KR-20260062735-A - BIG DATA ANALYSIS SERVICE PROVIDING DEVICE AND METHOD PERFORMING THEREOF

KR20260062735AKR 20260062735 AKR20260062735 AKR 20260062735AKR-20260062735-A

Abstract

A big data analysis service providing device according to the present invention includes a data collection and processing module that collects data having different structures and formats from a plurality of data sources, processes it, and stores it in a database; a first query generation module that generates an integrated query by connecting tables of the database; a second query generation module that generates a query to extract and group data with conditions defined by a user from the database; a data modeling module that generates a data set by modeling data according to the execution of a query generated by the first query generation module or the second query generation module; and an AI learning module that trains an AI model using the data set.

Inventors

김상태
김기수
김대화
김연규
신용석

Assignees

주식회사 에이다루트

Dates

Publication Date: 20260507
Application Date: 20241029

Claims (10)

A data collection and processing module that collects data with different structures and formats from multiple data sources, processes it, and stores it in a database; A first query generation module that generates an integrated query by connecting tables of the above database; A second query generation module that generates a query to extract and group data with user-defined conditions from the above database; A data modeling module that generates a data set by modeling data resulting from the execution of a query generated by the first query generation module or the second query generation module; Characterized by including an AI learning module that trains an AI model using the above dataset. Big data analysis service providing device.
In paragraph 1, The above-mentioned first query generation module is Characterized by generating and executing an integrated query through join conditions and relationship definitions via a graphical user interface that can visually define relationships between multiple tables. Big data analysis service providing device.
In paragraph 1, The above second query generation module is Characterized by generating and executing a query based on the search conditions when the user selects a desired column in the above database and the search conditions required for data retrieval are set. Big data analysis service providing device.
In paragraph 1, The above data modeling module is The method is characterized by converting the data extracted by the above-mentioned first query generation module into a data frame or table format, structuring and visualizing it to generate a model for predictive analysis. Big data analysis service providing device.
In paragraph 1, The above AI learning module is Characterized by executing a machine learning algorithm in an R-Studio or Jupyter-Notebook environment to train a dataset generated by the above data modeling module, and then visualizing the analysis results. Big data analysis service providing device.
In a method for providing big data analysis services executed on a big data analysis service providing device, A step of collecting data with different structures and formats from multiple data sources, processing it, and storing it in a database; A step of generating an integrated query by connecting tables of the above database, or generating a query that extracts and groups data with user-defined conditions from the above database; A step of generating a dataset by modeling data based on the execution of the above query; Characterized by including the step of training an AI model using the above dataset. Method of providing big data analysis services.
In paragraph 6, The step of generating an integrated query by connecting tables in the above database or generating a query that extracts and groups data with user-defined conditions from the above database Characterized by including the step of generating and executing an integrated query through join conditions and relationship definitions via a graphical user interface that can visually define relationships between multiple tables. Method of providing big data analysis services.
In paragraph 6, The step of generating an integrated query by connecting tables in the above database or generating a query that extracts and groups data with user-defined conditions from the above database Characterized by including the step of generating and executing a query according to the search conditions after the user selects a desired column in the above database and the search conditions required for data retrieval are set. Method of providing big data analysis services.
In paragraph 6, The step of generating a dataset by modeling the data resulting from the execution of the above query Characterized by including the step of converting the extracted data into a data frame or table format, structuring and visualizing it, and generating a model for predictive analysis. Method of providing big data analysis services.
In paragraph 6, The step of training an AI model using the above dataset is Characterized by including the step of visualizing the analysis results after running a machine learning algorithm in an R-Studio or Jupyter-Notebook environment to train a dataset generated by the above data modeling module. Method of providing big data analysis services.

Description

Big Data Analysis Service Providing Device and Method for Performing the Same The present invention relates to a device for providing big data analysis services and a method for executing the same. More specifically, it relates to a big data analysis system and a method for executing the same that allows a user to easily process and analyze data through a query generation tool and to query and process desired data through a visual interface without programming knowledge. In modern society, data has experienced explosive quantitative growth. Data generated through the Internet, social media, the Internet of Things (IoT), and smart devices is diverse and complex, making it difficult to process using traditional database systems. Consequently, the need for new platforms to effectively store, process, and analyze data has emerged. To handle the characteristics of such big data, technologies such as distributed processing systems like Hadoop have been developed. However, systems like Hadoop are difficult for general users to access easily and require a high level of technical understanding. Consequently, there was a need for big data processing tools that are both user-friendly and powerful. Deriving meaningful insights from big data is the core of data analysis. Companies are utilizing data in various ways through big data analysis, such as identifying customer behavior patterns, predicting future trends, and formulating marketing strategies. However, existing data analysis tools have high technical barriers and limitations in analyzing large-scale data. In particular, accurate data analysis and the derivation of reliable results were critical in sectors such as healthcare, finance, and the public sector. Accordingly, the need arose for a system capable of integrating the entire process, from data collection and processing to analysis and visualization. Traditional data processing systems operated using physical servers and high-performance computers, but advancements in cloud computing technology have made it possible to transition this infrastructure to a cloud-based model. Cloud environments offer high flexibility and scalability, as well as the advantage of processing and monitoring data in real time. Consequently, there is a growing need for a system that integrates data analysis tools with the cloud environment to collect and analyze data in real time. The advancement of AI technology has presented a new paradigm for data analysis. Big data and AI are complementary, and AI models can perform tasks such as prediction or classification by learning from and analyzing massive amounts of data. However, the process of building AI models and training data also required significant time and effort. The aforementioned advancements in AI technology have presented a new paradigm for data analysis. Big data and AI are complementary, and AI models can perform tasks such as prediction or classification by learning and analyzing massive amounts of data. However, the process of building AI models and training data also required significant time and effort. FIG. 1 is a network configuration diagram for explaining a big data analysis device system according to one embodiment of the present invention. FIGS. 2 and FIGS. 3 are exemplary diagrams for explaining the execution process of a first query generation module according to the present invention. FIG. 4 is an example diagram illustrating the execution process of a second query generation module according to the present invention. FIGS. 5 to 9 are exemplary diagrams for explaining the execution process of a data modeling module according to the present invention. FIGS. 10 to 13 are exemplary diagrams for explaining the execution process of an AI learning module according to the present invention. The aforementioned objectives, signatures, and advantages are described in detail below with reference to the attached drawings, thereby enabling those skilled in the art to easily implement the technical concept of the present invention. In describing the present invention, detailed descriptions of known technologies related to the present invention are omitted if it is determined that such descriptions would unnecessarily obscure the essence of the invention. Hereinafter, preferred embodiments according to the present invention will be described in detail with reference to the attached drawings. In the drawings, the same reference numerals are used to indicate the same or similar components. FIG. 1 is a network configuration diagram for explaining a big data analysis service providing device according to one embodiment of the present invention. Referring to FIG. 1, the big data analysis service providing device includes a data collection and processing module (110), a first query generation module (120), a second query generation module (130), a data modeling module (140), and an AI learning module (150). The data collection and processing module (110) collects data from variou