Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

User portrait knowledge similarity calculation method

A user and knowledge technology, applied in the field of intelligent analysis, can solve problems such as spending a lot of time

Active Publication Date: 2020-10-02
南京国睿信维软件有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When users query knowledge, they need to spend a lot of time and energy traversing the search results, or salvaging in the vast knowledge base.

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 portrait knowledge similarity calculation method
  • User portrait knowledge similarity calculation method
  • User portrait knowledge similarity calculation method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0029] Such as figure 1 As shown, the user portrait knowledge similarity calculation method of the present invention includes the following steps:

[0030] Step 1: Count the standard behaviors and basic attributes that affect user portraits. Standard behaviors include viewing, liking, sharing, collecting, downloading, commenting, and asking questions. The basic attributes include departments, positions, roles, and majors; the present invention selects users There are 5 standard behaviors (behavior operations) of downloading, asking questions, collecting, sharing, and commenting, and two basic user attributes of department and position, with a total of 7 parameters.

[0031] Step 2: Assign weights to standard behaviors and basic attributes, and set the weight of each parameter , and recorded as , the present invention has 7 calculation values ​​in total, taking .

[0032] Step 3: Extract standard behavior records and basic attribute tags, record the user behavior log tab...

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 user portrait knowledge similarity calculation method, and belongs to the technical field of intelligent analysis, and the method comprises the steps: firstly stipulating theimportant behaviors of a user, the selection number of personal basic attributes, and the specific behavior operation and attribute contents; secondly, performing parameter weighting on each user behavior and each user attribute, and determining a specific gravity value of the user behavior and the user attribute in overall knowledge similarity calculation; extracting behavior records and attributes of the user, counting labels associated with knowledge accessed by user behaviors, and endowing the labels with weight one by one; and finally, collecting the total weight values of the user knowledge labels, and performing sorting according to the weights to obtain a user knowledge portrait. The knowledge similarity is calculated based on the user behavior operation and the parameter weight of the personal basic attribute, the user portrait is drawn through the specific behavior operation of the user, and the matched similar knowledge is correspondingly returned. The method is high in knowledge recommendation accuracy, the recommendation proportion can be dynamically adjusted, and operation is convenient.

Description

technical field [0001] The invention relates to a method for calculating the similarity degree of user portrait knowledge, which belongs to the technical field of intelligent analysis. Background technique [0002] Today is an era of massive data, and users can receive a lot of information on various websites. A large part of this is invalid, repetitive, or spam traffic that users are not interested in. When users query knowledge, they need to spend a lot of time and energy traversing the search results, or salvaging in the vast knowledge base. In order to accurately deliver similar knowledge to users that conforms to user behavior habits and personal characteristics, a method that can dynamically adjust the weight ratio and perform statistics based on the tags of a single piece of knowledge is needed to obtain user knowledge portraits and personal knowledge tags for dynamic knowledge similarity recommendations . Contents of the invention [0003] In order to solve the ...

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
IPC IPC(8): G06F16/9535G06F17/16G06K9/62
CPCG06F16/9535G06F17/16G06F18/22
Inventor 曹保龙彭天颖王磊卢浩然周苏霞
Owner 南京国睿信维软件有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com