Data feature extraction method fusing user time features and personality features

A technology of data features and extraction methods, which is applied in special data processing applications, electronic digital data processing, digital data information retrieval, etc., and can solve problems that affect the relevance of user personality factors, fail to extract discrete features, and reduce feature extraction efficiency. , to achieve accurate and efficient recommendation or prediction services, good scalability, and low efficiency

Active Publication Date: 2020-08-07
BEIJING INSTITUTE OF TECHNOLOGYGY
View PDF7 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When GAN is applied to extract discrete-time data such as user sequences, it often fails to extract suitable discrete features; when adjacent user features are quite different, it will generate "overall dependence" and ignore the differences between users. Differences, which affect the correlation with user personality factors and reduce the efficiency of feature extraction

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
  • Data feature extraction method fusing user time features and personality features
  • Data feature extraction method fusing user time features and personality features
  • Data feature extraction method fusing user time features and personality features

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0045] The data features obtained by using the present invention can be used in multiple application scenarios such as continuous point of interest recommendation, investment analysis, and health assessment, so as to meet people's growing material and cultural needs.

[0046] In this example, the application of continuous point of interest recommendation is taken as an example, and the sequence data of the present invention, which combines user time characteristics and personality characteristics, is applied to the task of continuous point of interest recommendation. The specific process is as follows:

[0047] figure 1 and figure 2 Shown is the check-in data within the scope of New York City in the FourSquare dataset we selected. They contain the transition probabilities (Probability) of different users in different types of locations within different time intervals (TransitionInterval), which shows that they are different for different Changes in interest in places. figur...

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 relates to a data feature extraction method fusing user time features and personality features, and belongs to the technical field of artificial intelligence. The method is based on multi-user batch time series data, a sequence relationship of data is modeled through a time convolution neural network, and meanwhile a time channel attention mechanism and a personality characteristic channel attention mechanism are introduced to automatically select data characteristics closely related to prediction of a next data point, so that comprehensive data characteristics of the user are obtained; and on the basis, related services based on historical habits of the user can be provided by utilizing an existing neural network model. Compared with the prior art, the method effectively solves the problem that the traditional neural network model is low in efficiency when using data, emphasizes the importance of time information and user personality to feature extraction through two attention mechanisms of the time channel and the personality feature channel, and improves the effectiveness of feature extraction.

Description

technical field [0001] The invention relates to a data feature extraction method, in particular to a data feature extraction method that integrates user time features and personality features, and belongs to the technical field of artificial intelligence. Background technique [0002] In recent years, social networks based on geographic location information have made great progress: users can easily obtain their own real-time location information, share or search for related information services in the network, and related applications have emerged spontaneously. In addition to latitude and longitude, places in social networks also include specific place names, place types, social functions, and user-defined tags. Such places with rich information are called places of interest, which are distinguished from meaningless latitude and longitude coordinates. However, each user's location data is highly discrete, and how to model it and make accurate recommendation calculations is...

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): G06F16/9537G06F16/9535G06K9/62
CPCG06F16/9537G06F16/9535G06F18/251
Inventor 礼欣郭振宇苏海萍
Owner BEIJING INSTITUTE OF TECHNOLOGYGY
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