Document retrieval system and method for retrieving document

Patent metadata

Field	Value
Publication number	US-12086181-B2
Application number	US-202017791316-A
Country	US
Kind code	B2
Filing date	Dec 28, 2020
Priority date	Jan 10, 2020
Publication date	Sep 10, 2024
Grant date	Sep 10, 2024

Abstract

A document retrieval system retrieving a document with the concept of the document taken into account is provided. The system includes a processing portion and the processing portion creates a retrieval graph from a retrieval composition. The retrieval graph includes first to m-th retrieval local graphs (m is an integer of greater than or equal to 1), and the retrieval local graphs are each constituted by two nodes and one edge. The processing portion performs retrieval of first to m-th sentences on a reference document. The i-th sentence (i is an integer of greater than or equal to 1 and less than or equal to m) includes one of the two nodes in the i-th retrieval local graph or a related term or a hyponym of the one of the two nodes; the other of the two nodes in the i-th retrieval local graph or a related term or a hyponym of the other of the two nodes; and the edge in the i-th retrieval local graph or a related term or a hyponym of the edge. A mark is assigned to the score of the reference document in accordance with the number of sentences included in the reference document among the first to m-th sentences.

First claim

The invention claimed is:

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.

2. The document retrieval system according to claim 1 ,
wherein the processing portion is configured to assign, when the reference document comprises a second sentence of the plurality of sentences including the first word, the second word, and the third word and a third sentence of the plurality of sentences including the first word, the second word, and the third word, a second mark to the score of the reference document in accordance with a distance between the second sentence of the plurality of sentences and the third sentence of the plurality of sentences; and
wherein the processing portion is configured to calculate the score of the reference document in accordance with the first mark and the second mark assigned to the score of the reference document.

3. The document retrieval system according to claim 1 , wherein the output portion is configured to output the score as visual information to a memory portion.

4. 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 a related term of one of the two nodes in 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 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.

5. The document retrieval system according to claim 4 , wherein the output portion is configured to output the score as visual information to a memory portion.

6. 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 first reference document of a plurality of reference documents and a plurality of sentences from a second reference document of the plurality of reference documents,
wherein a first sentence of the plurality of sentences of the first reference document of the plurality of reference documents comprises a first word, a second word, and a third word,
wherein a first sentence of the plurality of sentences of the second reference document of the plurality of reference documents comprises the first word, the second word, and the 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 first reference documen

Assignees

• Semiconductor Energy Lab

Inventors

• Momo Junpei
• Higashi Kazuki
• Nakashima Motoki

Classifications

• G06F40/211

  Syntactic parsing, e.g. based on context-free grammar [CFG] or unification grammars · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F16/3344 Primary

  using natural language analysis · CPC title

• G06F16/93

  Document management systems · CPC title

• G06F16/9024 Primary

  Graphs; Linked lists (G06F16/9027 takes precedence) · CPC title