned data monitoring method.

[0061] In the data monitoring method, monitoring device 10, electronic device 100 and storage medium 40 of the implementation mode of the present application, multiple groups of defect data are obtained by processing the original data of the detection process, and the multiple groups of defect data are monitored by the data monitoring model, so that the defect fluctuation data in the production process can be monitored in a timely and comprehensive manner, thereby improving the timeliness of factory defect monitoring. In this way, problems can be discovered and corrected based on the defect fluctuation data, thereby improving the overall product quality and production capacity, and enhancing the competitiveness of the enterprise.

[0062] In some embodiments, the electronic device 100 may be a server, and the server may include a big data platform. The big data platform is a platform that integrates data access, data processing, data storage, query retrieval, analysis and mining, application interface, etc. In this way, the electronic device 100 can implement the data monitoring method of the implementation mode of the present application.

[0063] In some embodiments, the monitoring device 10 may be a part of the electronic device 100 . In other words, the electronic device 100 includes the monitoring device 10 .

[0064] In some embodiments, the monitoring device 10 may be a discrete component assembled in a certain manner to have the aforementioned functions, or a chip having the aforementioned functions in the form of an integrated circuit, or a computer software code segment that enables the computer to have the aforementioned functions when running on the computer.

[0065] In some embodiments, as hardware, the monitoring device 10 can be independent or installed as an additional peripheral component to a computer or computer system. The monitoring device 10 can also be integrated into a computer or computer system. For example, when the monitoring device 10 is part of the electronic device 100, the monitoring device 10 can be integrated into the processor 20.

[0066] In some embodiments where the monitoring device 10 is a part of the electronic device 100, as software, the code segments corresponding to the monitoring device 10 can be stored in the memory 30 and executed by the processor 20 to implement the aforementioned functions. In other words, the monitoring device 10 includes the aforementioned one or more programs 32, or the aforementioned one or more programs 32 include the monitoring device 10.

[0067] In some embodiments, the computer-readable storage medium 40 may be a storage medium built into the electronic device 100, such as the memory 30, or a storage medium that can be plugged into the electronic device 100, such as an SD card.

[0068] Please further combine Figure 3 In some embodiments, the electronic device 10 may further include a communication module 50, through which the electronic device 10 outputs the data after the detection process is completed, and / or obtains the data to be processed by the electronic device 10 from an external device. For example, the communication module 50 is connected to a relational database of a manufacturing plant to obtain the original data of the detection process in the relational database.

[0069] Technical personnel in the relevant field can understand that a relational database refers to a database that uses a relational model to organize data. It stores data in the form of rows and columns to facilitate user understanding. This series of rows and columns of a relational database is called a table, and a group of tables constitutes a database.

[0070] It should be noted that the original data of the testing process refers to the relevant data generated during the production process of the product. It can be understood that relevant data will be generated in each production process.

[0071] The original data of the inspection process includes the growth batch number, the identity of the production raw materials, the inspection time, the defect type, the defect location, etc. The defect defect data may include the factory, process, the growth batch number, the identity of the production raw materials, the monitoring time, the defect type, the defect number, the defect ratio, etc.

[0072] For example, please combine Figure 5 For the production process of the display panel, in production process A, the production batch number, glass identification, processing time, defect type, and occurrence location are recorded. In production process B, the production batch number, glass identification, display panel identification, glass identification, processing time, defect type, and occurrence location are recorded. In production process C, the production batch number, glass identification, processing time, occurrence location, thin film transistor (TFT) production batch number, and glass identification of the thin film transistor are recorded. The defect data obtained according to the original data of the detection process may include: the identification of the defective glass, the manufacturer, the production batch number, the production time, the defect type, the number of defectives, the defective ratio, etc.

[0073] Of course, the original data of the inspection process may include all the processes in multiple factories that produce the same product. It can be understood that the more original data of the inspection process, the more defect data generated by the original data of the inspection process, and thus, the more accurate the monitoring results of the defect data by the data monitoring model.

[0074] In addition, it can be seen from the above example that in the data monitoring method of the present application, the data obtained during the production process of the display panel is used as an example for explanation. It can be understood that the above is only an example of the data monitoring method and does not strictly limit the object of application of the data monitoring method in the embodiment of the present invention.

[0075] It should also be noted that the monitoring model refers to a mathematical model used to monitor bad defect data. The detection model can be established based on preset logic and mathematical algorithms. The preset logic is the business logic, which refers to the rules and processes that an entity unit should have in order to provide services to another entity unit.

[0076] The processor 20 can pre-process the original data of the detection process according to the preset logic through the data warehouse technology (Extract-Transform-Load, ETL) tool to obtain multiple groups of defect data. Data warehouse technology refers to a data processing technology used to extract, transform, and load the acquired data to obtain target business data. Therefore, it can be understood that the ETL tool refers to a tool that uses ETL technology to extract, transform, and load data to obtain target business data. That is, in an embodiment of the present application, the ETL tool can be set in the processor 20, or the processor 20 includes the ETL tool, so that the processor 20 can extract, transform, and load the original data of the monitoring process according to the preset logic to obtain multiple groups of defect data.

[0077] Specifically, the processor 20 first extracts the data to be processed from the original data of the detection process, then cleans the extracted data to be processed, and converts it into a format acceptable to the target database according to pre-set specifications, and then loads the cleaned data into a specified location of the data storage device. In this way, multiple groups of defect data that are consistent with the business logic and in a unified format are obtained.

[0078] After obtaining multiple sets of defect data, import them into the data center, and then extract and store them in the data warehouse according to business logic through ETL, so that the monitoring model can monitor multiple sets of defect data, thereby obtaining defect fluctuation data. In this way, comprehensive monitoring of product defect fluctuations is achieved, so that relevant personnel can quickly locate the cause of the defect, thereby discovering the problem and improving it as quickly as possible, reducing the impact of defects on quality and production capacity.

[0079] See also Figure 6 In some embodiments, step S14 further comprises the steps of:

[0080] S142, establishing a data monitoring model using one-way ANOVA technique and / or multi-way ANOVA technique;

[0081] S144, optimizing the defect data according to the inspection site information;

[0082] S146, monitoring the bad defect data in chronological order through a computing engine.

[0083] Please further combine Figure 2In some embodiments, step S142 and step S144 can be implemented by the monitoring module 14. That is, the monitoring module 14 can be used to establish a data monitoring model using a one-way variance analysis technique and / or a multi-way variance analysis technique. The monitoring module 14 can also be used to optimize the defect data according to the inspection site information and monitor the defect data in chronological order through the computing engine.

[0084] Please further combine Figure 3 In some embodiments, the processor 20 can be used to establish a data monitoring model using a one-way variance analysis technique and / or a multi-way variance analysis technique. The processor 20 can also be used to optimize the defect data according to the inspection site information and monitor the defect data in chronological order through a computing engine.

[0085] Analysis of Variance (ANOVA), also known as "analysis of variance", was invented by RA Fisher and is used to test the significance of the difference between the means of two or more samples. Due to the influence of various factors, the data obtained from the study fluctuates. The causes of fluctuations can be divided into two categories: one is uncontrollable random factors, and the other is controllable factors that affect the results in the study. That is, ANOVA analyzes the contribution of variances from different sources to the total variance, thereby determining the influence of controllable factors on the research results.

[0086] One-way ANOVA refers to the comparison of the means of multiple samples in a group design, and a completely random design ANOVA should be used. Multiple one-way ANOVA refers to the use of multi-factor ANOVA to analyze when there are two or more factors that affect the dependent variable, that is, through the method of variance comparison and the process of hypothesis testing to determine whether multiple factors have a significant impact on the dependent variable.

[0087] The monitoring model is built based on variance analysis combined with business logic. There can be one or more monitoring models, and the specific number can be established according to specific business needs. One or more data monitoring models can be established based on business logic using single-factor variance analysis technology, or one or more data monitoring models can be established based on business logic using multiple-factor variance analysis technology.

[0088] For example, to monitor all production batches to obtain adverse fluctuation trends, a monitoring model can be established by single-factor variance analysis technology, so that variance analysis can be performed on all production batches to obtain adverse fluctuation trends of production batches. To obtain adverse fluctuation trends by monitoring production time periods and production batches, a monitoring model can be established by multi-factor variance analysis technology, so that variance analysis can be performed on a certain time period and the production batches within the time period to obtain adverse fluctuation trends of production batches for a continuous fixed time.

[0089] After the monitoring model is established, the defect data is optimized according to the inspection site information. It can be understood that the defects detected by the production raw materials at each inspection site will be different according to the actual business situation, so the data needs to be optimized. For example, in the process of processing the production raw material glass to generate a display panel, the defects detected by each glass at each inspection site may be different according to business needs. Therefore, it is necessary to optimize the data. Specifically, when analyzing each defect, as long as the production raw material has been detected at the analyzed inspection site, it is included in the analysis sample, and the defects that have not occurred are filled with 0. In this way, the normal distribution premise of the significance theory is guaranteed to be established.

[0090] Furthermore, the processor 20 can monitor the defect data in chronological order through a computing engine including big data distributed cloud computing. It can be understood that big data distributed cloud computing can fully support the execution of hundreds or thousands of businesses, so the computing engine using big data distributed cloud computing can realize the monitoring of all defective differences in all inspection processes. For example, the defect data can be monitored through Spark, which is a fast and general computing engine designed for large-scale data processing, with the characteristics of fast, efficient, easy to use and general.

[0091] Specifically, the processing is programmed by Spark program, with each inspection process as a task, and the production raw material data newly extracted by ETL is grouped in time sequence (to meet the first-in-first-out requirement of monitoring) and the number of defective defects or defect ratio of the production raw materials is monitored according to the monitoring model to obtain the monitoring results. In this way, the processor 20 can obtain the defective fluctuation data from the monitoring results.

[0092] Furthermore, in some embodiments, the processor 20 may also generate an adverse fluctuation notification based on the adverse fluctuation data and send the adverse fluctuation notification to notify relevant personnel, so that relevant personnel can quickly view and analyze. The notification method is not limited to SMS notification, phone notification, email notification, etc. For example, after monitoring an adverse fluctuation, the processor 20 notifies different process managers by email and in a real-time alarm mode, so that the process managers can quickly view the analysis details according to the email, so as to find problems in time and make improvements.

[0093] See also Figure 7 In certain embodiments, the monitoring method further comprises the steps of:

[0094] S18: Perform production history analysis, process parameter analysis and equipment timing status analysis based on defect data and defect fluctuation data;

[0095] S20: Push the analysis results to the users respectively.

[0096] In some embodiments, the monitoring device 10 further includes an analysis module 18 and a push module 19, wherein step S18 can be performed by the analysis module 18, and step S20 can be performed by the push module 19. In other words, the analysis module 18 can be used to perform production history analysis, process parameter analysis, and equipment timing state analysis based on the defect data and the fluctuation data, and the push module 19 can also be used to push the analysis results to the user.

[0097] In some embodiments, the processor 20 can be used to perform production history analysis, process parameter analysis, and equipment timing state analysis based on the defect data and the fluctuation data. The processor 20 can also be used to push the analysis results to the user.

[0098] The production history may include but is not limited to processing time, waiting time, equipment differences, unit differences, room differences, layer differences, equipment continuity, process routes, transport paths, equipment parameter differences, etc.

[0099] Process parameters may include but are not limited to process parameters, measurement parameters, and electrical characteristics.

[0100] The device timing status may include, but is not limited to, the temperature of the device, the pressure and humidity in the device chamber, etc.

[0101] It can be understood that by analyzing the bad fluctuation data and the production history of the bad fluctuation data, it can be clear whether there is a problem with a certain production equipment, and analyzing the process parameters and equipment timing status of the bad fluctuation data and the production history of the bad fluctuation data can locate the specific root cause of the bad fluctuation.

[0102] Specifically, the processor 20 may also include an intelligent root cause analysis system, which can regenerate samples based on the input defect data and defect fluctuation data, and then perform production history, process parameter analysis and equipment timing status analysis respectively, and obtain each analysis result.

[0103] Furthermore, after obtaining the analysis results of each step, the defect root cause intelligent analysis system will generate a notification of the analysis results and push it to relevant personnel, so that relevant personnel can obtain the analysis results in a timely manner.

[0104] It should be noted that the defect data and the defect fluctuation data can be obtained by the defect root cause intelligent analysis system either manually input by relevant personnel or actively monitored by the defect root cause intelligent analysis system.

[0105] It can be understood that the defect root cause intelligent analysis system can be a system developed based on the production history, process parameter analysis and equipment timing state analysis theory. Of course, the defect root cause intelligent analysis system can also be generated based on other theories. For example, the defect root cause intelligent analysis system can be developed based on traditional statistical theory, so that the defect root cause intelligent analysis system sorts the defect data and the defect fluctuation data to obtain the analysis result. Alternatively, it can be developed based on the machine learning algorithm theory such as decision tree, random forest, gradient descent tree algorithm (Gradient Boost Decision Tree, GBDT), (eXtremeGradient Boosting, GXBoost) algorithm, so that the machine learning algorithm can process the defect data and the defect fluctuation data to obtain the analysis result.

[0106] See also Figure 8 In some embodiments, step S18 comprises the steps of:

[0107] S182, determining that the bad fluctuation data is bad sample data, and the bad defect data other than the bad fluctuation data is good sample data;

[0108] S184, performing production history analysis on bad sample data based on good sample data to determine the problem factors;

[0109] S186, performing process parameter analysis based on the problem factors to determine the problem parameters, and / or performing equipment timing status analysis based on the problem factors to determine the problem status.

[0110] Please further combine Figure 2In some embodiments, step S182, step S184, and step S186 can be implemented by the analysis module 18. In other words, the analysis module 18 can be used to determine that the bad fluctuation data is the bad sample data, and the bad defect data other than the bad fluctuation data is the good sample data. The analysis module 18 can be used to perform a production history analysis on the bad sample data based on the good sample data to determine the problem factor. The analysis module 18 can also be used to perform a process parameter analysis based on the problem factor to determine the problem parameter, and / or perform a device timing state analysis based on the problem factor to determine the problem state.

[0111] In some embodiments, the processor 20 may be used to determine that the bad fluctuation data is bad sample data, and the bad defect data other than the bad fluctuation data is good sample data. The processor 20 may also be used to perform a production history analysis on the bad sample data based on the good sample data to determine the problem factor. The processor 20 may also be used to perform a process parameter analysis based on the problem factor to determine the problem parameter, and / or perform a device timing state analysis based on the problem factor to determine the problem state.

[0112] It should be noted that the problem factors include, but are not limited to, production equipment problems, process processing time problems, and waiting time problems. Problem parameters may be process parameters, measurement parameters, and / or electrical parameters.

[0113] It can be understood that since bad sample data is bad fluctuation data, the bad sample data and good sample data can be compared in production history analysis to find out which specific problem factors lead to the generation of bad fluctuation data, and then the process parameter analysis of the problem factors can be performed to find out which specific problem parameters lead to bad fluctuations. Alternatively, the equipment timing status analysis of the generation process can find out which specific states lead to bad fluctuations.

[0114] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (digital subscriber line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium (eg, a floppy disk, a hard disk, a magnetic tape), an optical medium (eg, a digital video disc (DVD)), or a semiconductor medium (eg, a solid state disk (SSD)).

[0115] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0116] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0117] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0118] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A data monitoring method, characterized in that: include: Acquiring original data of the inspection process and preprocessing the original data of the inspection process to obtain multiple groups of bad defect data; Establishing a data monitoring model and using the data monitoring model to monitor multiple groups of the bad defect data; and Determining bad fluctuation data from the bad defect data according to the monitoring result of the data monitoring model; Determine that the bad fluctuation data is bad sample data, and determine that the bad defect data other than the bad fluctuation data is good sample data; Performing a production history analysis on the bad sample data based on the good sample data to determine the problem factor; Performing process parameter analysis based on problem factors to determine problem parameters, and / or performing equipment timing status analysis based on problem factors to determine problem status; The analysis results are pushed to users separately.

2. The data monitoring method according to claim 1, characterized in that: The acquiring of the original data of the inspection process and preprocessing the original data of the inspection process to obtain multiple groups of defect data includes: According to the ETL tool, the original data of the inspection process is preprocessed according to the preset logic to obtain multiple groups of defect data. The original data of the inspection process includes the production batch number, the identity of the production raw materials, the inspection time, the defect type, and the defect location. The defect data includes the factory, process, production batch number, the identity of the production raw materials, time, defect type, defect number, and defect ratio.

3. The data monitoring method according to claim 1, characterized in that: The establishing of a data monitoring model and using the data monitoring model to monitor multiple groups of the bad defect data includes: Establish the data monitoring model using one-way analysis of variance technique and / or multi-way analysis of variance technique; Optimizing the defect data according to the inspection site information; The bad defect data is monitored in chronological order by a computing engine.

4. The data monitoring method according to claim 1, characterized in that: The data monitoring method further includes: An adverse fluctuation notification is sent according to the adverse fluctuation data.

5. The data monitoring method according to claim 1, characterized in that: The production history includes processing time, waiting time, equipment differences, unit differences, room / layer differences, equipment continuity, process route, transport path, and equipment parameter differences; The problem factors include production equipment problems, process processing time problems, and waiting time problems; The problematic parameters include process parameters, measurement parameters and / or electrical parameters.

6. A data monitoring device, characterized in that: The monitoring device comprises: A processing module, the processing module is used to obtain the original data of the detection process and pre-process the original data of the detection process to obtain multiple groups of bad defect data; A monitoring module, the monitoring module is used to establish a data monitoring model and use the data monitoring model to monitor multiple groups of the bad defect data; and A determination module, the determination module is used to determine bad fluctuation data from the bad defect data according to the monitoring result of the data monitoring model; An analysis module, the analysis module is used to determine that the bad fluctuation data is bad sample data, determine that the bad defect data other than the bad fluctuation data is good sample data, and perform a production history analysis on the bad sample data based on the good sample data to determine a problem factor, and perform a process parameter analysis based on the problem factor to determine a problem parameter, and / or perform a device timing state analysis based on the problem factor to determine a problem state; The push module is used to push the analysis results to the users respectively.

7. An electronic device, characterized in that: include: One or more processors, memory; and One or more programs, wherein the one or more programs are stored in the memory and executed by the one or more processors, and the programs include instructions for executing the data monitoring method according to any one of claims 1-5.

8. A non-volatile computer-readable storage medium for a computer program, characterized in that: When the computer program is executed by one or more processors, the processors are enabled to execute the data monitoring method according to any one of claims 1 to 5.

Images