High-quality electric power package recommendation method based on improved collaborative filtering algorithm

A technology of collaborative filtering algorithm and recommendation method, which is applied in the field of intelligent electricity sales, can solve problems such as cold start and low accuracy, and achieve the effect of increasing accuracy, avoiding one-sidedness, and solving cold start problems

Inactive Publication Date: 2021-10-22
SICHUAN UNIV
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] In view of the above problems, the purpose of the present invention is to provide a high-quality power package recommendation method based on an improved collaborative filtering algorithm to solve the problems of one-sidedness, low accuracy, and cold start problems in the high-quality power package recommendation process

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
  • High-quality electric power package recommendation method based on improved collaborative filtering algorithm
  • High-quality electric power package recommendation method based on improved collaborative filtering algorithm
  • High-quality electric power package recommendation method based on improved collaborative filtering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0050] The present invention will be described in further detail below in conjunction with the accompanying drawings and specific embodiments. The flow chart of the high-quality power package recommendation method based on the improved collaborative filtering algorithm proposed by the present invention is as follows figure 1 As shown, the specific process is as follows:

[0051] Step 1: Users score the package according to their own needs to obtain explicit demand scores, and analyze the behavior preferences of target users to obtain users' implicit demand scores. The explicit and implicit needs are fused to obtain the explicit and implicit package rating matrix based on user needs.

[0052] Dominant demand scoring: Users score high-quality power packages based on past power quality problems and demand for high-quality power. In active and subjective situations, the data obtained by scoring projects based on their own needs is called explicit demand scoring data. use Domina...

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 high-quality power package recommendation method based on an improved collaborative filtering algorithm, and the method comprises the steps: fusing the dominant demand score of a user and the implicit demand score of the user, and obtaining an implicit and implicit package score matrix based on the demands of the user; calculating the comprehensive package similarity among different high-quality power packages according to the high-quality power packages to obtain a nearest neighbor set of the high-quality power packages; weighting the score of the target high-quality power package by taking the comprehensive package similarity among the different high-quality power packages as a weight to obtain an initial prediction score of the target user on the target high-quality power package; calculating user similarity between the target user and other users to obtain a nearest neighbor set of the target user; for a high-quality electric power package of which the target user is not scored, weighting the high-quality electric power package through a nearest neighbor set of the target user to obtain a final prediction score; and forming a recommendation set by the first plurality of high-quality electric power packages with relatively high scores. According to the method, the problems of one-sidedness, low accuracy and cold start in the high-quality power package recommendation process are solved.

Description

technical field [0001] The invention relates to the technical field of intelligent electricity sales, in particular to a method for recommending high-quality electric power packages based on an improved collaborative filtering algorithm. Background technique [0002] With the in-depth development of my country's market economy, the promotion of power market reform is urgent. After the country launched the reform of the power system, it used market mechanisms to optimize the power supply guarantee mechanism and power source structure. Under the premise of ensuring necessary supervision, it gradually reduced government intervention in the power industry, and introduced market mechanisms in the determination of power prices and the provision of power services. , restoring the commodity attribute of energy. As an important electricity commodity, the electricity sales package is the carrier for electricity sales companies to provide users with electricity sales services. In ord...

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): G06Q30/06G06Q50/06
CPCG06Q30/0631G06Q30/0605G06Q50/06
Inventor 肖先勇王盼盼汪颖胡文曦陈韵竹陈智凡
Owner SICHUAN 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