User model construction method and recommendation method for web news classification recommendation

A user model and construction method technology, applied in the direction of text database clustering/classification, character and pattern recognition, special data processing applications, etc., can solve problems such as inability to meet user diversity, single recommended content, etc., to reduce waste, ensure unifying effect

Active Publication Date: 2021-10-08
TONGJI UNIV
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its disadvantage is that the recommended content is single and cannot satisfy the diversity of users

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
  • User model construction method and recommendation method for web news classification recommendation
  • User model construction method and recommendation method for web news classification recommendation
  • User model construction method and recommendation method for web news classification recommendation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The present invention will be described in detail below in conjunction with the accompanying drawings and specific embodiments. This embodiment is carried out on the premise of the technical solution of the present invention, and detailed implementation and specific operation process are given, but the protection scope of the present invention is not limited to the following embodiments.

[0040] Because the model is mainly trained under the convolutional neural network of deep learning, I will briefly introduce the algorithm recommended by the convolutional neural network for text classification, such as figure 1 Shown:

[0041] (1) Manually classify the training in advance, for example, we can divide it into ten categories: technology, entertainment, sports, etc.

[0042] (2) Before the input of the convolutional neural network, the data needs to be preprocessed to convert words into word vectors. Generally use Word2Vec or Glove, which one is better depends on the t...

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 present invention relates to a user model construction method and recommendation method for webpage news classification recommendation, wherein the user model construction method includes: step S1: loading the user's browsing history, and extracting pictures and text respectively; step S2: according to The extracted pictures are processed separately to obtain the first description feature used to describe each picture; Step S3: According to the extracted text, respectively processed to obtain the second description feature used to describe each paragraph of text; Step S4: The first description feature and the second description feature are combined to obtain the third description feature, and fast clustering is performed to obtain multiple cluster centers; step S5: perform n-gram processing on the third description feature to obtain multiple n-gram units, and n The ‑gram unit is compared with the clustering center, and the n‑gram unit outside the threshold value is discarded; step S6: taking the remaining n‑gram unit as input, constructing and training a wide convolutional neural network to obtain a user model. Compared with the prior art, the present invention has the advantages of accurate recommendation and the like.

Description

technical field [0001] The invention relates to a news classification recommendation technology, in particular to a user model construction method and recommendation method for web page news classification recommendation. Background technique [0002] In recent years, with the rapid development of mobile terminals, the proportion of news browsing on the Internet has become larger and larger. All web browsers push relevant news to increase the reading volume of customers. Browsers can directly accept recommendations, which can improve reading efficiency and save a lot of time. Therefore, it is very urgent to build a user-based fast and efficient web page recommendation system model. [0003] There are roughly three types of current recommendation system models, content-based recommendation, association-based recommendation, and collaborative filtering-based recommendation. [0004] The primary task of building a content-based personal webpage recommendation system is to ext...

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): G06F16/9535G06F16/35G06K9/62
CPCG06F16/35G06F16/9535G06F18/24147
Inventor 李菁陶爱山赵生捷刘庆文
Owner TONGJI 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
Try Eureka
PatSnap group products