Bigdata Application Cases


National big data analysis platform building

Spatial big data system building project – MLIT – received an MLIT Minister award

Productive intelligent spatial data was built by fusing structured and non-structured big data and text data based on spatial data such as administrative and private information. Based on this, various analysis models and templates, along with workflow-based analysis tools, are provided so that users can easily and quickly use and analyze the analysis models in the web environment. In addition, it provided a multi-purpose spatial big data analysis standard platform based on spatial big data, along with its service environment. To make it possible to proactively respond to national affairs and establish future strategies, intelligent spatial big data are built and the framework for smart administration is established.


<MLIT – spatial big data system portal>

① Business contents

  1. Integrated DB building: By providing the results of various integrated DBs in the form of a dashboard through the integrated data service, users can easily understand and access the spatial data. It provides various types of result values ​​in the form of a dashboard
  2. Data Service Development: You can download related data via a query using the data service that classifies datasets into fusion and basic data. It provides a screen division-type visualization service in which you can effectively utilize the time-series information of convergence DB
  3. Building an analysis platform and developing visualization service: The data provided by spatial information and spatial big data and the spatial library provided by the spatial big data analysis tool are used to build a spatial big data analysis platform that supports analysis. In addition, it also provides a visualization service in which spatial Hadoop-based analysis results are visualized and displayed on a map
  4. Development of social-spatial analysis service: A service is provided that performs emotion analysis on non-structured data by sentence unit, combines it with existing location information, identifies relationships with issues, and analyzes major topics and vocabulary trends according to regions and visualizes them on a map

<spatial big data analysis feature>

② Application technology and solutions

  1. Bigdata Suite product application
    To implement smart data based on structured ·non-structured spatial big data and big data analysis platform of the next generation, Bigdata Suite’s product is applied which enables one-stop real-time spatial big data analysis
  2. HDP 3.2 product application
    By applying HDP 3.2 packaged by Horton Works, it connects Bigdata suite product with Hadoop Eco System and constructs optimal spatial big data analysis platform.

③ Validity of product selection

  1. Evaluation on product quality excellence and exceptional performance with Bigdata Suite Pilot
    The pilot system, consisting of the first building system and the Bigdata Suite, is tested for its performance and quality on all stages of the big data life cycle by external experts appointed by MLIT, and then quality and performance excellence of the Bigdata Suite Pilot system is evaluated

④ Main accomplishments

  1. Received an MLIT Minister award among the building projects under the auspice of MLIT
  2. Supporting government-wide use of the system by establishing a spatial big data system using spatial information in order to implement scientific administration and provide customized services
  3. We establish the groundwork for common utilization of spatial big data, so that central administrative offices, local governments, and public corporations can establish rational and objective policies using spatial information in the public sector
    • Preemptive response to socio․economic issues in real estate, education, welfare, crime, and disasters, etc.
    • Support for future national strategies building and decision making through scientific spatial analysis technology
  4. Promotion of the spatial informational industry, including new industry and job creation, through the development, expansion of various utilization service models using spatial big data
  5. The spatial big data system provides, for user utilization, an environment in which users can develop analysis models more easily and quickly in various kinds of templates and web environment
  6. This provides users with the feature in which new analysis models are developed and analysis results are derived by combining data and analysis functions according to their purpose
  7. It uses spatial Hadoop-based location information to introduce visualization, achieves time series informatization through screen division, and provides a service in which analysis results such as past information and future prediction can be visually presented

New technology sensing & prediction analysis platform building

Samsung Electronics new technology sensing system building – Samsung Electronics & Samsung Semiconductors

To establish an early risk detection system for future technology and business uncertainty, we combined and integrated the two following pieces of knowledge. One is knowledge information accumulated in Samsung Electronics and Samsung Semiconductor’s internal KMS. The other is the materials supplied through MOU contract with KISTI: a large number of technical documents including overseas academic data, information on domestic conferences, various research reports, information on trend analysis of overseas science and technology, domestic and international IT news, IT professional review/blog, technical magazines, etc.

In addition, by establishing an automatic system for collecting and analyzing new technology information, new technology early sensing capabilities are strengthened on new technologies and applications. Through various analysis and prediction features of new technology sensing, such as response to risks due to the limitations of continuous technology and the emergence of non-continuous technology, venture investment to complement business risks, and establishment of M & A strategies, we have laid the foundation for internal data-based decision support.


<Samsung Electronics – new technology sensing system>

① Business contents

  1. Building of data collection system: Building an integrated DB for new technology sensing and predictive analysis by establishing a collection system that applies various collection features for various internal and external types of structured and unstructured data
  2. Building of data modeling and knowledge base: In order to extract various relevant information from technical documents and social data (news, blogs, etc.) generated and collected externally as well as internally generated knowledge to secure new technology sensing quality, various data models were built, and through this, technical and corporate information knowledge bases (person/paper/patent association, technology/company/person association, company/investment institution/person association) were established
  3. Building of New Technology Sensing Platform and Analysis Service Development: Samsung Electronics built a new technology sensing/prediction/analysis platform that collects, stores, processes, analyzes, and visualizes internal knowledge and externally collected data. Correlation analysis, knowledge trend analysis, knowledge information network analysis, and real-time new technology sensing/prediction analysis were conducted for various large amounts of data. It provides a service that can visualize and present the results of various analysis features

② Application technology and solutions

  1. Bigdata Suite product application
    Application of Bigdata Suite product that enables real-time/batch analysis to realize intelligent new technology sensing and predictive analysis platform based on internal knowledge information and external technical data

③ Validity of product selection

  1. Proven excellence in product performance and quality tests through PoC
    • After preliminary verification of the big data analysis platform to be applied to the construction of new technology sensing platform for Samsung Electronics KMS, POC is conducted three times, and the winner is selected based on the excellence in product performance and quality
    • We perform various verifications such as data collection, storage, analysis, visualization, and system performance for each Korean and English data, and select Bigdata Suite for intelligent new technology sensing and predictive analysis platform

④ Main accomplishments

  1. The simple search function only yielded a series of simple descriptions or individual keywords. With these limited functions, it was almost impossible to look at the entire technology network or identify trends in technical analysis. However, thanks to the new technology sensing system, it was possible to obtain information trends in ability, application technology, or technology of interest, just like seeing the forest over trees. So it was able to meet the exploratory technical needs of the employees at Samsung Electronics that have huge and individual technical issues.
  2. This has dramatically increased the number of KMS connections and users three to five times since the opening of the existing system, thereby increasing and improving Samsung Electronics’ knowledge management activities.

Media content analysis platform building

New big data analysis building – Korean Press Foundation

The aim was to revolutionize journalism services and develop them into differentiated government/national services by building high value-added knowledge base out of news media contents built by decades of domestic media organizations. We built a platform to systematically analyze a large amount of news data, and built analytical data for intelligent analysis. By establishing various analysis services and management systems for users, media organizations that produce high-quality journalism information such as media-based intelligent analysis, integration, and prediction services continue to derive higher-quality next-generation media contents in the future and lay the foundation for innovation in distribution support.


<Korean Press Foundation – news big data analysis service (BIGKinds)>

① Business contents

  1. News big data DB establishment: Ranging from domestic comprehensive daily newspaper, economic daily newspaper, TV broadcasting news, internet newspaper, English daily newspaper, regional weekly newspaper and old newspaper, to the pre-90s newspaper and overseas news, the largest article DB was built.
  2. News big data analysis platform building: In order to analyze news big data, we built a platform for deep analysis of news big data. This includes intelligent natural language processing engines capable of analyzing English as well as Korean, machine learning-based unstructured text analysis engines, and semantic-based search engines.
  3. News big data analysis service development: It provides Big Kinds search services for the general public and Big Kinds professional services for professionals by using semantic-based news search features with news big data.
  4. Through deep news analysis, it provides a feature that produces relevant information between news and stock index and its predictive analysis. It analyzes news articles, extracts citations, and provides a news source analysis (network) feature in which the sources of citations are analyzed. In addition, it provides a trend report feature, along with various analysis features, to users, such as deep analysis of overseas news, analysis of political news of each country, and trend analysis on national press reports, related analysis, and network analysis.

<News big data analysis feature>

② Application technology and solutions

  1. Bigdata Suite product application
    Application of Bigdata Suite product in which one-stop real-time media content big data analysis is made possible, in order to implement unstructured news big data analysis platform based on domestic/overseas news content
  2. Application of Apach SPARK, STORM, KAFKA, etc.
    OpenSource Apach SPARK, STORM, and KAFKA will be applied to the news big data platform and linked with Bigdata Suite products, which creates a news big data analysis platform that guarantees optimal quality

③ Main accomplishments

  1. By building and analyzing large-scale news data, it contributes to nationally important historical asset accumulation, social change prediction, and policy-making and business opportunities
  2. On the economic side, it also lays the foundation on which a creative economic brain that can predict and respond to future situations or circumstances plays a role
  3. Media organizations, the producers of high-quality journalism information, will lay the groundwork for an innovative system in which higher-quality next-generation media contents are continuously generated and distributed in the future
  4. It provides a global news analysis system service using the news big data analysis system and a service that analyzes differences in media coverage by country on specific issues. Therefore, it can be a leading example in the global news analysis service area
  5. It contributes to raising social awareness of the value of news utilization and creating a corresponding profit model based on media content
  6. It provides customized news and related information by analyzing characteristics and dispositions of vast news data, individual users, and institutions

Financial data & real-time VOC analysis platform building

Intelligent real-time VOC analysis system building – Nonghyup Bank

As the use of digital channels by customers is expected to increase and the demand for intelligent services will continue to rise, customer satisfaction and operational efficiency should be improved by expanding AI-based services. To this end, we established a AI big data system call center with the goal of upgrading and improving existing systems.

Real-time voice processing, language analysis processing, and large-scale distributed environment were applied to the counseling big data analysis system that records, stores and analyzes daily telephone counseling contents generated by Nonghyup Bank Customer Happiness Center. It developed a structure that enables real-time TA (Text Analysis) analysis service and provided the result of consultation data analysis in a timely and appropriate manner. Therefore, we laid the foundation for intelligent VOC analysis and TA analysis that can be analyzed and studied from various purposes and perspectives.


<Nonghyup Bank – intelligent financial data analysis>

① Business contents

  1. Data storage and operational environment improvement: Collected counseling big data is stored in the message queue, indexed by dispersion applications, stored in a big data repository, and then turned into services through text analysis
  2. Intelligent Knowledge Management System building: The knowledge information constructed/managed through the new KMS (Intelligent Knowledge Management System) is managed at the same time as the knowledge base, and a structure that can automatically distribute it to the Q & A system is developed
  3. TA service composition: Providing issue cloud and issue trends analysis features.
    • Providing a feature of emotion analysis on issue keywords.
    • Providing a navigation feature on related topic analysis
    • Providing a feature of automatically collecting consultation results

<Intelligent VOC analysis and TA analysis feature>

② Application technology and solutions

  1. Bigdata Suite product application
    Application of Bigdata Suite products that will make up consultation data collection class, message class, big data indexing class, utilization class, etc.
  2. Application of Apach SPARK, STORM, KAFKA, etc.
    OpenSource Apach SPARK, STORM, and KAFKA will be applied to the news big data platform and linked with Bigdata Suite products, which creates an intelligent financial big data analysis platform that guarantees optimal quality

③ Validity of product selection

  1. It guarantees the integrity in large data collection of Bigdata Suite and prevents any loss in real-time data transmission and reception. In addition, through distributed processing environment and in-memory analysis, it selects the product that guarantees the performance of the big data system even in large-scale aggregation and analysis processing
  2. It selects products that meet the needs of an analytics platform system that can accommodate both real-time and batch analysis of ever-increasing consultation data
  3. It selects products that can perform high-performance big data analysis through in-memory-based aggregation and statistical analysis and real-time indexing and distributed processing

④ Main accomplishments

  1. It enables smooth service even during customer-intensive consultations, where the system may be overloaded due to the increase in the number of users, and the system infrastructure is flexible enough to buffer continuous data growth or service expansion in the future
  2. It improves TA analysis feature and service for real-time issue analysis and consultation quality evaluation
    • It provides relevance to search, statistics, trend analysis, etc. for counseling issues, improves the UI so that it can be analyzed in-depth, and provides analysis results in the form of visualization services
    • By monitoring the counselor’s customer consultation in real-time, or by automating part of the quality evaluation of the counseling results, timely detection and improvement of mistaken consultation or inappropriate response can lead to improved customer satisfaction.
  3. It is necessary to convert voice data into text and analyze the unstructured text and present the results and provide an intelligent recognition analysis feature that can process it in large quantities in real-time

Intelligent integration search system building

Posco GIH (Global Information Hub) building project – POSRI

IT systems need to be built to support the GIH process efficiently and support strategic decision-making in the affiliates. The purpose is to establish a POSCO Family Integrated Information Management Network for integrated management of domestic and international external information managed by POSCO and family companies in GIH, and analyzed and processed by experts in each field.

Intelligent analysis of structured and unstructured data was performed for GIH internal information and external information, and the semantic search of related topics and issues keywords maximizes more accurate information retrieval and monitoring capability. We have made it possible to conduct more three-dimensional and meaningful analysis of accumulated unstructured data such as trend analysis, trend analysis, and related topic analysis on specific topics.


<Posco – semantic integration search & analysis>

① Business contents

  1. Establishing a semantic-based intelligent integrated search system: By analyzing in real-time the top 100 of the important documents among the documents that include the user’s query or selected keywords (topics), we extract relevant information that is most closely related to the search terms. In doing so, we build an intelligent search system that can be retrieved in the form of a radial tree
  2. Intelligent search feature development:
    • Search results clustering: It provides document clustering results by analyzing in real-time search result documents for user query
    • Popular search words: It statistically extracts the search term history used by the user to create a ranking and display it visually
    • Automatic Classification search: Through automatic information (document) classification, it provides a feature to search through the classification system for the data classified automatically
    • Search for similar documents: Similar documents are searched from various sources and the search results are provided in real-time
  3. Intelligent trend analysis function and service development: It analyzes the CEO’s message and information needs data, extracts key keywords by period, extracts keywords that become issues during the period, and then provides visual analysis services in which various charts are presented to the users

<Meaning-based intelligent integration search and trends analysis>

② Application technology and solutions

  1. Bigdata Suite product application
    In order to perform intelligent retrieval and data analysis of structured and unstructured data for GIH internal and external information, storage/search engine (DISCOVERY) and unstructured analysis engine (TMS) of Bigdata Suite products are applied

③ Validity of product selection

  1. It selects the DISCOVERY and unstructured analysis engine (TMS), which guarantee the best performance and quality in Korea since they have won the GS Certification, SW Certification for Administrative Business, New SW Product Award, and Presidential Award of Korea SW Grand Prize

④ Main accomplishments

  1. Strengthening Posco Family information competitiveness
    Providing useful information fast and accurately
    Sharing information through division of labor and cooperation
    Efficient use of information and business productivity increase through the use of up to date information technology
  2. Posco Family information mind and cultural settlement
    Evolution of information mind through information collection and use (formation→expansion→settlement)
    Encouraging change management through information activity monitoring and feedback
  3. Finding strategic insight information
    Systematic accumulation of domestic and overseas meaningful information
    Supporting decision making through the use of strategic insight information
    Finding new business ideas and preemptive response to management risks
  4. Strengthening POSRI information-based analysis power
    Efficient communication between POSRI and Families and decision making Support base building
    Strengthening POSRI field research/task through information gathered live at home and abroad