• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.1
• /
• pp.89-95
• /
• 2024

Nowadays, the competitiveness of a company depends on the ability of all organizational members to share and utilize the organizational knowledge accumulated by the organization. As if to prove this, the world is now focusing on ChetGPT service using generative AI technology based on LLM (Large Language Model). However, it is still difficult to apply the ChetGPT service to work because there are many hallucinogenic problems. To solve this problem, sLLM (Lightweight Large Language Model) technology is being proposed as an alternative. In order to construct sLLM, corporate data is essential. Corporate data is the organization's ERP data and the company's office document knowledge data preserved by the organization. ERP Data can be used by directly connecting to sLLM, but office documents are stored in file format and must be converted to data format to be used by connecting to sLLM. In addition, there are too many technical limitations to utilize office documents stored in file format as organizational knowledge information. This study proposes a method of storing office documents in DB format rather than file format, allowing companies to utilize already accumulated office documents as an organizational knowledge system, and providing office documents in data form to the company's SLLM. We aim to contribute to improving corporate competitiveness by combining AI technology.

• Journal of Korea Game Society
• /
• v.18 no.4
• /
• pp.75-82
• /
• 2018

With the development of information and communication technology, various methods have been tried to provide learners with a fun educational environment through fun and interest. It is a good example to utilize technologies such as games and robots in education for edutainment and game-based learning. In this study, we propose an intelligent rhythm education system using user data collection and analysis for humanoid robot rhythm generation. To do this, the user selects music and inputs rhythm information according to the selected music. The robot utilization data of this user extracts patterns through collection and analysis. Patterns are based on frequency, and FFT similarity comparison method is applied when past data is insufficient. The proposed method is validated through experiments of kindergarten children.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.4
• /
• pp.595-602
• /
• 2021

Marine accidents are mostly caused by medium and small ships, and are continuously increasing. In this paper, we propose an architecture of the speech synthesis based automatic safety navigation support service providing system for small ships that equiped onboard systems compared with vessels. The main purpose of the system is to prevent marine accidents by providing synthesized voice safety messages to nearby ships. The safety navigation support service is operated by connecting GPS and AIS to synthesize voice safety messages, automatically broadcast through VHF. Therefore, we developed a data processing module, a staged risk analysis module, a voice synthesis safety message generation module, and a VHF broadcasting equipment control module, which are components of the system. In addition, we conducted laboratory-level and sea-trial demonstration tests using the developed the system, which verified usefulness of the proposed service.

• The Journal of the Convergence on Culture Technology
• /
• v.10 no.5
• /
• pp.673-679
• /
• 2024

Recently, various contents set in the Josun Dynasty have emerged. However, there is a growing number of hanboks that do not preserve the basic original form of hanbok, such as hanboks that deviate significantly from the form of hanboks. Therefore, in this study, a system was created and implemented in the game to express various colors and patterns of hanbok using the DALL-E API in this game by examining the basic hanbok form of hanbok through literature review. However, despite the fact that the results are inconsistent depending on the quality of the Generative AI service and the limitations of not passing through the historical evidence of traditional hanbok experts, it is meaningful to present a system that uses the creativity of users to create a design that can enhance the aesthetics of traditional hanbok. In future research, we want to investigate users' preferences and develop a system that can create an image that fits them when clicking the interface.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.9
• /
• pp.421-428
• /
• 2024

Recently, services utilizing large-scale language models (LLMs) such as GPT-4 and LLaMA have been released, garnering significant attention. These models can respond fluently to various user queries, but their insufficient training on Korean data raises concerns about the potential to provide inaccurate information regarding Korean culture and language. In this study, we selected eight major publicly available models that have been trained on Korean data and evaluated their understanding of Korean culture using a dataset composed of five domains (Korean language comprehension and cultural aspects). The results showed that the commercial model HyperClovaX exhibited the best performance across all domains. Among the publicly available models, Bookworm demonstrated superior Korean language proficiency. Additionally, the LDCC-SOLAR model excelled in areas related to understanding Korean culture and language.

• Journal of KIISE:Software and Applications
• /
• v.36 no.9
• /
• pp.732-748
• /
• 2009

The technology of Semantic Web realizes the base technology for context-awareness that creates new services by dynamically and flexibly combining various resources (people, concepts, etc). According to the realization of ubiquitous computing technology, many researchers are currently working for the embodiment of web service. However, most studies of them bring about the only predefined results those are limited to the initial description by service designer. In this paper, we propose a new service supporting model to provide an automatic method for plan related tasks which achieve goal state from initial state. The inputs on an planner are intial and goal descriptions which are mapped to the current situation and to the user request respectively. The idea of the method is to infer context from world model by DL-based ontology reasoning using OWL domain ontology. The context guide services to be loaded into planner. Then, the planner searches and plans at least one service to satisfy the goal state from initial state. This is STRIPS-style backward planner, and combine OWL-S services based on AI planning theory that enabling reduced search scope of huge web-service space. Also, when feasible service do not find using pattern matching, we give user alternative services through DL-based semantic searching. The experimental result demonstrates a new possibility for realizing dynamic service modeler, compared to OWLS-XPlan, which has been known as an effective application for service composition.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.151-158
• /
• 2021

In this paper, we analyzed the latest research trends, challenges, and potential applications of next-generation solar cell materials in various industrial fields. In addition, future prospects and possibilities of Smart Textile Hybrid Energy Harvesting Devices that will supply electricity by combining with wearable IoT devices are presented. The hybrid textile energy harvesting device fused next-generation solar cells with tribo-piezoelectric devices will develop into new 'Convergence Integrated Smart Wear' by combining the material itself with wearable IoT devices in the era of the 4th industrial revolution. The next-generation nanotechnology and devices proposed in this paper will be applied to the field of smart textile with an energy harvesting function. And we hope it will be a paradigm shift that evolves into creative products which provide AI services such as medical & healthcare by convergence with the future smart wear industry.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.267-286
• /
• 2023

The conversational agents such as AI speakers utilize voice conversation for human-computer interaction. Voice recognition errors often occur in conversational situations. Recognition errors in user utterance records can be categorized into two types. The first type is misrecognition errors, where the agent fails to recognize the user's speech entirely. The second type is misinterpretation errors, where the user's speech is recognized and services are provided, but the interpretation differs from the user's intention. Among these, misinterpretation errors require separate error detection as they are recorded as successful service interactions. In this study, various text separation methods were applied to detect misinterpretation. For each of these text separation methods, the similarity of consecutive speech pairs using word embedding and document embedding techniques, which convert words and documents into vectors. This approach goes beyond simple word-based similarity calculation to explore a new method for detecting misinterpretation errors. The research method involved utilizing real user utterance records to train and develop a detection model by applying patterns of misinterpretation error causes. The results revealed that the most significant analysis result was obtained through initial consonant extraction for detecting misinterpretation errors caused by the use of unregistered neologisms. Through comparison with other separation methods, different error types could be observed. This study has two main implications. First, for misinterpretation errors that are difficult to detect due to lack of recognition, the study proposed diverse text separation methods and found a novel method that improved performance remarkably. Second, if this is applied to conversational agents or voice recognition services requiring neologism detection, patterns of errors occurring from the voice recognition stage can be specified. The study proposed and verified that even if not categorized as errors, services can be provided according to user-desired results.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.207-216
• /
• 2024

As big data was built due to the 4th Industrial Revolution, personalized services increased rapidly. As a result, the amount of personal information collected from online services has increased, and concerns about users' personal information leakage and privacy infringement have increased. Online service providers provide privacy policies to address concerns about privacy infringement of users, but privacy policies are often misused due to the long and complex problem that it is difficult for users to directly identify risk items. Therefore, there is a need for a method that can automatically check whether the privacy policy is safe. However, the safety verification technique of the conventional blacklist and machine learning-based privacy policy has a problem that is difficult to expand or has low accessibility. In this paper, to solve the problem, we propose a safety verification technique for the privacy policy using the GPT-3.5 API, which is a generative artificial intelligence. Classification work can be performed evenin a new environment, and it shows the possibility that the general public without expertise can easily inspect the privacy policy. In the experiment, how accurately the blacklist-based privacy policy and the GPT-based privacy policy classify safe and unsafe sentences and the time spent on classification was measured. According to the experimental results, the proposed technique showed 10.34% higher accuracy on average than the conventional blacklist-based sentence safety verification technique.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.967-971
• /
• 2023

Recently, a variety of AI-based platform services are available, and one of them is ChatGPT that processes a large quantity of data in the natural language and generates an answer after self-learning. ChatGPT can perform various tasks including software programming in the IT sector. Particularly, it may help generate a simple program and correct errors using C Language, which is a major programming language. Accordingly, it is expected that ChatGPT is capable of effectively using Verilog HDL, which is a hardware language created in C Language. Verilog HDL synthesis, however, is to generate imperative sentences in a logical circuit form and thus it needs to be verified whether the products are executed properly. In this paper, we aim to select small-scale logical circuits for ease of experimentation and to verify the results of circuits generated by ChatGPT and human-designed circuits. As to experimental environments, Xilinx ISE 14.7 was used for module modeling, and the xc3s1000 FPGA chip was used for module embodiment. Comparative analysis was performed on the use area and processing time of FPGA to compare the performance of ChatGPT products and Verilog HDL products.