Method for Collecting and Managing Semiconductor Wafer Quality Data in Various Formats

Abstract

A method for collecting and managing semiconductor wafer quality data of a data collection and management system according to an embodiment of the present invention comprises: a step of providing a workflow interface to a user and receiving a data selection from the user through the workflow interface; a step of preprocessing data and generating a dataset by connecting nodes and edges within the workflow; a step of generating Python code by receiving attribute values ​​entered by the user as parameters using each node that matches one-to-one with a selected Python function; a step of generating a preprocessed dataset by executing the generated Python code; and a step of providing a feedback interface that induces the user to recognize and correct errors occurring during the execution of the Python code.

Description

Technology Field

[0001] The present invention relates to a method for collecting and managing semiconductor wafer quality data of various formats, and more specifically, to a method for collecting and managing semiconductor wafer quality data of various formats that uses a workflow-based no-code method to preprocess data through data selection and node connection via edges, and enables more intuitive data set generation. Background Technology

[0002] As the semiconductor industry is a core sector of the national economy, quality control is of paramount importance. The accuracy and reliability of quality data directly impact semiconductor production efficiency and yield. Existing manual data management methods carry a high risk of human error and undermine the reliability of data analysis. Differences in the formats and storage methods of quality test results across semiconductor companies are causing difficulties in data management and analysis. Furthermore, the probability of human error is high due to operators manually classifying, identifying, and statistically analyzing quality data.

[0003] Data inaccuracies undermine the reliability of analysis results, and the lack of a data-driven semiconductor wafer quality analysis system makes it difficult to make rapid and accurate decisions regarding semiconductor yield. Workers face increased fatigue as they visually inspect quality test results and manually perform statistical analysis; furthermore, due to the nature of the work being directly linked to semiconductor yield and corporate revenue, delays in decision-making lead to increased corporate costs. Prior art literature

[0004] Published Patent 10-2019-0075508, published on July 1, 2019 The problem to be solved

[0005] The present invention was devised to improve upon the prior art described above, and aims to provide a method for collecting and managing semiconductor wafer quality data of various formats that enables more intuitive data preprocessing and dataset generation through data selection and node connection via edges using a workflow-based no-code method. means of solving the problem

[0006] To achieve the above objective and solve the problems of the prior art, a method for collecting and managing semiconductor wafer quality data of a data collection and management system according to an embodiment of the present invention comprises: a step of providing a visual workflow interface to a user through a display means and receiving input of a data selection made by the user through an input means via the visual workflow interface displayed on the display means; a step of maintaining a visual interface that allows for individual modification of each node to change and expand the structure of the workflow, and providing the visual interface to a user through the display means; a step of providing a library of preprocessing functions according to various data formats and allowing the user to select a preprocessing function suitable for the data format, connecting nodes and edges within the visual workflow to preprocess data into average values ​​and generating a dataset necessary for AI analysis and modeling; a step of maintaining a dataset management module that manages the generated dataset, tracks the history of changes to the dataset, and, if necessary, provides functions for modifying and updating the dataset to the visual interface via the display means; a step of generating Python code by receiving attribute values ​​entered by the user as parameters using each node that matches one-to-one with a selected Python function; and a step of generating a preprocessed dataset by executing the generated Python code. and includes the step of providing a visual feedback interface through the display means to induce the user to recognize and correct errors occurring during the execution of Python code.

[0007] delete

[0008] delete

[0009] delete Effects of the invention

[0010] According to the method for collecting and managing semiconductor wafer quality data of various formats of the present invention, datasets required for AI analysis and modeling can be easily generated without coding, and by automating the data preprocessing and dataset generation processes through a visual workflow user interface, the time and cost required for data processing can be minimized, thereby enabling more efficient data management and data-driven decision-making.

[0011] In addition, according to the method for collecting and managing semiconductor wafer quality data of various formats of the present invention, modifications can be easily made for each node of the workflow, thereby making it easier to change or finalize the structure of the workflow and, accordingly, enabling a more immediate response to changes in requirements that occur during the dataset generation process.

[0012] In addition, according to the method for collecting and managing semiconductor wafer quality data of various formats of the present invention, by minimizing errors that may occur during the data preprocessing process through automated Python code generation and execution, and thereby maximizing data accuracy, the effect of improving the performance of AI analysis and modeling can be obtained. Specific details for implementing the invention

[0013] To clarify the features and advantages of the means for solving the problem of the present invention, the present invention will be described in more detail with reference to specific embodiments of the present invention illustrated in the accompanying drawings. However, detailed descriptions of known functions or configurations that may obscure the essence of the present invention in the following description and the accompanying drawings are omitted. Additionally, it should be noted that identical components throughout the drawings are indicated by the same reference numerals whenever possible.

[0014] Terms and words used in the following description and drawings should not be interpreted as being limited to their ordinary or dictionary meanings, but should be interpreted in a meaning and concept consistent with the technical spirit of the invention, based on the principle that the inventor can appropriately define the concept of terms to best describe his invention. Accordingly, the embodiments described in this specification and the configurations illustrated in the drawings are merely the most preferred embodiments of the invention and do not represent all aspects of the technical spirit of the invention; therefore, it should be understood that various equivalents and modifications capable of replacing them may exist at the time of filing this application.

[0015] Furthermore, terms including ordinal numbers, such as "first," "second," etc., are used to describe various components and are used solely for the purpose of distinguishing one component from another, not to limit said components. For example, without departing from the scope of the present invention, the second component may be named the first component, and similarly, the first component may be named the second component. In addition, when it is stated that a component is "connected" or "connected" to another component, this means that they may be logically or physically connected or connected.

[0016] In other words, it should be understood that while a component may be directly connected to or coupled with another component, there may also be other components in between, or that it may be indirectly connected or coupled. Furthermore, terms such as "comprising" or "having" as used in this specification are intended to specify the existence of the features, numbers, steps, actions, components, parts, or combinations thereof described in the specification, and should not be understood as precluding the existence or addition of one or more other features, numbers, steps, actions, components, parts, or combinations thereof.

[0017] Additionally, terms such as “…part,” “…unit,” and “module” as described in the specification refer to a unit that processes at least one function or operation, and this may be implemented in hardware, software, or a combination of hardware and software. Furthermore, “one (a or an),” “one,” “the,” and similar terms may be used in the context describing the invention (particularly in the context of the following claims) to include both singular and plural forms, unless otherwise indicated in the specification or clearly contradicted by the context.

[0018] In describing the embodiments of the present invention, descriptions of known configurations that are obvious to those skilled in the art will be omitted so as not to obscure the essence of the invention. Furthermore, when referring to the drawings, it should be taken into account that the thickness of lines or the size of components depicted in the drawings may be exaggerated for the sake of clarity and convenience of explanation.

[0019] Embodiments of the present invention will be described in detail below.

[0020] According to a method for collecting and managing semiconductor wafer quality data of a data collection and management system according to an embodiment of the present invention, a workflow interface is provided to a user, and a data selection is received from the user through the workflow interface. Nodes and edges within the workflow are connected to preprocess data and generate a dataset. Python code is generated by receiving attribute values ​​entered by the user as parameters using each node that is matched one-to-one with a selected Python function.

[0021] The Python code generated above is executed to create a preprocessed dataset. A feedback interface is provided to induce the user to recognize and correct errors occurring during the execution of the Python code. Furthermore, according to the method for collecting and managing semiconductor wafer quality data of a data collection and management system according to an embodiment of the present invention, a dataset management module is maintained to manage the generated dataset, track the change history of the dataset, and provide functions for modifying and updating the dataset when necessary.

[0022] Furthermore, according to the method for collecting and managing semiconductor wafer quality data of a data collection and management system according to an embodiment of the present invention, a library of preprocessing functions according to various data formats is provided, and data preprocessing is performed by allowing a user to select a preprocessing function suitable for the data format. In addition, according to the method for collecting and managing semiconductor wafer quality data of a data collection and management system according to an embodiment of the present invention, an interface that allows for individual modification of each node, thereby enabling changes and expansion of the workflow structure, can be maintained and provided to the user.

[0023] As such, the present invention relates to a method for collecting and managing semiconductor wafer quality data of various formats, which enables more intuitive data preprocessing and dataset generation through data selection and node connection via edges using a workflow-based no-code method. According to the present invention, datasets required for AI analysis and modeling can be easily generated without coding, and by automating the data preprocessing and dataset generation processes through a visual workflow user interface, the time and cost required for data processing are minimized, thereby enabling more efficient data management and data-driven decision-making.

[0024] Furthermore, since workflow nodes can be easily modified, the workflow structure can be more easily changed or finalized, enabling a more immediate response to changes in requirements that occur during the dataset generation process. Additionally, automated Python code generation and execution minimize errors that may occur during data preprocessing, thereby maximizing data accuracy and improving the performance of AI analysis and modeling.

[0025] The method for collecting and managing semiconductor wafer quality data of a data collection and management system according to the present invention may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either individually or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the present invention, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The above-described hardware device may be configured to operate as one or more software modules to perform the operation of the present invention, and vice versa.

[0026] As described above, although the present invention has been explained by limited embodiments and drawings, the present invention is not limited to the above embodiments, and various modifications and variations are possible from this description by those skilled in the art.

[0027] Therefore, the scope of the present invention should not be limited to the described embodiments, but should be defined by the claims set forth below as well as equivalents thereof.

Claims

Claim 1 A method for collecting and managing semiconductor wafer quality data of a data collection and management system comprises: providing a visual workflow interface to a user through a display means and receiving a data selection made by the user through an input means via the visual workflow interface displayed on the display means; maintaining a visual interface that allows for individual modification of each node to change and expand the structure of the workflow, and providing the visual interface to the user through the display means; providing a library of preprocessing functions according to various data formats and allowing the user to select a preprocessing function suitable for the data format, connecting nodes and edges within the visual workflow to preprocess data into average values ​​and generating a dataset necessary for AI analysis and modeling; maintaining a dataset management module that manages the generated dataset, tracks the history of changes to the dataset, and, if necessary, provides functions for modifying and updating the dataset to the visual interface via the display means; generating Python code by receiving attribute values ​​entered by the user as parameters using each node that matches one-to-one with a selected Python function; and executing the generated Python code to generate a preprocessed dataset. A method for collecting and managing semiconductor wafer quality data of a data collection and management system, characterized by including the step of providing a visual feedback interface through the display means to induce the user to recognize and correct errors occurring during Python code execution. Claim 2 delete Claim 3 delete Claim 4 delete

Images