• Journal of Astronomy and Space Sciences
• /
• v.20 no.2
• /
• pp.109-122
• /
• 2003

To examine the causal relationship between geomagnetic storm and substorm, we investigate the correlation between dispersionless particle injection rate of proton flux observed from geosynchronous satellites, which is known to be a typical indicator of the substorm expansion activity, and Dst index during magnetic storms. We utilize geomagnetic storms occurred during the period of 1996 ~ 2000 and categorize them into three classes in terms of the minimum value of the Dst index ($Dst_{min}$); intense ($-200nT{$\leq$}Dst_{min}{$\leq$}-100nT$), moderate($-100nT{\leq}Dst_{min}{\leq}-50nT$), and small ($-50nT{\leq}Dst_{min}{\leq}-30nT$) -30nT)storms. We use the proton flux of the energy range from 50 keV to 670 keV, the major constituents of the ring current particles, observed from the LANL geosynchronous satellites located within the local time sector from 18:00 MLT to 04:00 MLT. We also examine the flux ratio ($f_{max}/f_{ave}$) to estimate particle energy injection rate into the inner magnetosphere, with $f_{ave}$ and $f_{max}$ being the flux levels during quiet and onset levels, respectively. The total energy injection rate into the inner magnetosphere can not be estimated from particle measurements by one or two satellites. However, the total energy injection rate should be at least proportional to the flux ratio and the injection frequency. Thus we propose a quantity, “total energy injection parameter (TEIP)”, defined by the product of the flux ratio and the injection frequency as an indicator of the injected energy into the inner magnetosphere. To investigate the phase dependence of the substorm contribution to the development of magnetic storm, we examine the correlations during the two intervals, main and recovery phase of storm separately. Several interesting tendencies are noted particularly during the main phase of storm. First, the average particle injection frequency tends to increase with the storm size with the correlation coefficient being 0.83. Second, the flux ratio ($f_{max}/f_{ave}$) tends to be higher during large storms. The correlation coefficient between $Dst_{min}$ and the flux ratio is generally high, for example, 0.74 for the 75~113 keV energy channel. Third, it is also worth mentioning that there is a high correlation between the TEIP and $Dst_{min}$ with the highest coefficient (0.80) being recorded for the energy channel of 75~113 keV, the typical particle energies of the ring current belt. Fourth, the particle injection during the recovery phase tends to make the storms longer. It is particularly the case for intense storms. These characteristics observed during the main phase of the magnetic storm indicate that substorm expansion activity is closely associated with the development of mangetic storm.

• Korean Journal of Remote Sensing
• /
• v.36 no.5_2
• /
• pp.867-879
• /
• 2020

As the era of space technology utilization is approaching, the launch of CAS (Compact Advanced Satellite) 500-1/2 satellites is scheduled during 2021 for acquisition of high-resolution images. Accordingly, the increase of image usability and processing efficiency has been emphasized as key design concepts of the CAS 500-1/2 ground station. In this regard, "CAS 500-1/2 Image Acquisition and Utilization Technology Development" project has been carried out to develop core technologies and processing systems for CAS 500-1/2 data collecting, processing, managing and distributing. In this paper, we introduce the results of the above project. We developed an operation system to generate precision images automatically with GCP (Ground Control Point) chip DB (Database) and DEM (Digital Elevation Model) DB over the entire Korean peninsula. We also developed the system to produce ortho-rectified images indexed to 1:5,000 map grids, and hence set a foundation for ARD (Analysis Ready Data)system. In addition, we linked various application software to the operation system and systematically produce mosaic images, DSM (Digital Surface Model)/DTM (Digital Terrain Model), spatial feature thematic map, and change detection thematic map. The major contribution of the developed system and technologies includes that precision images are to be automatically generated using GCP chip DB for the first time in Korea and the various utilization product technologies incorporated into the operation system of a satellite ground station. The developed operation system has been installed on Korea Land Observation Satellite Information Center of the NGII (National Geographic Information Institute). We expect the system to contribute greatly to the center's work and provide a standard for future ground station systems of earth observation satellites.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.31 no.2
• /
• pp.43-57
• /
• 2013

The purpose of this study is to identify potential semantic landscape makeup of "the Forty Eight Poems of Soswaewon" according to Yin-Yang and Five Elements Principle(陰陽五行論). that speculation system between human's nature and cosmical universal order. Existing academic discussions made so far concerning this topic can be summed up as follows: 1. Among Yin-Yang-based landscape makeups of the Forty Eight Poems of Soswaewon, poetic writings for embodiment of interactions between nature and human behaviors focused on depicting dynamic aspects of a poetic narrator when he appreciates or explores hills and streams as of to live free from worldly cares. Primarily, many of those writings were created on the east and south primarily through assignment of yang. On the other hand, poetic writings for embodiment of nature and seasonal scenery - as static landscape makeup of yin - were often created on or near the north and west for many times. Those writings focusing on embodiment of nature and artificial scenery as a work are divided into two categories: One category refers to author Kim In-hu's expression of semantic landscape from seasonal scenery in nature. The other refers to his depiction of realistic garden images as they are. In the Forty Eight Poems of Soswaewon, the poetic writings show that author Kim focused on embodying seasonal scenery rather than expressing human behaviors. In addition, both Poem No. 1 and Poem No. 48(last poem; titled 'Jangwon Jeyeong') were created in a same place, which author Kim sought to understand the place as a space of beginning and end where yin and yang - i.e. the principle of natural cycle - are inherent. 2. According to construction about landscape in the Forty Eight Poems of Soswaewon on the basis of Ohaeng-ron (five natural element principle), it was found that tree(木) and fire(火) are typical examples of a world combined by emanation. First, many of poetic writings depicting the sentiments of tree focused on embodying seasonal scenery and were located in the place of Ogogmun(五曲門) area in the east, from overall perspective of Soswaewon. The content of these poems shows generation and curve / straightness in flexibility and simplicity. Many of poems depicting the sentiments of fire(火) focused on embodying human behaviors, and they were created in Aeyangdan area on the south of Soswaewon over which sun rises at noon. These poems are all on a status of side movement that is characterized by emanation and ascension which belong to attributes of yang. 3. With regard to Ohaeng-ron's interpretation about landscape in the Forty Eight Poems of Soswaewon, it was found that metal(金) and water(水) are typical examples of world combined by convergence. First, it was found that all of poems depicting sentiments of metal focused on embodying seasonal scenery, and were created in a bamboo grove area on the west from overall perspective of Soswaewon. They represent scenery of autumn among 4 seasons to symbolize faithfulness vested in a man of virtue(seonbi) with integrity and righteousness. Poems depicting sentiments of water were created in vicinity of Jewoldang on the north, possibly topmost of Soswaewon. They were divided into two categories: One category refers to poems embodying actions of welcoming the first full moon deep in the night after sunset, and the other refers to poems embodying natural scenery of snowscape. All of those poems focused on expressing any atmosphere of turning into yin via convergence. 4. With regard to Ohaeng-ron's interpretation of landscape in the Forty Eight Poems of Soswaewon, it was found that poems depicting sentiments of earth(土), a complex body of convergence and emanation, were created in vicinity of mountain stream around Gwangpunggak which is located in the center of Soswaewon. These poems focused on carrying actions of author Kim by way of natural phenomena and artificial scenery.

• Sijohaknonchong
• /
• v.30
• /
• pp.263-300
• /
• 2009

Adoration for nature constitutes one of the primary subjects that literature has tackled since the origin of human history. Nature expressed through a poet's subjective imagination is the internalized and reorganized nature. This study examines the view on nature enacted in Ch'o-Jung's three-verse poems (sijo) in light of the traditional views on nature implicated in the ancient three-verse poems (koshijo), which is in line with the long-established Oriental view on nature. To dignitaris(sadaebu) in the Chosun Dynasty, nature appeared as the idealistic subject for moral culture ($shims{\breve{o}}ngsuyang$), which also becomes the literary space where the purity and justice of the world view of Neo-Confucianism(Sungrihak) is contained in the form of the three-verse poem, the lyrical poetic space where the "I" is united with nature by way of "enjoying of wind and moon"($umpungnongw{\breve{o}}i$) and "living in quiet retiremen"($yuyuchaj{\breve{o}}k$), and the object for the poetical perception of the surrounding world. Ch'o-Jung' s three-verse odes are found in Reed pipe ($Ch'oj{\breve{o}}k$), Sixty Five Pieces of Three-Verse Odes (Samhaengshi-$yukshipopy{\breve{o}}n$), Autumn Fragrance ($Hyangginam{\check{u}}n-ga{\check{u}}l$), and The Words of Zelko va Tree ($N{\check{u}}tinamu{\check{u}}i-mal$). This study analyzes 212 pieces of Ch'o-Jung' s three-verse poems chosen from theses books. In Ch'o-Jung's poems, the traditional view on nature expressed in the ancient three-verse poems is rendered in such a way that metaphysical understanding of nature is indirectly transmitted through the objective correlatives found nature. Nature is no longer the object of straightforward utterance, but transformed, displaced, and removed: that way, nature gets objectified to form a complicated and multi-layered structure. In conclusion, the view on nature manifested in Ch'o-Jung's three-verse poems is based on traditional metaphysics. Second, nature is the object of lyrical nostalgia and adoration. Third, nature is imbued with the fundamental affection for parents. Fourth, nature is associated with organic life. Fifth, the nature in Ch'o-Jung's poems reveals the beauty of stillness endorsed in Lao-tse's and Chung-tze's philosophy. And last, nature is the agent for self-realization and meditation.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.137-152
• /
• 2012

In the generation of Web 2.0, as many users start to make lots of web contents called user created contents by themselves, the World Wide Web is overflowing by countless information. Therefore, it becomes the key to find out meaningful information among lots of resources. Nowadays, the information retrieval is the most important thing throughout the whole field and several types of search services are developed and widely used in various fields to retrieve information that user really wants. Especially, the legal information search is one of the indispensable services in order to provide people with their convenience through searching the law necessary to their present situation as a channel getting knowledge about it. The Office of Legislation in Korea provides the Korean Law Information portal service to search the law information such as legislation, administrative rule, and judicial precedent from 2009, so people can conveniently find information related to the law. However, this service has limitation because the recent technology for search engine basically returns documents depending on whether the query is included in it or not as a search result. Therefore, it is really difficult to retrieve information related the law for general users who are not familiar with legal terms in the search engine using simple matching of keywords in spite of those kinds of efforts of the Office of Legislation in Korea, because there is a huge divergence between everyday words and legal terms which are especially from Chinese words. Generally, people try to access the law information using everyday words, so they have a difficulty to get the result that they exactly want. In this paper, we propose a term mapping methodology between everyday words and legal terms for general users who don't have sufficient background about legal terms, and we develop a search service that can provide the search results of law information from everyday words. This will be able to search the law information accurately without the knowledge of legal terminology. In other words, our research goal is to make a law information search system that general users are able to retrieval the law information with everyday words. First, this paper takes advantage of tags of internet blogs using the concept for collective intelligence to find out the term mapping relationship between everyday words and legal terms. In order to achieve our goal, we collect tags related to an everyday word from web blog posts. Generally, people add a non-hierarchical keyword or term like a synonym, especially called tag, in order to describe, classify, and manage their posts when they make any post in the internet blog. Second, the collected tags are clustered through the cluster analysis method, K-means. Then, we find a mapping relationship between an everyday word and a legal term using our estimation measure to select the fittest one that can match with an everyday word. Selected legal terms are given the definite relationship, and the relations between everyday words and legal terms are described using SKOS that is an ontology to describe the knowledge related to thesauri, classification schemes, taxonomies, and subject-heading. Thus, based on proposed mapping and searching methodologies, our legal information search system finds out a legal term mapped with user query and retrieves law information using a matched legal term, if users try to retrieve law information using an everyday word. Therefore, from our research, users can get exact results even if they do not have the knowledge related to legal terms. As a result of our research, we expect that general users who don't have professional legal background can conveniently and efficiently retrieve the legal information using everyday words.

• Journal of Intelligence and Information Systems
• /
• v.23 no.3
• /
• pp.45-67
• /
• 2017

According to the Internet Usage Research performed in 2016, the number of internet users and the internet usage have been increasing. Smartphone, compared to the computer, is taking a more dominant role as an internet access device. As the number of smart devices have been increasing, some views that the demand on high-speed internet will decrease; however, Despite the increase in smart devices, the high-speed Internet market is expected to slightly increase for a while due to the speedup of Giga Internet and the growth of the IoT market. As the broadband Internet market saturates, telecom operators are over-competing to win new customers, but if they know the cause of customer exit, it is expected to reduce marketing costs by more effective marketing. In this study, we analyzed the relationship between the cancellation rates of telecommunication products and the factors affecting them by combining the data of 3 cities, Anyang, Gunpo, and Uiwang owned by a telecommunication company with the regional data from KOSIS(Korean Statistical Information Service). Especially, we focused on the assumption that the neighboring areas affect the distribution of the cancellation rates by coupling type, so we conducted spatial cluster analysis on the 3 types of cancellation rates of each region using the spatial analysis tool, SatScan, and analyzed the various relationships between the cancellation rates and the regional data. In the analysis phase, we first summarized the characteristics of the clusters derived by combining spatial information and the cancellation data. Next, based on the results of the cluster analysis, Variance analysis, Correlation analysis, and regression analysis were used to analyze the relationship between the cancellation rates data and regional data. Based on the results of analysis, we proposed appropriate marketing methods according to the region. Unlike previous studies on regional characteristics analysis, In this study has academic differentiation in that it performs clustering based on spatial information so that the regions with similar cancellation types on adjacent regions. In addition, there have been few studies considering the regional characteristics in the previous study on the determinants of subscription to high-speed Internet services, In this study, we tried to analyze the relationship between the clusters and the regional characteristics data, assuming that there are different factors depending on the region. In this study, we tried to get more efficient marketing method considering the characteristics of each region in the new subscription and customer management in high-speed internet. As a result of analysis of variance, it was confirmed that there were significant differences in regional characteristics among the clusters, Correlation analysis shows that there is a stronger correlation the clusters than all region. and Regression analysis was used to analyze the relationship between the cancellation rate and the regional characteristics. As a result, we found that there is a difference in the cancellation rate depending on the regional characteristics, and it is possible to target differentiated marketing each region. As the biggest limitation of this study and it was difficult to obtain enough data to carry out the analyze. In particular, it is difficult to find the variables that represent the regional characteristics in the Dong unit. In other words, most of the data was disclosed to the city rather than the Dong unit, so it was limited to analyze it in detail. The data such as income, card usage information and telecommunications company policies or characteristics that could affect its cause are not available at that time. The most urgent part for a more sophisticated analysis is to obtain the Dong unit data for the regional characteristics. Direction of the next studies be target marketing based on the results. It is also meaningful to analyze the effect of marketing by comparing and analyzing the difference of results before and after target marketing. It is also effective to use clusters based on new subscription data as well as cancellation data.

• Journal of Intelligence and Information Systems
• /
• v.26 no.3
• /
• pp.109-125
• /
• 2020

The Ministry of National Defense is pushing for the Defense Acquisition Program to build strong defense capabilities, and it spends more than 10 trillion won annually on defense improvement. As the Defense Acquisition Program is directly related to the security of the nation as well as the lives and property of the people, it must be carried out very transparently and efficiently by experts. However, the excessive diversification of laws and regulations related to the Defense Acquisition Program has made it challenging for many working-level officials to carry out the Defense Acquisition Program smoothly. It is even known that many people realize that there are related regulations that they were unaware of until they push ahead with their work. In addition, the statutory statements related to the Defense Acquisition Program have the tendency to cause serious issues even if only a single expression is wrong within the sentence. Despite this, efforts to establish a sentence comparison system to correct this issue in real time have been minimal. Therefore, this paper tries to propose a "Comparison System between the Statement of Military Reports and Related Laws" implementation plan that uses the Siamese Network-based artificial neural network, a model in the field of natural language processing (NLP), to observe the similarity between sentences that are likely to appear in the Defense Acquisition Program related documents and those from related statutory provisions to determine and classify the risk of illegality and to make users aware of the consequences. Various artificial neural network models (Bi-LSTM, Self-Attention, D_Bi-LSTM) were studied using 3,442 pairs of "Original Sentence"(described in actual statutes) and "Edited Sentence"(edited sentences derived from "Original Sentence"). Among many Defense Acquisition Program related statutes, DEFENSE ACQUISITION PROGRAM ACT, ENFORCEMENT RULE OF THE DEFENSE ACQUISITION PROGRAM ACT, and ENFORCEMENT DECREE OF THE DEFENSE ACQUISITION PROGRAM ACT were selected. Furthermore, "Original Sentence" has the 83 provisions that actually appear in the Act. "Original Sentence" has the main 83 clauses most accessible to working-level officials in their work. "Edited Sentence" is comprised of 30 to 50 similar sentences that are likely to appear modified in the county report for each clause("Original Sentence"). During the creation of the edited sentences, the original sentences were modified using 12 certain rules, and these sentences were produced in proportion to the number of such rules, as it was the case for the original sentences. After conducting 1 : 1 sentence similarity performance evaluation experiments, it was possible to classify each "Edited Sentence" as legal or illegal with considerable accuracy. In addition, the "Edited Sentence" dataset used to train the neural network models contains a variety of actual statutory statements("Original Sentence"), which are characterized by the 12 rules. On the other hand, the models are not able to effectively classify other sentences, which appear in actual military reports, when only the "Original Sentence" and "Edited Sentence" dataset have been fed to them. The dataset is not ample enough for the model to recognize other incoming new sentences. Hence, the performance of the model was reassessed by writing an additional 120 new sentences that have better resemblance to those in the actual military report and still have association with the original sentences. Thereafter, we were able to check that the models' performances surpassed a certain level even when they were trained merely with "Original Sentence" and "Edited Sentence" data. If sufficient model learning is achieved through the improvement and expansion of the full set of learning data with the addition of the actual report appearance sentences, the models will be able to better classify other sentences coming from military reports as legal or illegal. Based on the experimental results, this study confirms the possibility and value of building "Real-Time Automated Comparison System Between Military Documents and Related Laws". The research conducted in this experiment can verify which specific clause, of several that appear in related law clause is most similar to the sentence that appears in the Defense Acquisition Program-related military reports. This helps determine whether the contents in the military report sentences are at the risk of illegality when they are compared with those in the law clauses.

• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.1-25
• /
• 2020

In this paper, we suggest an application system architecture which provides accurate, fast and efficient automatic gasometer reading function. The system captures gasometer image using mobile device camera, transmits the image to a cloud server on top of private LTE network, and analyzes the image to extract character information of device ID and gas usage amount by selective optical character recognition based on deep learning technology. In general, there are many types of character in an image and optical character recognition technology extracts all character information in an image. But some applications need to ignore non-of-interest types of character and only have to focus on some specific types of characters. For an example of the application, automatic gasometer reading system only need to extract device ID and gas usage amount character information from gasometer images to send bill to users. Non-of-interest character strings, such as device type, manufacturer, manufacturing date, specification and etc., are not valuable information to the application. Thus, the application have to analyze point of interest region and specific types of characters to extract valuable information only. We adopted CNN (Convolutional Neural Network) based object detection and CRNN (Convolutional Recurrent Neural Network) technology for selective optical character recognition which only analyze point of interest region for selective character information extraction. We build up 3 neural networks for the application system. The first is a convolutional neural network which detects point of interest region of gas usage amount and device ID information character strings, the second is another convolutional neural network which transforms spatial information of point of interest region to spatial sequential feature vectors, and the third is bi-directional long short term memory network which converts spatial sequential information to character strings using time-series analysis mapping from feature vectors to character strings. In this research, point of interest character strings are device ID and gas usage amount. Device ID consists of 12 arabic character strings and gas usage amount consists of 4 ~ 5 arabic character strings. All system components are implemented in Amazon Web Service Cloud with Intel Zeon E5-2686 v4 CPU and NVidia TESLA V100 GPU. The system architecture adopts master-lave processing structure for efficient and fast parallel processing coping with about 700,000 requests per day. Mobile device captures gasometer image and transmits to master process in AWS cloud. Master process runs on Intel Zeon CPU and pushes reading request from mobile device to an input queue with FIFO (First In First Out) structure. Slave process consists of 3 types of deep neural networks which conduct character recognition process and runs on NVidia GPU module. Slave process is always polling the input queue to get recognition request. If there are some requests from master process in the input queue, slave process converts the image in the input queue to device ID character string, gas usage amount character string and position information of the strings, returns the information to output queue, and switch to idle mode to poll the input queue. Master process gets final information form the output queue and delivers the information to the mobile device. We used total 27,120 gasometer images for training, validation and testing of 3 types of deep neural network. 22,985 images were used for training and validation, 4,135 images were used for testing. We randomly splitted 22,985 images with 8:2 ratio for training and validation respectively for each training epoch. 4,135 test image were categorized into 5 types (Normal, noise, reflex, scale and slant). Normal data is clean image data, noise means image with noise signal, relfex means image with light reflection in gasometer region, scale means images with small object size due to long-distance capturing and slant means images which is not horizontally flat. Final character string recognition accuracies for device ID and gas usage amount of normal data are 0.960 and 0.864 respectively.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.167-194
• /
• 2019

This research starts from the four basic concepts of incentive incompatibility, limited information, myopia and decision variable which are confronted when making decisions in keyword bidding. In order to make these concept concrete, four framework approaches are designed as follows; Strategic approach for the incentive incompatibility, Statistical approach for the limited information, Alternative optimization for myopia, and New model approach for decision variable. The purpose of this research is to propose the statistical optimization model in constructing the portfolio of Sponsored Search Advertising (SSA) in the Sponsor's perspective through empirical tests which can be used in portfolio decision making. Previous research up to date formulates the CTR estimation model using CPC, Rank, Impression, CVR, etc., individually or collectively as the independent variables. However, many of the variables are not controllable in keyword bidding. Only CPC and Rank can be used as decision variables in the bidding system. Classical SSA model is designed on the basic assumption that the CPC is the decision variable and CTR is the response variable. However, this classical model has so many huddles in the estimation of CTR. The main problem is the uncertainty between CPC and Rank. In keyword bid, CPC is continuously fluctuating even at the same Rank. This uncertainty usually raises questions about the credibility of CTR, along with the practical management problems. Sponsors make decisions in keyword bids under the limited information, and the strategic portfolio approach based on statistical models is necessary. In order to solve the problem in Classical SSA model, the New SSA model frame is designed on the basic assumption that Rank is the decision variable. Rank is proposed as the best decision variable in predicting the CTR in many papers. Further, most of the search engine platforms provide the options and algorithms to make it possible to bid with Rank. Sponsors can participate in the keyword bidding with Rank. Therefore, this paper tries to test the validity of this new SSA model and the applicability to construct the optimal portfolio in keyword bidding. Research process is as follows; In order to perform the optimization analysis in constructing the keyword portfolio under the New SSA model, this study proposes the criteria for categorizing the keywords, selects the representing keywords for each category, shows the non-linearity relationship, screens the scenarios for CTR and CPC estimation, selects the best fit model through Goodness-of-Fit (GOF) test, formulates the optimization models, confirms the Spillover effects, and suggests the modified optimization model reflecting Spillover and some strategic recommendations. Tests of Optimization models using these CTR/CPC estimation models are empirically performed with the objective functions of (1) maximizing CTR (CTR optimization model) and of (2) maximizing expected profit reflecting CVR (namely, CVR optimization model). Both of the CTR and CVR optimization test result show that the suggested SSA model confirms the significant improvements and this model is valid in constructing the keyword portfolio using the CTR/CPC estimation models suggested in this study. However, one critical problem is found in the CVR optimization model. Important keywords are excluded from the keyword portfolio due to the myopia of the immediate low profit at present. In order to solve this problem, Markov Chain analysis is carried out and the concept of Core Transit Keyword (CTK) and Expected Opportunity Profit (EOP) are introduced. The Revised CVR Optimization model is proposed and is tested and shows validity in constructing the portfolio. Strategic guidelines and insights are as follows; Brand keywords are usually dominant in almost every aspects of CTR, CVR, the expected profit, etc. Now, it is found that the Generic keywords are the CTK and have the spillover potentials which might increase consumers awareness and lead them to Brand keyword. That's why the Generic keyword should be focused in the keyword bidding. The contribution of the thesis is to propose the novel SSA model based on Rank as decision variable, to propose to manage the keyword portfolio by categories according to the characteristics of keywords, to propose the statistical modelling and managing based on the Rank in constructing the keyword portfolio, and to perform empirical tests and propose a new strategic guidelines to focus on the CTK and to propose the modified CVR optimization objective function reflecting the spillover effect in stead of the previous expected profit models.

• Journal of Intelligence and Information Systems
• /
• v.24 no.4
• /
• pp.111-136
• /
• 2018

In this paper, we propose a methodology to extract answer information about queries from various types of unstructured documents collected from multi-sources existing on web in order to expand knowledge base. The proposed methodology is divided into the following steps. 1) Collect relevant documents from Wikipedia, Naver encyclopedia, and Naver news sources for "subject-predicate" separated queries and classify the proper documents. 2) Determine whether the sentence is suitable for extracting information and derive the confidence. 3) Based on the predicate feature, extract the information in the proper sentence and derive the overall confidence of the information extraction result. In order to evaluate the performance of the information extraction system, we selected 400 queries from the artificial intelligence speaker of SK-Telecom. Compared with the baseline model, it is confirmed that it shows higher performance index than the existing model. The contribution of this study is that we develop a sequence tagging model based on bi-directional LSTM-CRF using the predicate feature of the query, with this we developed a robust model that can maintain high recall performance even in various types of unstructured documents collected from multiple sources. The problem of information extraction for knowledge base extension should take into account heterogeneous characteristics of source-specific document types. The proposed methodology proved to extract information effectively from various types of unstructured documents compared to the baseline model. There is a limitation in previous research that the performance is poor when extracting information about the document type that is different from the training data. In addition, this study can prevent unnecessary information extraction attempts from the documents that do not include the answer information through the process for predicting the suitability of information extraction of documents and sentences before the information extraction step. It is meaningful that we provided a method that precision performance can be maintained even in actual web environment. The information extraction problem for the knowledge base expansion has the characteristic that it can not guarantee whether the document includes the correct answer because it is aimed at the unstructured document existing in the real web. When the question answering is performed on a real web, previous machine reading comprehension studies has a limitation that it shows a low level of precision because it frequently attempts to extract an answer even in a document in which there is no correct answer. The policy that predicts the suitability of document and sentence information extraction is meaningful in that it contributes to maintaining the performance of information extraction even in real web environment. The limitations of this study and future research directions are as follows. First, it is a problem related to data preprocessing. In this study, the unit of knowledge extraction is classified through the morphological analysis based on the open source Konlpy python package, and the information extraction result can be improperly performed because morphological analysis is not performed properly. To enhance the performance of information extraction results, it is necessary to develop an advanced morpheme analyzer. Second, it is a problem of entity ambiguity. The information extraction system of this study can not distinguish the same name that has different intention. If several people with the same name appear in the news, the system may not extract information about the intended query. In future research, it is necessary to take measures to identify the person with the same name. Third, it is a problem of evaluation query data. In this study, we selected 400 of user queries collected from SK Telecom 's interactive artificial intelligent speaker to evaluate the performance of the information extraction system. n this study, we developed evaluation data set using 800 documents (400 questions * 7 articles per question (1 Wikipedia, 3 Naver encyclopedia, 3 Naver news) by judging whether a correct answer is included or not. To ensure the external validity of the study, it is desirable to use more queries to determine the performance of the system. This is a costly activity that must be done manually. Future research needs to evaluate the system for more queries. It is also necessary to develop a Korean benchmark data set of information extraction system for queries from multi-source web documents to build an environment that can evaluate the results more objectively.