US 12,216,699 B2
Information processing device, and generation method
Takeyuki Aikawa, Tokyo (JP); Daishin Ito, Tokyo (JP); Hayato Uchide, Tokyo (JP); and Yusuke Koji, Tokyo (JP)
Assigned to MITSUBISHI ELECTRIC CORPORATION, Tokyo (JP)
Filed by Mitsubishi Electric Corporation, Tokyo (JP)
Filed on Aug. 16, 2023, as Appl. No. 18/234,551.
Application 18/234,551 is a continuation of application No. PCT/JP2021/015714, filed on Apr. 16, 2021.
Prior Publication US 2023/0394077 A1, Dec. 7, 2023
Int. Cl. G06F 16/38 (2019.01); G06F 16/383 (2019.01); G06F 40/279 (2020.01)
CPC G06F 16/383 (2019.01) [G06F 40/279 (2020.01)] 9 Claims
OG exemplary drawing
 
1. An information processing device comprising:
a memory;
acquiring circuitry to acquire a plurality of documents and clue information including a plurality of words, the clue information being information acquired from a user of the information processing device or information stored in the memory; and
generation processing circuitry to
generate inter-document relationship source information indicating relationship between a plurality of documents including at least one of the plurality of words included in the clue information and an appearance position of each of the plurality of words included in the clue information in the document based on the plurality of documents and the clue information;
judge based on the inter-document relationship source information whether or not a number of documents corresponding to each of the plurality of words included in the clue information is larger than or equal to a predetermined threshold value;
generate high frequency appearance information indicating relationship between a plurality of documents including a plurality of words each corresponding to the number of documents larger than or equal to the threshold value and the appearance position of each of the plurality of words each corresponding to the number of documents larger than or equal to the threshold value in the document;
generate vicinity appearance information indicating documents in which the plurality of words each corresponding to the number of documents larger than or equal to the threshold value appear in a predetermined range based on the high frequency appearance information,
generate new inter-document relationship source information based on the vicinity appearance information and the inter-document relationship source information,
calculate an inter-document relationship score indicating a relationship level between documents based on the new inter-document relationship source information;
generate inter-document relationship information indicating relationship between documents based on the new inter-document relationship source information and the inter-document relationship score, and
output a list of documents based on the inter-document relationship information.