• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.129-164
• /
• 2023

In a situation where the use and introduction of Large Language Models (LLMs) is expanding due to recent developments in generative AI technology, it is difficult to find actual application cases or implementation methods for the use of internal company data in existing studies. Accordingly, this study presents a method of implementing generative AI services using the LLM application architecture using the most widely used LangChain framework. To this end, we reviewed various ways to overcome the problem of lack of information, focusing on the use of LLM, and presented specific solutions. To this end, we analyze methods of fine-tuning or direct use of document information and look in detail at the main steps of information storage and retrieval methods using the retrieval augmented generation (RAG) model to solve these problems. In particular, similar context recommendation and Question-Answering (QA) systems were utilized as a method to store and search information in a vector store using the RAG model. In addition, the specific operation method, major implementation steps and cases, including implementation source and user interface were presented to enhance understanding of generative AI technology. This has meaning and value in enabling LLM to be actively utilized in implementing services within companies.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.7 no.2
• /
• pp.57-68
• /
• 2004

Recently in order to more effectively and scientifically process forest official tasks, which have been focused on documents and inventories, they should be applied with the up-to-date spatial information technologies. Especially, the forest resource information management based on GIS(geographic information system) and aerial orthophoto is expected not only to play an important role as DSS(decision support system) for domestic forest conservation policy and forestry development industry but also to service forest resource information toward people such as the owners of a mountain rapidly. In this study, the important forest information such as digital topography map, digital forest type map, digital forest cadastral map, digital aerial photographs and attribute data were first reprocessed and constructed in DBMS(data base management system). In addition, forest officials could analyze and retrieve forest information by using detail sub-application systems such as forest cadastral retrieval, forest land development information management, reserved forest information management and forest resource information retrieval. For this, the user interface is developed by using Visual Basic 6.0 and MapObjects 2.1 of ESRI based on CBD(component based development) technology. The result of developing this system will not only perform constructing economical forest and better environment but also be the foundation of domestic spatial technology for forest resource management.

• Convergence Security Journal
• /
• v.16 no.7
• /
• pp.167-172
• /
• 2016

The purpose of this study is to provide implications for preventing insider information leakages in public agencies for national security. First, the study examined the definitions and current usage of information security systems of public agencies were examined. Second, web-service base information leaks and malware-base information leaks were discussed and three major credit card companies' personal information leakage cases were analyzed. Based on the analysis, four solutions were provided. First, information leakages can be protected by using web filtering solutions based on the user, which make possible to limit frequencies of malware exposures. Second, vaccine programs and vaccine management system should be implemented to prevent information leakages by malware. Third, limit the use of portable devices within local networks to prevent information leakages and vaccines programs for malware should be regularly used. Forth, to prevent information leakages by smartphone malwares, data encryption application should be used to encrypt important information.

• Journal of Digital Convergence
• /
• v.14 no.5
• /
• pp.273-281
• /
• 2016

The issue about the safety management of gas related work has been studied toward a direction to utilize IoT system recently. For this purpose, the matters of user's demand has been deduced through the literature survey, field survey, and professional consultation, by studying the characteristics of worker, work, and work site. In summary, these are the demands for mobile App, 1)a clear arrangement of contents, 2)a design with high readability, 3)a design with low death, 4) securing of user's accessibility, 5)an effective information transmission plan in the work section where it is impossible to operate the mobile device, 6)an activation of alarm function at the section of high working error, 7)a fast two-way transmission and receipt of safety inspection matter needed at work, 8)a selection of images and contents that can guide the situation to the worker in case of accident, 9)an alarm function for the degree of danger in an area of worker's location. Based on these, a basic design of safety application for gas related work has been proposed, that can secure the user accessibility.

• Journal of Korean Society of Transportation
• /
• v.29 no.2
• /
• pp.37-45
• /
• 2011

The main objective of this study is two-fold: 1) to analyze the effect of PG technology application on road user's satisfaction and driving speed, and 2) to investigate the relationship between driver's subjective workload level and their reactions related to the PG technology application. Based on the result of field observation, the experimental scenario for driving simulation study was prepared. The experimental results showed that drivers were more satisfied to the road condition with PG technology applied, and even the pattern of speed reduction was more stable than control condition. The pattern of speed reduction along driver's subjective driving workload level were slightly different by physical road condition, and road user's satisfaction was revealed to be negatively correlated with their subjective driving workload level. This result indicates that depending on situation and driver characteristic, information for the drivers could be nothing more than nuisance that just distracts drivers. In order to facilitate the implementation of PG technology in Korea, further study on related human factors, especially for those who are weak in traffic situations, is recommended.

• Journal of Service Research and Studies
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2020

As big data become more important socially and economically in recent years, many problems have been derived from the indiscriminate application of big data. Big data are valuable because it can figure out the meaning of informative information hidden within the data. In particular, to predict customer behavior patterns and experiences, structured data that were extracted from Customer Relationship Management (CRM) or unstructured data that were extracted from Social Network Service(SNS) can be defined as a population to interpret the data, during which many errors can occur. However, those errors are usually overlooked. In addition to data analysis techniques, some data, which should be considered in the analysis, are not included in the population and thus do not show any meaningful patterns. Therefore, this study presents the measurement and interpretation of the data generated when the cause of error in the population setting is strong relationship and interaction between people or a person and an object. In other words, it will be shown that if the relationship and interaction are strong, it is important to include data collected from the perspective of user experience and ethnography in the population by comparing various cases of big data application, through which the meaning will be derived and the best direction will be suggested.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.129-140
• /
• 2021

The next generation mBcN should be built to cooperate with the wireless network to support hyper-speed and hyper-connectivity. In this paper, we propose a network architecture for the cooperation mBcN and 5G commercial network and architecture of the cooperative security gateway required for the cooperation. The proposed cooperative security gateway is between gNB and UPF to support LBO, SFC, and security. Our analysis shows that the proposed architecture has several advantages. First of all, user equipment connected with the mBcN can be easily connected through the 5G commercial radio network to the mBcN. Second, the military application traffic can be transmitted to mBcN without going through the 5G core network, reducing the end-to-end transmission delay without causing the traffic load on the 5G core network. In addition, the security level of the military application can effectively be maintained because the user equipment can be connected to the cooperative security gateway, and the traffic generated by the user equipment is transmitted to the mBcN without going through the 5G core network. Finally, we demonstrate that LBO, SFC, and security modules are essential functions of the proposed gateway in the 5G test-bed environment.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.10
• /
• pp.709-721
• /
• 2006

The traditional broadcasting services over terrestrial, satellite and cable media have been unidirectional mass media regardless of TV viewer's preferences. Recently ich media streaming has become possible via the broadb and networks. Furthermore, since bidirectional communication is possible, personalcasting such as personalized streaming services has been emerging by taking into account the user's preference on content genres, viewing times and actors/actresses etc. Accordingly, personal media becomes an important means for content provision service in addition to the traditional broadcasting service as mass media. In this paper, we introduce a user profile reasoning method for target advertisement which is considered an important application in personalcasting service. The proposed user profile reasoning method predicts an unknown TV viewer's gender and ages by analyzing TV Viewing history data. Based on the estimated user's gender and ages, a target advertisement is provided with TV Anytime metadata. A proposed target advertisement system is developed based on the user profile reasoning and the target advertisement selection method. To show the effectiveness of our proposed methods, we present a plenty of experimental results by using realistic TV viewing history data.

• The KIPS Transactions:PartC
• /
• v.13C no.4 s.107
• /
• pp.501-510
• /
• 2006

Software streaming allows the execution of stream-enabled software on desktop or portable computing devices like PC, PDA, laptop, cellular phone, etc., even while the transmission/streaming from the server may still be in progress. In this paper, we present an efficient streaming system called Software On-Demand(SOD) streaming system to transmit stream-enabled applications in addition to automatic installation of program registry, environment variables, configuration files, and related components. In particular, we design and implement a SOD system in Linux to provide the user with the instant look-and-click software execution environment such that software download and installation are internally proceeded in a completely user-transparent way. Therefore, the SOD system relieves the user from the tricky, failure-prone installation business. In addition, the software developer now obtains a new, powerful means to advertise and propagate their software products since the user can use software packages via user-friendly UI window or web browser by look-and-click interactive operation. In the paper, we also make a couple of SOD streaming experiments using a spectrum of popular softwares. Based on the analysis of the experiment results, we also propose two performance improvement schemes.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.2
• /
• pp.101-122
• /
• 2011

Information literacy(IL) is the essential skill in the knowledge information society in the 21st century. Spreading the awareness of importance of IL across the world, the efforts to develop and implement IL standards or instructions are expanded around United States, United Kingdom, and Australia. In this study, Author extracts the core elements of IL from domestic and foreign IL standards and integrates those with Kuhlthau's Information Search Process(ISP) Model in order to develop the curriculum model of IL for undergraduates. The curriculum model has been constructed by consideration of capability of application to practice and expressed as the syllabus for the structure of university education. In the curriculum model, major instructional contents are extracted from 6 core elements of IL and the contents are organized by 6 ISP stages. Author suggests some successive studies based on the curriculum model for expansion and advancement of IL instruction.