Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

Intelligent search completion method for block decomposition based on relation interaction

A technology of intelligent search and relation, applied in the field of intelligent search and completion of block decomposition method, can solve problems such as cost and accuracy constraints, and achieve the effect of no technical requirements and simple system interface

Pending Publication Date: 2022-04-12
TIANJIN UNIV
View PDF0 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, it is severely constrained by cost and accuracy

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
  • Intelligent search completion method for block decomposition based on relation interaction
  • Intelligent search completion method for block decomposition based on relation interaction
  • Intelligent search completion method for block decomposition based on relation interaction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0018] An intelligent search and completion method based on block decomposition based on relational interaction of the present invention will be described in detail below with reference to the embodiments and drawings. Apparently, the described embodiments are only some of the embodiments of the present invention, but not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0019] Such as figure 1 , figure 2 As shown, a kind of intelligent search and completion method of block decomposition based on relational interaction of the present invention comprises the following steps:

[0020] 1) Divide the data set to be completed into training set T and test set S according to the ratio of 8:2;

[0021] 2) Structuring the data set, specifically, using the language technology platform (LTP) to sequentially perform ...

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

The invention discloses an intelligent search completion method for block decomposition based on relation interaction. The method comprises the following steps: dividing a data set needing to be completed into a training set and a test set according to a proportion of 8: 2; sequentially performing structured processing of entity extraction, relationship extraction, entity unification and anaphora resolution on the data set; encoding the data subjected to the structured processing; establishing a relation interaction block decomposition model which comprises a score function and a loss function; model hyper-parameters are set for relation interaction block decomposition; training the relation interaction block decomposition model by using the training set until the loss function of the model is converged; complementing the test set by using the trained relation interaction block decomposition model; and verifying the trained relation interaction block decomposition model through test evaluation. The method can reasonably complement or predict facts with higher efficiency and interpretability.

Description

technical field [0001] The invention relates to an intelligent search and completion method. In particular, it involves an intelligent search-completion method based on a relational interaction-based block decomposition method. Background technique [0002] For intelligent search systems, we can understand it as the task of predicting unknown facts based on existing facts to improve the knowledge map. Therefore, knowledge graphs, as a structured representation of real-world triples, can help in many fields such as search, recommender systems, natural language processing, and question answering. [0003] Generally, the triplet form is: head entity, relation, tail entity. Currently, the existing knowledge base already contains very complex information, such as: Tmall, Baidu Data, YAGO, DBpedia, WordNet, FreeBase, etc. However, there is still a serious lack of information in most databases, and it is urgent to improve the information. For example, in the FreeBase database, ...

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): G06F16/215G06F16/28G06F16/9538
Inventor 喻梅郭九江许林英
Owner TIANJIN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Eureka Blog
Learn More
PatSnap group products