US 12,169,689 B2
Crime type inference system and method based on text data
Myung Sun Baek, Daejeon (KR); Seung Hee Kim, Daejeon (KR); Young Soo Park, Daejeon (KR); Won Joo Park, Daejeon (KR); Sang Yun Lee, Daejeon (KR); and Yong Tae Lee, Daejeon (KR)
Assigned to Electronics and Telecommunications Research Institute, Daejeon (KR)
Filed by ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE, Daejeon (KR)
Filed on May 24, 2022, as Appl. No. 17/752,611.
Claims priority of application No. 10-2021-0068365 (KR), filed on May 27, 2021; and application No. 10-2022-0049513 (KR), filed on Apr. 21, 2022.
Prior Publication US 2022/0382974 A1, Dec. 1, 2022
Int. Cl. G06F 40/242 (2020.01); G06F 16/35 (2019.01); G06F 40/268 (2020.01); G06F 40/279 (2020.01); G06Q 50/26 (2012.01)
CPC G06F 40/242 (2020.01) [G06F 16/35 (2019.01); G06F 40/268 (2020.01); G06F 40/279 (2020.01); G06Q 50/265 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A crime type inference system based on text data, comprising:
a keywords dictionary construction unit configured to receive crime source data, and generate a crime type keywords dictionary by extracting crime keywords;
a data set construction unit configured to generate a dataset for crime type learning by using the crime source data and the keywords dictionary;
a crime type prediction model training unit configured to generate a crime type prediction model by using the dataset, and train the crime type prediction model; and
a crime type inference unit configured to infer a crime type by using new crime data;
wherein the crime type inference unit analyzes the new crime data which is a report reception text, and provides an inference result including a probability value for the crime type.