Supercharge Your Innovation With Domain-Expert AI Agents!

Identification method, generation method, dimensionality reduction method, display method, and information processing device

A technology to determine the method and dimension, applied in the direction of electronic digital data processing, digital data information retrieval, special data processing applications, etc., can solve problems such as difficult to retrieve words, words, and sentences that cannot be retrieved

Pending Publication Date: 2021-11-30
FUJITSU LTD
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] However, in the prior art described above, there are cases where retrieval cannot be performed due to expression fluctuations in the granularity of words and sentences in texts such as professional books and search query texts.
[0009] For example, since the above-mentioned inverted index establishes a correspondence relationship between words and their offsets, it is difficult to retrieve words that are inconsistent with the words in the search query even if they have the same meaning

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Identification method, generation method, dimensionality reduction method, display method, and information processing device
  • Identification method, generation method, dimensionality reduction method, display method, and information processing device
  • Identification method, generation method, dimensionality reduction method, display method, and information processing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0033] figure 1 with figure 2 It is a diagram for explaining the processing of the information processing device of this embodiment. first of all, yes figure 1 Be explained. Such as figure 1 As shown, the dimension compression unit 150b of the information processing device acquires the word vector table 140a. The word-vector table 140a is a table holding information on the vector of each word. The vector of each word included in the word vector table 140 a is a vector calculated in advance using Word2Vec or the like, and is, for example, a 200-dimensional vector.

[0034] The dimension compression unit 150b generates the dimensionally compressed word vector table 140b by performing dimensionally compressed on the vector of each word in the word vector table 140a. The dimensionally compressed word vector table 140b is a table that holds information on the vectors of each word after dimensionally compressed. The vectors of each word included in the dimensionally compress...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

This information processing device identifies a vector corresponding to any word included in a text included in a search condition. The information processing device refers to a storage unit that stores presence information indicating whether words corresponding to each of a plurality of vectors are included in each of a plurality of text files, and identifies a text file, among the plurality of text files, that includes any of the words on the basis of the presence information which is mapped to a vector, among the plurality of vectors, that has a degree of similarity to an identified vector equal to or greater than a standard.

Description

technical field [0001] The present invention relates to determination methods and the like. Background technique [0002] In the conventional retrieval technology, etc., when compressing and encoding the text of professional books, etc., the text is lexically analyzed to generate an inverted index that associates words with offsets of words in the text, and uses for text retrieval. For example, when a search query (text to be searched) is specified, the inverted index is used to specify an offset corresponding to the word of the search query, and a text including the word of the search query is searched. [0003] Patent Document 1: Japanese Patent Application Laid-Open No. 2006-119714 [0004] Patent Document 2: Japanese Patent Laid-Open No. 2018-180789 [0005] Patent Document 3: Japanese Patent Laid-Open No. 2006-146355 [0006] Patent Document 4: Japanese Patent Laid-Open No. 2002-230021 [0007] Non-Patent Document 1: Masajiro Iwasaki, "Disclosure of NGT for High-Sp...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/383
CPCG06F16/3347G06F16/334
Inventor 片冈正弘尾上聪加藤翔
Owner FUJITSU LTD
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2025 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com