US 12,086,181 B2
Document retrieval system and method for retrieving document
Junpei Momo, Kanagawa (JP); Kazuki Higashi, Kanagawa (JP); and Motoki Nakashima, Kanagawa (JP)
Assigned to Semiconductor Energy Laboratory Co., Ltd., (JP)
Appl. No. 17/791,316
Filed by Semiconductor Energy Laboratory Co., Ltd., Kanagawa-ken (JP)
PCT Filed Dec. 28, 2020, PCT No. PCT/IB2020/062467
§ 371(c)(1), (2) Date Jul. 7, 2022,
PCT Pub. No. WO2021/140406, PCT Pub. Date Jul. 15, 2021.
Claims priority of application No. 2020-003074 (JP), filed on Jan. 10, 2020.
Prior Publication US 2023/0350949 A1, Nov. 2, 2023
Int. Cl. G06F 16/00 (2019.01); G06F 16/33 (2019.01); G06F 16/901 (2019.01); G06F 16/93 (2019.01); G06F 40/211 (2020.01); G06F 40/284 (2020.01)
CPC G06F 16/9024 (2019.01) [G06F 16/3344 (2019.01); G06F 16/93 (2019.01); G06F 40/211 (2020.01); G06F 40/284 (2020.01)] 7 Claims
OG exemplary drawing
 
1. A document retrieval system comprising:
a processing portion;
an input portion; and
an output portion,
wherein the input portion is configured to supply a retrieval composition to the processing portion,
wherein the processing portion is configured to create a retrieval graph from the retrieval composition,
wherein the retrieval graph comprises first to m-th retrieval local graphs,
wherein each of the first to m-th retrieval local graphs is constituted by two nodes and an edge between the two nodes,
wherein the processing portion is configured to retrieve a plurality of sentences from a reference document,
wherein a first sentence of the plurality of sentences comprises a first word, a second word, and a third word,
wherein the first word is one of the two nodes in one retrieval local graph of the first to m-th retrieval local graphs, a related term of the one of the two nodes in the one retrieval local graph of the first to m-th retrieval local graphs, or a hyponym of the one of the two nodes in the one retrieval local graph of the first to m-th retrieval local graphs,
wherein the second word is the other of the two nodes in the one retrieval local graph of the first to m-th retrieval local graphs, a related term of the other of the two nodes in the one retrieval local graph of the first to m-th retrieval local graphs, or a hyponym of the other of the two nodes in the one retrieval local graph of the first to m-th retrieval local graphs,
wherein the third word is the edge in the one retrieval local graph of the first to m-th retrieval local graphs, a related term of the edge in the one retrieval local graph of the first to m-th retrieval local graphs, or a hyponym of the edge in the one retrieval local graph of the first to m-th retrieval local graphs,
wherein the processing portion is configured to assign a first mark to a score of the reference document in accordance with a similarity between the retrieval graph and the number of sentences included in the reference document among the plurality of sentences which include the two nodes and the edge of each of the first to m-th retrieval local graphs,
wherein m is an integer of greater than or equal to 2, and
wherein the output portion is configured to supply the score of the reference document.