Structured entity recording method, device, server and storage medium

A structured entity and entity technology, applied in the field of data processing, can solve the problems of low accuracy, long time consumption, and large amount of calculation, and achieve the effect of improving efficiency and accuracy, reducing calculation amount, and simple and efficient collection

Active Publication Date: 2020-11-24
BEIJING BAIDU NETCOM SCI & TECH CO LTD
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide a structured entity recording method, device, server and storage medium to solve the problems of large amount of calculation, time-consuming and low accuracy when recording entities in existing knowledge graphs

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
  • Structured entity recording method, device, server and storage medium
  • Structured entity recording method, device, server and storage medium
  • Structured entity recording method, device, server and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] figure 1 The flow chart of the structured entity recording method provided by Embodiment 1 of the present invention, this embodiment is applicable to the situation of expanding the knowledge map, the method can be executed by the structured entity recording device, and the device can use software and / or or hardware, and the device can be integrated in the server. like figure 1 As shown, the method specifically includes:

[0029] S110. Select candidate entities related to the structured entities to be included from the knowledge graph.

[0030] Existing knowledge graphs collect structured entities, and for each structured entity to be included, entity resolution needs to be performed on all entities in the knowledge graph. Since it involves entity analysis of all entities, the process is computationally intensive and time-consuming. Based on this, when the knowledge map in this embodiment collects structured entities, it no longer performs entity analysis on all entit...

Embodiment 2

[0045] This embodiment provides a preferred implementation manner of S120 on the basis of the foregoing embodiments, figure 2 It is a flow chart of the structured entity recording method provided by Embodiment 2 of the present invention. like figure 2 As shown, the method includes:

[0046] S210. Select candidate entities related to the structured entities to be included from the knowledge graph.

[0047] S220. Calculate the entity similarity probability between the structured entity to be included and each candidate entity according to the prior attribute information and the preset model of the category to which the candidate entity belongs.

[0048] Each structured entity to be included and each candidate entity has attribute information. In this embodiment, the attribute information of each entity can be used to calculate the entity similarity probability between the structured entity to be included and each candidate entity according to the prior attribute information...

Embodiment 3

[0055] This embodiment provides a preferred implementation manner of S220 on the basis of the foregoing embodiments, image 3 It is a flow chart of the structured entity recording method provided by Embodiment 3 of the present invention. like image 3 As shown, the method includes:

[0056] S310. Select candidate entities related to the structured entities to be included from the knowledge graph.

[0057] S320. For each candidate entity, calculate the probability of each attribute similarity between the structured entity to be included and the candidate entity by using a preset attribute comparison method and attribute importance.

[0058] In this embodiment, there may be one or more candidate entities corresponding to the structured entity to be included, and the structured entity to be included and each candidate entity include one or more attributes. For each candidate entity, a preset attribute comparison method and attribute importance can be used to calculate the prob...

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 embodiment of the present invention discloses a structured entity recording method, device, server and storage medium, wherein the structured entity recording method includes: selecting a candidate entity related to the structured entity to be recorded from the knowledge map, and according to the candidate entity The prior attribute information of the category and the preset model determine that the structured entity to be included is an associated entity, the associated entity and the candidate entity are merged, and the associated entity is included in the knowledge graph. The embodiment of the present invention solves the problem that when the existing knowledge map collects entities, each time an entity is added, an entity analysis must be performed for each existing entity in the knowledge map, which results in a large amount of calculation, a long time-consuming and troublesome entity analysis. For problems with low accuracy, selecting candidate entities and then using prior knowledge to fuse preset models can effectively improve the efficiency and accuracy of entity associations, reduce the amount of calculation, and enable knowledge graphs to simply and efficiently include structured entities.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of data processing, and in particular to a structured entity recording method, device, server and storage medium. Background technique [0002] Knowledge graph plays a pivotal role in both academia and industry. It is the foundation of artificial intelligence and the only way to realize applications such as intelligent question answering. It can provide users with information quickly and conveniently. The knowledge graph is essentially a network composed of entity nodes and edges between nodes. The repetition rate and accuracy rate of the knowledge graph will affect its service quality. [0003] When there is an update requirement, the knowledge map needs to include new entities. At present, usually every time an entity is added, an entity analysis is required for each entity in the knowledge graph. This process is computationally intensive and time-consuming, and cannot be applie...

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): G06F16/36
CPCG06F16/367G06F16/28G06N5/022G06N20/00G06N7/01G06F16/288G06F16/951G06F16/955G06F16/9024
Inventor 徐也冯知凡陆超张扬方舟王述朱勇李莹
Owner BEIJING BAIDU NETCOM SCI & TECH CO LTD
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
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap