• Annual Conference on Human and Language Technology
• /
• 2022.10a
• /
• pp.461-464
• /
• 2022

법원도서관이 발간하는 판례공보를 기반으로 판결문 자동요약을 위한 학습 데이터들이 구축되고 있다. 그런데 판결문 요약에서는 뉴스 요약과는 달리 추출요약과 생성요약 방식이 함께 사용되는 특수성이 있고, 이러한 특수성 때문에 현재 판결문 요약 데이터셋이 요약 프로그램의 성능 향상을 이끌지 못하고 있다고 생각된다. 따라서 법률가들이 판결문을 요약하는 방식을 반영하여, 추출요약 방식으로 작성된 판결요지와 생성요약 방식으로 작성된 판결요지를 분리해서 요약 데이터셋을 만들 필요가 있다. 추출요약과 생성요약에 관한 데이터셋을 따로 구축하기 위해서는 판례공보의 판결요지를 추출요약과 생성요약으로 분류하는 작업이 필요한데, 감성 분석에 사용되는 알고리즘이 판결요지의 분류 작업에 응용될 수 있다는 것을 실험 결과로 알 수 있었다.

• Journal of Internet Computing and Services
• /
• v.25 no.1
• /
• pp.91-98
• /
• 2024

With the advancement of ICT (Information and Communication Technology), searching for judgments through the internet has become increasingly convenient. However, predicting sentencing based on judgments remains a challenging task for individuals. This is because sentencing involves a complex process of applying aggravating and mitigating factors within the framework of legal provisions, and it often depends on the subjective judgment of the judge. Therefore, this research aimed to develop a model for predicting sentencing using artificial intelligence by focusing on structuring the data from judgments, making it suitable for AI applications. Through theoretical and statistical analysis of previous studies, we identified variables with high explanatory power for predicting sentencing. Additionally, by analyzing 50 legal judgments related to serious crimes that are publicly available, we presented a framework for extracting essential information from judgments. This framework encompasses basic case information, sentencing details, reasons for sentencing, the reasons for the determination of the sentence, as well as information about offenders, victims, and accomplices evident within the specific content of the judgments. This research is expected to contribute to the development of artificial intelligence technologies in the field of law in the future.

• Journal of Korean Institute of Fire Investigation
• /
• v.11 no.1
• /
• pp.145-153
• /
• 2007

화재발생시 경찰, 소방 등 행정관서는 현장통제 초동조치, 응급구조 진화작업, 화재조사 및 수사, 화재증명 발급 및 통계작성, 피의자(원인 제공자) 입건 및 송치를 담당하고 있고, 검찰청은 수사보완 및 기소, 법원은 형사 및 민사재판을 진행하게 됨으로써 책임과 보상관계를 판가름하게 된다. 물론 이재관계자의 합의, 화재보험 등으로 피해보상을 받기도 하나 모든 것이 국민으로부터 나온 것이고, 국민을 볼모로 하여서는 않되므로 화재원인의 명쾌한 규명으로 유사사고의 재발방지를 위한 연구가 필요하다.

• Korean Journal of Social Welfare
• /
• v.68 no.2
• /
• pp.131-160
• /
• 2016

In this study, we analyzed determination of punishment of victimizers presented in sentencing(81 plaintiffs, 95 sentencing) for 55 cases involving child maltreatment fatalities between 2001 and 2015. The results showed that about 40% of main victimizers were imposed relatively minor punishment such as probation or imprisonment for less than 3 years. Judgments that deviated from lower limit comprised large proportion in connection with compliance with standards for statutory punishment and punishment determination. The elements of punishment determination, such as earnest rearing of child, psychological pain arising from death of child, sense of guilt, motivation that can be considered, were found to have a significant influence on mitigation of punishment although such elements could be judged differently, depending on perception or subjective tendency of judges towards child abuse. Even abetters in a position to prevent death of child were imposed minor punishment mostly by probation or monetary penalty. This study presented the need to reconsider the circumstances of punishment determination which has been conventionally mentioned in cases involving child maltreatment fatalities, such as first offender, accidental crime, person with parental rights, fosters, agreement with family of the deceased, etc. Moreover, this study suggested the need to reinforce child abuse prevention training for law enforcement officers and to revamp standards for determining punishment unique to the cases of child abuse in the future.

• Korean Journal of Forensic Psychology
• /
• v.12 no.1
• /
• pp.1-13
• /
• 2021

This study analyzed the use of expert reports in the investigations and trials of cases of sexual violence against people with intellectual disabilities. A total of 670 alleged sexual assault cases against victims with intellectual disabilities were analyzed. Results showed that 97.5% of the cases included at least one expert report. In most cases(91%), the expert reports of statement validity assessment were included. Additionally, doctor's note (41.1%) from obstetricians and Psychiatrists, intermediary reports(36%), and expert witnesses(psychologists') reports (9.5%) were included. In 80 cases (44.4%) of the 180 cases in which a victim' statement credibility was in question during the trial, judges cited the expert's reports of statement validity assessment as the basis for the judgment on the reliability of the victims' accusation. The frequency of citing the report was higher when the victim was under the age of 13, or when the defendant was found guilty. Regrading the report content, the evaluations of criteria-based content analysis(CBCA) was most frequently cited, while the victim's psychological status, cognitive limitation, as well as possibile contamination of victim's account, were also mentioned in the ruling statements. Results showed agreement between experts' statement validity assessments and judges' determinations in 79 cases out of the 80 cases Finally, this study discussed ways to utilize expert options.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.490-492
• /
• 2022

최근 사법분야에 지능형 법률 서비스를 제공하게 되면서 학습데이터로서 판결문의 중요성이 높아지고 있다. 그중 범죄사실은 수사자료와 유사하여 범죄수사에 귀중한 자료역할을 하고 있지만, 주체가 생략되거나 긴 문장의 형태로 인해 구성요건을 추출하고 사건의 인과관계 파악이 어려울 수 있어 이를 분석하는데 적지 않은 시간과 인력이 소비될 수밖에 없다. 따라서, 본 논문에서는 사전학습모델을 활용한 개체명 인식과 형태소 분석기반 이벤트 추출기법을 범죄사건 재구성에 적용하여 핵심 사건추출을 간편화하고 시각적으로 표현해 전체적인 사건 흐름 이해도를 향상할 수 있는 방법론을 제안하고자 한다.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.99-105
• /
• 2023

In the 4th industrial revolution, the field of criminal justice is paying attention to Legaltech using artificial intelligence to provide efficient legal services. This paper attempted to create a crime prediction model that can apply Recurrent Neural Network(RNN) to increase the potential for using legal technology in the domestic criminal justice field. To this end, the crime process was divided into pre, during, and post stages based on the criminal facts described in the judgment, utilizing crime script analysis techniques. In addition, at each time point, the method and evidence of crime were classified into objects, actions, and environments based on the sentence composition elements and the 8 principles of investigation. The case summary analysis framework derived from this study can contribute to establishing situational crime prevention strategies because it is easy to identify typical patterns of specific crime methods. Furthermore, the results of this study can be used as a useful reference for research on generating crime situation prediction data based on RNN models in future follow-up studies.

• Proceedings of the Korea Contents Association Conference
• /
• 2017.05a
• /
• pp.233-234
• /
• 2017

서울남부지방법원 2012나4904 손해배상 판결판결은 일반적인 어문저작물 표절과 달리 포괄적 비문언적 유사성을 인정받은 사건이다. 실질적 유사성에서 포괄적 비문언적 유사성의 분석을 (1) 등장인물, (2) 줄거리와 플롯, (3) 에피소드 별로 분석하여 표절임을 인정하고 있다. 창작물을 구성하는 사건과 그 배열 형태를 가리키는 플롯은 소설의 창작 요소 중 매우 중요한 부분임에도 표절의 판정에서 거의 고려되지 않아왔다. 본 사건은 특히 이종 장르 간의 플롯을 표절한 경우 법원이 어떻게 판결을 내렸는가에 대한 중요한 자료로 검토할 가치를 지니고 있다.

• Electronics and Telecommunications Trends
• /
• v.33 no.2
• /
• pp.64-76
• /
• 2018

This paper addresses the antitrust case of Google's general search service to find evidence and logic used for defining markets, and the proof of dominant power and its abuse in detail. This antitrust case has certain meaning because it is not easy to apply traditional approaches to a general search service, which has two-sided market characteristics. This paper finds some implications through an analysis of the antitrust case shown below. First, for market definition, the overall qualitative analysis can be used to draw conclusions without a quantitative analysis, such as a Small but Significant and Non-transitory Increasing in Price (SSNIP) analysis. Second, the multi-homing behavior seems to be one of the key factors in judging the dominant power in Internet-based services. Lastly, the fact that the value of traffic can differ based on the traffic source needs to be considered to address the competition issue of Internet-based services.

• Korean Journal of Social Welfare
• /
• v.67 no.2
• /
• pp.113-136
• /
• 2015

This study is about criminal judgement of child abuse. The purpose of this study is to analyze contents and reasons for judgements about child abuse crime in detail especially focused on elements and contents of weighing of an offense and concurrent imposition and then to suggest alternatives for policies and law-enforcement for the prevention of that crime. The data were collected from 484 written judgements on 579 criminal defendants that were related to 'Violation of the Child Welfare Act' and were conducted by content analysis. The results are as follows. First, Only about 25% criminal defendants were guilty of violations of the Child Welfare Act were sentenced to imprisonment and the rest of them(about 75%) were merely sentenced to probation of imprisonment or fined. Second, Proportion of prison sentence or period of jail time have not been increased in spite of public indignation and upward of statutory punishment by legislation. Third, in the case of child sexual abuse, there are frequent cases in which concurrent imposition was not put, regardless of explicit statement in the related laws. Last, this study revealed that some mitigation factors of sentence that have been identical to crimes against adult have been applied to child abuse crime uncritically, for example agreement and regret and so on. On the basis of such results, this study proposed policy alternatives for prevention of the recurrence of child abuse, i.e. intrinsic standard of weighing of an offense, concurrent imposition to perpetrators of child abuse and so on.