US 12,327,083 B2
Related expression extraction device and related expression extraction method
Akira Ioku, Tokyo (JP); and Hideki Hayashi, Tokyo (JP)
Assigned to HITACHI, LTD., Tokyo (JP)
Appl. No. 18/025,950
Filed by Hitachi, Ltd., Tokyo (JP)
PCT Filed Mar. 17, 2021, PCT No. PCT/JP2021/010897
§ 371(c)(1), (2) Date Mar. 13, 2023,
PCT Pub. No. WO2022/064741, PCT Pub. Date Mar. 31, 2022.
Claims priority of application No. 2020-162131 (JP), filed on Sep. 28, 2020.
Prior Publication US 2023/0359816 A1, Nov. 9, 2023
Int. Cl. G06F 40/216 (2020.01); G06F 16/355 (2025.01); G06F 40/35 (2020.01)
CPC G06F 40/216 (2020.01) [G06F 16/355 (2019.01); G06F 40/35 (2020.01)] 10 Claims
OG exemplary drawing
 
1. A related expression extraction device for extracting, with respect to input text data, a related expression related to content of the text data, the related expression extraction device comprising:
a processor; and
a memory,
wherein the memory stores related expression group data including at least an answer to the content of the text data and a plurality of comparative assessment models that perform comparative assessment between the text data and the related expression group data,
wherein the processor receives an input of the text data, performs at least one of categorization of the received text data and determination of a structural pattern of the text data, determines, based on a result of at least one of the categorization of the text data and the determination of the structural pattern of the text data, which of the plurality of comparative assessment models is used to extract the related expression group data, and extracts the related expression related to the content of the text data from the related expression group data using the determined comparative assessment model, and
wherein the memory stores the first comparative assessment model based on a frequency of a word included in the text data and the second comparative assessment model that is strong in expression fluctuation of a word included in the text data.