Unlock instant, AI-driven research and patent intelligence for your innovation.

A hybrid search method that integrates structured and unstructured data

An unstructured data, unstructured technology, applied in structured data retrieval, database indexing, digital data information retrieval, etc., can solve the problems of slow query speed and low query result accuracy, and achieve the effect of improving efficiency

Active Publication Date: 2022-08-02
HANGZHOU DIANZI UNIV
View PDF7 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This hybrid search method has the problems of slow query speed and low accuracy of query results

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
  • A hybrid search method that integrates structured and unstructured data
  • A hybrid search method that integrates structured and unstructured data
  • A hybrid search method that integrates structured and unstructured data

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] In order to make the technical solutions and advantages of the present invention clearer, the present invention will be further described below with reference to the accompanying drawings.

[0028] figure 1 It is a schematic flow diagram of the present invention, which mainly includes the following steps:

[0029] (1) Vectorize the structured and unstructured data contained in each entity in the dataset to obtain entity vectors containing structured vectors and unstructured vectors;

[0030] The process is specifically to convert each entity e in the data set S i The contained structured and unstructured data are vectorized separately to obtain the unstructured vector α containing i and the entity vector (α of the structured vector βi i , β i ). Among them, the dataset S is represented as:

[0031] S={e i |i=1,2,...,N}

[0032] where e i is the ith entity in the dataset, and N is the number of entities in the dataset.

[0033] unstructured vector alpha i Expr...

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 a hybrid search method integrating structured and unstructured data. The method firstly vectorizes the structured and unstructured data contained in each entity in the dataset to obtain entity vectors containing structured vectors and unstructured vectors; Fusion of structured and unstructured data neighbor graphs; then the structured and unstructured data contained in the query entity is vectorized to obtain a mixed query vector containing structured and unstructured vectors; finally, the mixed query vector is in the fusion structure. The nearest neighbor of the query entity is obtained by performing a hybrid search on the nearest neighbor graph of the unstructured and unstructured data through a greedy algorithm. The invention realizes the mixed search of searching unstructured and structured data at the same time, and the efficiency is greatly improved compared with the current two separate index systems.

Description

technical field [0001] The invention relates to the field of approximate nearest neighbor search, in particular to a hybrid search method integrating structured and unstructured data. Background technique [0002] Various Internet and intelligent applications have generated massive amounts of unstructured data (pictures, videos, voice, etc.) and structured data (numbers, symbols, labels, etc.) A core technology of intelligent applications. Structured data query based on relational database is mature and widely used, and unstructured data search is rapidly being applied to various scenarios with the development of deep learning vectorization technology. With the increasing requirement for the consistency of query results, many scenarios need to perform searches on structured and unstructured data at the same time, that is, hybrid searches. [0003] Hybrid search method is currently a research hotspot in the field of approximate nearest neighbor search, and has been practica...

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 Patents(China)
IPC IPC(8): G06F16/2455G06F16/22G06F16/28
CPCG06F16/2455G06F16/2228G06F16/288
Inventor 徐小良王梦召吕凌威
Owner HANGZHOU DIANZI UNIV