CN114429256A

CN114429256A - Data monitoring method and device, electronic equipment and storage medium

Info

Publication number: CN114429256A
Application number: CN202011182868.XA
Authority: CN
Inventors: 王士侠; 吴建民; 吴少擎; 王洪
Original assignee: BOE Technology Group Co Ltd; Beijing Zhongxiangying Technology Co Ltd
Current assignee: BOE Technology Group Co Ltd; Beijing Zhongxiangying Technology Co Ltd
Priority date: 2020-10-29
Filing date: 2020-10-29
Publication date: 2022-05-03

Abstract

The application discloses a data monitoring method and device, electronic equipment and a storage medium. The monitoring method comprises the following steps: the method comprises the steps of obtaining original data of a detection process, preprocessing the original data of the detection process to obtain multiple groups of bad defect data, establishing a data monitoring model, monitoring the multiple groups of bad defect data by using the data monitoring model, and determining bad fluctuation data according to a monitoring result of the data monitoring model. According to the data monitoring method, multiple groups of bad defect data are obtained by processing the original data of the detection process, and the multiple groups of bad defect data are monitored through the data monitoring model, so that bad fluctuation data in the production process can be monitored timely and comprehensively, the timeliness of the bad monitoring of a factory is improved, the quality and the productivity of the whole product can be effectively improved, and the competitiveness of an enterprise is improved.

Description

Data monitoring method and device, electronic equipment and storage medium

Technical Field

The present disclosure 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

The production and manufacturing industry needs to monitor the product defects of the detection process so as to realize the management and control of the production process of the product, find problems in time and correct the problems, and further improve the overall quality of the product. However, the conventional system management method is limited to the problem of poor computing capability of the system, and only can monitor a known small amount of failures, so that root cause analysis is difficult to be performed according to the known small amount of failures, and it is difficult for relevant personnel to quickly determine and correct the failure occurrence reason. Therefore, how to comprehensively monitor the adverse fluctuation of the product so as to improve the overall quality of the product becomes a problem to be solved urgently.

Disclosure of Invention

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

The data monitoring method comprises the following steps:

acquiring original data of a detection procedure and preprocessing the original data of the detection procedure to obtain a plurality of groups of bad defect data;

establishing a data monitoring model and monitoring a plurality of groups of bad defect data by using the data monitoring model; and

and determining bad fluctuation data according to the monitoring result of the data monitoring model.

In some embodiments, the acquiring raw inspection process data and preprocessing the raw inspection process data to obtain a plurality of sets of bad defect data includes:

and preprocessing the original data of the detection process according to a preset logic according to an ETL tool to obtain a plurality of groups of bad defect data, wherein the original data of the detection process comprises production batch numbers, identification marks of production raw materials, detection time, bad types and bad positions, and the bad defect data comprises factories, processes, production batch numbers, identification marks of the production raw materials, time, bad types, bad numbers and bad proportions.

In some embodiments, the establishing a data monitoring model and using the data monitoring model to monitor the plurality of sets of bad defect data includes:

establishing the data monitoring model by utilizing a one-factor analysis of variance technique and/or a multi-factor analysis of variance technique;

optimizing the bad defect data according to the information of the detection station;

the defect data is monitored by a calculation engine in chronological order.

In certain embodiments, the data monitoring method further comprises:

and sending a bad fluctuation notice according to the bad fluctuation data. .

In certain embodiments, the data monitoring method further comprises:

performing production record analysis, process parameter analysis and equipment time sequence state analysis according to the bad defect data and the bad fluctuation data;

and respectively pushing the analysis results to the user.

In some embodiments, the performing the production history analysis, the process parameter analysis, and the equipment timing state analysis based on the defective defect data and the defective fluctuation data includes:

determining the bad fluctuation data as bad sample data, and determining the bad defect data except the bad fluctuation data as good sample data;

performing the production history analysis on the bad sample data according to the good sample data to determine problem factors, wherein the problem factors comprise production equipment problems, procedure processing time problems and waiting time problems;

performing process parameter analysis according to the problem factors to determine problem parameters, wherein the problem parameters comprise process parameters, measurement parameters and/or electrical parameters, and/or performing equipment time sequence state analysis according to the problem factors to determine problem states.

In certain embodiments, the production history analysis includes processing time, wait time, equipment variation, unit variation, chamber/level variation, equipment continuity, process routes, transfer paths, equipment parameter variation.

The monitoring device of the embodiment of the application comprises:

the processing module can be used for acquiring original data of a detection process and preprocessing the original data of the detection process to obtain a plurality of groups of bad defect data;

the monitoring module can be used for establishing a data monitoring model and monitoring a plurality of groups of bad defect data by using the data monitoring model; and

a determination module, which can be used for determining the bad fluctuation data according to the monitoring result of the data monitoring model.

The data monitoring device of the application includes:

the processing module can be used for acquiring vehicle use data related to vehicle charging and preprocessing the vehicle use data to obtain data to be detected;

the monitoring module can be used for detecting the data to be detected according to the trained detection model; and

The electronic device of the present application includes:

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, the programs comprising instructions for performing the data monitoring method of any of the above.

The present application also provides a non-transitory computer readable storage medium of a computer program which, when executed by one or more processors, causes the processors to perform the data monitoring method of any one of the above.

In the data monitoring method, the monitoring device, the electronic equipment and the computer storage medium of the embodiment of the application, the original data of the detection process is processed to obtain multiple groups of bad defect data, and the multiple groups of bad defect data are monitored through the data monitoring model, so that bad fluctuation data in the production process can be monitored timely and comprehensively, the bad monitoring timeliness of a factory is improved, and therefore the quality and the capacity of the whole product can be effectively improved, and the competitiveness of enterprises is improved.

Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.

Drawings

The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:

FIG. 1 is a schematic flow chart of a data monitoring method according to some embodiments of the present application;

FIG. 2 is a block schematic diagram of a data monitoring device according to certain embodiments of the present application;

FIG. 3 is a block diagram of an electronic device according to some embodiments of the present application;

FIG. 4 is a block diagram of a storage medium coupled to a processor according to some embodiments of the present application;

FIG. 5 is a schematic illustration of pre-processing raw data from a detection process according to certain embodiments of the present disclosure;

FIG. 6 is a schematic flow chart of a data monitoring method according to some embodiments of the present application;

FIG. 7 is a schematic flow chart diagram of a data monitoring method according to some embodiments of the present application;

FIG. 8 is a schematic flow chart diagram of a data monitoring method according to some embodiments of the present application.

Description of the main element symbols:

monitoring apparatus 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

Reference will now be made in detail to embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.

Referring to fig. 1, the present application provides a data monitoring method, which includes the steps of:

s12, acquiring original data of the detection process and preprocessing the original data of the detection process to obtain a plurality of groups of bad defect data;

s14, establishing a data monitoring model and monitoring a plurality of groups of bad defect data by using the data monitoring model; and

and S16, determining the bad fluctuation data according to the monitoring result of the data monitoring model.

Referring to fig. 2, the present embodiment provides a data monitoring device 10. The monitoring device 10 includes a processing module 12, a monitoring module 14, and a determination module 16.

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.

Alternatively, the processing module 12 may be configured to obtain raw inspection process data and pre-process the raw inspection process data to obtain multiple sets of bad defect data.

The monitoring module 14 may be configured to establish a data monitoring model and monitor a plurality of sets of bad defect data using the data monitoring model.

The determination module 16 may be configured to determine the undesirable fluctuation data based on the monitoring results of the data monitoring model.

Referring to fig. 3, the electronic device 100 of the present application further 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 the one or more processors 20, the programs 32 being executed by the processors 20 to perform the instructions of the data monitoring method described above.

Referring to fig. 4, the present application also provides a non-volatile computer readable storage medium 40, where the readable storage medium 40 stores a computer program 42, and when the computer program 42 is executed by one or more processors 20, the processor 20 executes the data monitoring method described above.

In the data monitoring method, the monitoring device 10, the electronic device 100 and the storage medium 40 of the embodiment of the application, a plurality of groups of bad defect data are obtained by processing the original data of the detection process, and the plurality of groups of bad defect data are monitored through the data monitoring model, so that the bad fluctuation data in the production process can be monitored timely and comprehensively, the timeliness of the bad monitoring of a factory is improved, and therefore problems can be found and corrected according to the bad fluctuation data, the quality and the capacity of the whole product are improved, and the competitiveness of enterprises is improved.

In some embodiments, the electronic device 100 may be a server, and the server may include a big data platform, where the big data platform is a platform that integrates data access, data processing, data storage, query retrieval, analysis mining, and the like, and an application interface, and thus, the electronic device 100 may implement the data monitoring method according to the embodiments of the present application.

In some embodiments, the monitoring device 10 may be part of the electronic device 100. Alternatively, the electronic device 100 includes the monitoring apparatus 10.

In some embodiments, the monitoring device 10 may be a discrete component assembled in such a way as to have the aforementioned functions, or a chip having the aforementioned functions in the form of an integrated circuit, or a piece of computer software code that causes a computer to have the aforementioned functions when run on the computer.

In some embodiments, the monitoring device 10 may be a stand-alone or add-on peripheral component to a computer or computer system as hardware. The monitoring device 10 may also be integrated into a computer or computer system, for example, where the monitoring device 10 is part of the electronic device 100, the monitoring device 10 may be integrated into the processor 20.

In some embodiments where the monitoring device 10 is part of the electronic device 100, as software, a code segment corresponding to the monitoring device 10 may be stored in the memory 30 and executed by the processor 20 to implement the aforementioned functions. Or the monitoring device 10, includes one or more of the procedures 32 described above, or the one or more procedures 32 described above include the monitoring device 10.

In some embodiments, the computer-readable storage medium 40 may be a storage medium built in the electronic device 100, for example, the memory 30, or a storage medium that can be plugged into the electronic device 100, for example, an SD card.

Referring to fig. 3, in some embodiments, the electronic device 10 may further include a communication module 50, and the electronic device 10 outputs data of the detection process through the communication module 50, and/or acquires 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 factory to acquire raw data of the detection process in the relational database.

As will be understood by those skilled in the relevant art, a relational database refers to a database that employs a relational model to organize data, and stores data in rows and columns for easy understanding by a user, and a series of rows and columns of a relational database are referred to as tables, and a set of tables constitutes a database.

The raw data of the detection process refers to the relevant data generated in the production process of the product, and it is understood that the relevant data is generated in each production process.

The raw data of the detection process comprises a growth batch number, an identification of production raw materials, detection time, a defect type, a defect position and the like, and the defect data can comprise a factory, a process, a growth batch number, an identification of production raw materials, monitoring time, a defect type, a defect number, a defect proportion and the like.

For example, referring to fig. 5, in the production process of the display panel, in the production process a, the production lot number, the glass identifier, the processing time, the defect type, and the occurrence position are recorded, and in the production process B, the production lot number, the glass identifier, the display panel identifier, the glass identifier, the processing time, the defect type, and the occurrence position are recorded. In the production process C, a production lot number, a glass identification, a processing time, a generation position, a Thin Film Transistor (TFT) production lot number, and a glass identification for generating a TFT are recorded. The bad defect data obtained from the raw data of the inspection process may include: identification of bad glass, manufacturer, production batch number, production time, bad type, number of bad defects, proportion of bad defects and the like.

Of course, the raw data of the detection process may include all the processes in a plurality of factories that generate the same product, and it can be understood that the more the raw data of the detection process is, the more the defective defect data generated from the raw data of the detection process is, and further, the more accurate the monitoring result of the data monitoring model on the defective defect data is.

In addition, as can be seen from the above examples, the data monitoring method in the present application is described by taking data obtained during the manufacturing process of the display panel as an example. It should be understood that the foregoing is only an example of the data monitoring method, and the object of the data monitoring method applied in the embodiment of the present invention is not strictly limited.

It should be further noted that the monitoring model is a mathematical model for monitoring the bad defect data, and the detection model can be established according to a preset logic and a mathematical algorithm. The preset logic is a business logic, which refers to rules and processes that one entity unit should have in order to provide services to another entity unit.

The processor 20 may preprocess the raw data of the inspection process according to a preset logic by using an Extract-Transform-Load (ETL) tool to obtain a plurality of sets of bad defect data. The data warehouse technology refers to a data processing technology for extracting (extract), converting (transform), and loading (load) the acquired data to obtain target business data. Therefore, it can be understood that the ETL tool refers to a tool that extracts, converts, and loads data using the ETL technology to obtain target business data. That is, in the embodiment of the present application, the ETL tool may be disposed in the processor 20, or the processor 20 includes the ETL tool, so that the processor 20 may perform preprocessing such as extracting, converting, and loading on the raw data of the monitoring process according to a preset logic to obtain a plurality of sets of bad defect data.

Specifically, the processor 20 extracts data to be processed from the raw data of the detection process, cleans the extracted data to be processed, converts the data into a format acceptable by the target database according to a preset specification, and loads the cleaned data to a designated position of the data storage device, so as to obtain multiple sets of bad defect data which are consistent with the business logic and have a uniform format.

After a plurality of groups of bad defect data are obtained, a plurality of groups of bad defect data are imported into the data center, and then the plurality of groups of bad defect data of the data center are extracted and stored into the data warehouse through the ETL according to business logic, so that the monitoring model can monitor the plurality of groups of bad data, and bad fluctuation data are obtained. Therefore, the adverse fluctuation of the product can be comprehensively monitored, so that the related personnel can quickly locate the cause of the adverse occurrence, the problems can be found and improved at the highest speed, and the quality and capacity influence caused by the adverse occurrence is reduced.

Referring to fig. 6, in some embodiments, step S14 includes the following steps:

s142, establishing a data monitoring model by utilizing a one-factor analysis of variance technique and/or a multi-factor analysis of variance technique;

s144, carrying out optimization processing on the bad defect data according to the detection station information;

and S146, monitoring the bad defect data in time sequence through the calculation engine.

Referring further to fig. 2, in some embodiments, steps S142 and S144 may be implemented by the monitoring module 14. That is, the monitoring module 14 may be configured to build a data monitoring model using one-way analysis of variance techniques and/or multi-way analysis of variance techniques. The monitoring module 14 may also be configured to perform optimization processing on the bad defect data according to the inspection site information and monitor the bad defect data in time sequence through the calculation engine.

Referring further to fig. 3, in some embodiments, processor 20 may be configured to build a data monitoring model using one-way analysis of variance techniques and/or multi-way analysis of variance techniques. The processor 20 may also be configured to optimize the bad defect data according to the inspection site information and monitor the bad defect data in time sequence through the calculation engine.

Analysis of Variance (ANOVA), also known as "Variance Analysis", is invented by r.a. fisher for significance testing of mean differences between two or more samples. Due to the influence of various factors, the data obtained by research shows fluctuation, and the causes of the fluctuation can be divided into two types, namely an uncontrollable random factor and a controllable factor which is applied in the research and has influence on the result. Namely, the analysis of variance determines the influence of controllable factors on the research result by analyzing and researching the contribution of the variation from different sources to the total variation.

The one-way analysis of variance refers to the comparison of the mean values of a plurality of samples designed in a group, and the analysis of variance designed completely randomly should be adopted. The multi-single-factor analysis of variance means that when two or more factors affect the dependent variable, the analysis can be performed by a multi-factor analysis of variance method, that is, whether the multiple factors have significant influence on the dependent variable is determined by a process of hypothesis test through a method of variance comparison.

The monitoring models are built by combining service logic according to analysis of variance, one monitoring model or a plurality of monitoring models can be built, and the specific number can be built according to specific requirements of services. One or more data monitoring models can be established by a one-factor analysis of variance technique according to business logic, or by a plurality of factor analysis of variance techniques according to business logic.

For example, for monitoring all production lots to obtain a bad fluctuation trend, a monitoring model can be established by a one-factor analysis of variance technique, so that analysis of variance of all production lots to obtain a bad fluctuation trend of the production lot. For the bad fluctuation trend obtained by monitoring the production time period and the production batch number, a monitoring model can be established by a multi-factor variance analysis technology, so that variance analysis can be carried out on the production batch number in a certain time period and the time period, and the bad fluctuation trend of the production batch number in continuous fixed time is obtained.

And after the monitoring model is established, carrying out optimization processing on the bad defect data according to the information of the detection station. It can be understood that the defects detected by the production raw materials at the detection stations may be different according to actual business conditions, and the data needs to be optimized, for example, in the process of producing the display panel by processing the production raw material glass, the defects detected by each glass at the detection stations may be different according to business requirements. Therefore, optimization processing of data is required. Specifically, when each defect is analyzed, if the production material is detected at the detection site to be analyzed, the production material is included in the analysis sample, and the defect that has not occurred is subjected to the 0-complementing process. Thus, the establishment of the normal distribution premise using the significance theory is ensured.

In turn, the processor 20 may monitor the bad defect data chronologically through a computing engine that includes big data distributed cloud computing. It can be understood that the big data distributed cloud computing can completely support the execution of hundreds of services, so that the computing engine adopting the big data distributed cloud computing can realize all bad difference change monitoring of all detection procedures. For example, the bad defect data can be monitored by Spark, which is a fast and general-purpose computing engine designed for large-scale data processing, and has the characteristics of being fast, efficient, easy to use, and general.

Specifically, the processing is programmed by a Spark program, each detection procedure is taken as a task, the newly extracted production raw material data of the ETL is monitored according to a monitoring model by grouping the defective defect number or defect ratio of the production raw material according to the time sequence (so as to meet the first-in first-out requirement of monitoring), and thus the monitoring result is obtained. In this manner, the processor 20 may derive the undesirable fluctuation data from the monitoring results.

Further, in some embodiments, the processor 20 may also generate a bad wave notification from the bad wave data and send the bad wave notification to notify the relevant personnel, thus facilitating quick review and analysis by the relevant personnel. The notification method is not limited to short message notification, telephone notification, mail notification, etc. For example, after monitoring the undesirable fluctuation, the processor 20 notifies different process managers in a mail manner and a real-time alarm manner, so that the process managers can quickly check and analyze details according to the mail, and find and improve problems in time.

Referring to fig. 7, in some embodiments, the monitoring method further includes the steps of:

s18: performing production record analysis, process parameter analysis and equipment time sequence state analysis according to the bad defect data and the bad fluctuation data;

s20: and respectively pushing the analysis results to the user.

In certain embodiments, the monitoring device 10 further comprises an analyzing module 18 and a pushing module 19, wherein step S18 can be performed by the analyzing module 18 and step S20 can be performed by the pushing module 19. Alternatively, the analysis module 18 may be configured to perform production history analysis, process parameter analysis and equipment time sequence state analysis according to the bad defect data and the bad fluctuation data, and the pushing module 19 may be further configured to push the analysis results to the user respectively.

In some embodiments, the processor 20 may be configured to perform production history analysis, process parameter analysis, and equipment timing analysis based on the fault defect data and the fault fluctuation data. The processor 20 may also be configured to push the analysis results to the user individually.

The production history may include, but is not limited to, processing time, waiting time, equipment variation, unit variation, room-level variation, layer-level variation, equipment continuity, process route, transfer path, equipment parameter variation, and the like.

Process parameters may include, but are not limited to, process parameters, measurement parameters, electrical characteristics, and the like.

The device timing states may include, but are not limited to, the temperature of the device, the pressure within the device chamber, humidity, and the like.

It is understood that the analysis of the production history of the defective fluctuation data and the defective fluctuation data can specify whether or not a problem is a problem in a certain production facility, and the analysis of the process parameters and the facility time series state of the production history of the defective fluctuation data and the defective fluctuation data can locate a specific root cause of the defective fluctuation.

Specifically, the processor 20 may further include an intelligent analysis system for bad root cause, which is capable of regenerating a sample according to the input bad defect data and bad fluctuation data, and performing production history, process parameter analysis, and equipment time sequence state analysis, respectively, to obtain each analysis result.

Furthermore, after the intelligent analysis system for the bad root cause obtains the analysis result of each step, the intelligent analysis system generates a notice for the analysis result and pushes the notice to relevant personnel, so that the relevant personnel can obtain the analysis result in time.

It should be noted that the acquisition of the bad defect data and the bad fluctuation data by the intelligent analysis system for the bad root cause may be manually input by related personnel, or may be actively monitored by the intelligent analysis system for the bad root cause.

It is understood that the intelligent analysis system for the bad root cause can be a system which is compiled and developed based on production history, process parameter analysis and equipment time sequence state analysis theory. Of course, the intelligent analysis system for the bad root cause can also be generated based on other theories, for example, the intelligent analysis system for the bad root cause can be developed based on the traditional statistical theory, so that the intelligent analysis system for the bad root cause sorts the bad defect data and the bad fluctuation data to obtain an analysis result. Or the analysis result is obtained by developing the analysis result based on machine learning algorithm theories such as Decision trees, random forests, Gradient descent Tree algorithms (GBDT), (eXtreme Gradient Boosting, GXboost) and the like, so that the machine learning algorithm can process the bad defect data and the bad fluctuation data to obtain the analysis result.

Referring to fig. 8, in some embodiments, step S18 includes the steps of:

s182, determining bad fluctuation data as bad sample data, and bad defect data except the bad fluctuation data as good sample data;

s184, performing production history analysis on bad sample data according to the good sample data to determine problem factors;

and S186, performing process parameter analysis according to the problem factors to determine the problem parameters, and/or performing equipment time sequence state analysis according to the problem factors to determine the problem state.

Referring further to fig. 2, in some embodiments, step S182, step S184, and step S186 may be implemented by the analysis module 18. Alternatively, the analysis module 18 may be configured 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 analysis module 18 may be configured to perform production history analysis on bad sample data according to good sample data to determine problem factors, and the analysis module 18 may be further configured to perform process parameter analysis according to the problem factors to determine problem parameters, and/or perform equipment timing state analysis according to the problem factors to determine problem states.

In some embodiments, the processor 20 may be configured to determine that the bad wobble data is bad sample data and the bad defect data other than the bad wobble data is good sample data. The processor 20 may also be configured to perform a production history analysis on bad sample data based on good sample data to determine the problem factor. Processor 20 may also be configured to perform process parameter analysis to determine problem parameters based on the problem factors and/or perform equipment timing status analysis to determine problem status based on the problem factors.

It should be noted that the problem factors include, but are not limited to, production equipment problems, process time problems, and waiting time problems. The problem parameter may be a process parameter, a measurement parameter, and/or an electrical parameter, etc.

It can be understood that, since the bad sample data is the bad fluctuation data, the production history analysis of the bad sample data and the good sample data can compare the bad sample data with the good sample data to obtain specific generation of the bad fluctuation data caused by which problem factors, and further, the process parameter analysis of the problem factors can obtain specific generation of the bad fluctuation caused by which problem parameters. Alternatively, it is possible to obtain which states cause the occurrence of the undesirable fluctuation specifically by analyzing the device sequence state of the production process.

In the above embodiments, all or part of the implementation may be realized by software, hardware, firmware or any other combination. When implemented in software, may 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 loaded and executed on a computer, cause the processes or functions described in accordance with the embodiments of the application to occur, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a network of computers, or other programmable device. The computer instructions may be stored on a computer readable storage medium or transmitted from one computer readable storage medium to another, for example, from one website, computer, server, or data center to another website, computer, server, or data center via wire (e.g., coaxial cable, fiber optic, Digital Subscriber Line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device, such as a server, a data center, etc., that incorporates one or more of the available media. The usable medium may be a magnetic medium (e.g., a floppy disk, a hard disk, a magnetic tape), an optical medium (e.g., a Digital Video Disk (DVD)), or a semiconductor medium (e.g., a Solid State Disk (SSD)), among others.

Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.

In the several embodiments provided in the present application, it should be understood that the disclosed system, apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.

In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit.

The above description is only for the specific embodiments of the present application, but the scope of the present application is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present application, and shall be covered by the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. A method of data monitoring, comprising:

2. The data monitoring method of claim 1, wherein the obtaining raw inspection process data and pre-processing the raw inspection process data to obtain sets of bad defect data comprises:

3. The data monitoring method of claim 1, wherein the establishing a data monitoring model and using the data monitoring model to monitor the plurality of sets of bad defect data comprises:

the defect data is monitored by a calculation engine in chronological order.

4. The data monitoring method of claim 1, further comprising:

and sending a bad fluctuation notice according to the bad fluctuation data.

5. The data monitoring method of claim 1, further comprising:

and respectively pushing the analysis results to the user.

6. The data monitoring method according to claim 5, wherein the performing of production history analysis, process parameter analysis and equipment timing state analysis based on the defective defect data and the defective fluctuation data comprises:

performing the production history analysis on the bad sample data according to the good sample data to determine problem factors;

process parameter analysis is performed to determine problem parameters based on the problem factors, and/or equipment timing state analysis is performed to determine problem states based on the problem factors.

7. The data monitoring method of claim 6, wherein the production history includes processing time, waiting time, equipment variation, unit variation, chamber/layer variation, equipment continuity, process route, transfer path, equipment parameter variation;

the problem factors comprise the problems of production equipment, working procedure processing time and waiting time;

the problem parameters include process parameters, measurement parameters, and/or electrical parameters.

8. A data monitoring device, the monitoring device comprising:

9. An electronic device, comprising:

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, the programs comprising instructions for performing the data monitoring method of any of claims 1-7.

10. A non-transitory computer-readable storage medium of a computer program, which when executed by one or more processors causes the processors to perform the data monitoring method of any one of claims 1-7.