News recommendation method and device based on ontology model library

A recommendation method and ontology library technology, applied in the field of intelligent news recommendation method and its device, can solve the problems of high cost of news practice, achieve the effect of improving business output level, wide content, and improving work efficiency

Inactive Publication Date: 2016-11-09
ZHONGKE DINGFU BEIJING TECH DEV
View PDF0 Cites 37 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In their daily work, they need to manually spend a lot of time and energy to collect and mine the depth and breadth of related information knowledge, which also results in high requirements for practitioners' experience accumulation and extensive knowledge in this type of work, which makes the cost of journalism relatively high.

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
  • News recommendation method and device based on ontology model library
  • News recommendation method and device based on ontology model library
  • News recommendation method and device based on ontology model library

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in conjunction with specific embodiments and with reference to the accompanying drawings.

[0021] figure 1 It is a schematic diagram of the intelligent news recommendation method proposed by the present invention.

[0022] like figure 1 The input of the shown intelligent news recommendation method 100 is a news document 111, which may be one article or multiple articles. The "news documents" mentioned here generally refer to news texts published by various media, and the specific format can be in the form of web pages, plain text or any other semi-structured format (such as xml format).

[0023] In step S120, the news document 111 is preprocessed, including sentence segmentation, word segmentation, and part-of-speech tagging. The sentence segmentation process is to break the text 111 with a period and divid...

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 provides a news recommendation method and device based on an ontology model library. The method comprises the following steps: (1) carrying out preprocessing which includes punctuation, word segmentation, part-of-speech tagging and the like; (2) carrying out news ontology identification: identifying news ontology information in an input news text; (3) carrying out key information mining: combining with the identified news ontology information to mine key information (including keywords, key ontologies and the like) in an input news discourse; (4) carrying out attribute acquisition: on the basis of the information obtained in the previous steps, inquiring a knowledge graphto obtain knowledge point attribute information, carrying out expansion according to the relationship of the mapping knowledge domain, and further mining the attribute information; (5) carrying out dimension generation: on the basis of the information (including the ontology, the keyword, the attribute and the like) obtained in the previous steps, generating a recommendation dimension; and (6) carrying out recommendation knowledge recalling: on the basis of the recommendation dimension, obtaining the recommendation knowledge in a news document library and the knowledge library.

Description

technical field [0001] The invention relates to the technical fields of natural language processing and intelligent recommendation, in particular to an intelligent news recommendation method and device based on a news ontology knowledge base and a knowledge map. Background technique [0002] In the Internet era, especially the newly emerging mobile Internet and big data era, news recommendation is a key function in news reading services, which plays a great role in improving user experience and increasing user stickiness. [0003] There are generally two types of news recommendation technologies in the prior art. [0004] One is a content-based recommendation technology, which is mainly based on the vector space model of the bag of words to measure the similarity of documents. The other is a collaborative filtering technology based on user behavior, which is mainly based on user historical behavior data to predict news that potential users are interested in. [0005] The p...

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): G06F17/30
CPCG06F16/9535
Inventor 不公告发明人
Owner ZHONGKE DINGFU BEIJING TECH DEV
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