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

Hybrid recommendation method based on user commodity portrait and potential factor feature extraction

A feature extraction and mixed recommendation technology, applied in the field of artificial intelligence, can solve the problems of sparse features, reduced recommendation efficiency, and inability to make recommendations, so as to improve robustness and avoid the effect of dimensionality disaster

Active Publication Date: 2020-06-19
HARBIN UNIV OF SCI & TECH
View PDF12 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] Compared with the traditional recommendation method, such as the collaborative filtering method, this method encounters the situation that a new product is added to the scoring matrix, that is, when a new product appears, no user has evaluated it. Recommendations cannot be made because there is not enough scoring data. Using user and product portraits to establish user and product characteristics can effectively solve the cold start problem that collaborative filtering has for new users and new products. The method of user and item latent factors can map users and items into their respective latent spaces, and describe the feature representation of users and items through latent factors, which can describe the attributes of users and items from multiple latent spaces and overcome the problems based on The problem of sparse features in the method of user and product portrait, but also because of ignoring the inherent feature attributes of users and products, the recommendation efficiency will decrease

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
  • Hybrid recommendation method based on user commodity portrait and potential factor feature extraction
  • Hybrid recommendation method based on user commodity portrait and potential factor feature extraction
  • Hybrid recommendation method based on user commodity portrait and potential factor feature extraction

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0093] Embodiment one: adopt the data set of Movielens1M size to verify the method that the present invention proposes, and experimental process is as follows:

[0094] (1) Data preprocessing: preprocess the three files in the data set, the data includes user data set, movie data set and rating data set. The user data set contains user ID, gender, age group, occupation and other information. The movie dataset contains movie ID, movie showtime, movie title, and movie genre. The Ratings dataset contains user rating data for movies. The data processing method is as follows: For the discrete variables of gender, age group, and occupation in the user data, encode them according to Step1.2; for the movie title in the movie data, perform feature extraction according to the steps in Step1.3, and summarize the user and Feature representation after movie processing. Normalize the overall features.

[0095] (2) Construct the user's rating matrix for movies based on the rating data se...

Embodiment 2

[0103] Embodiment 2: Use the completion status of developers on a certain bidding website crawled by web crawlers to recommend reasonable developers for each task according to the method of the present invention. The experimental process is as follows:

[0104] (1) Data preprocessing: the data set includes developer information data, task data, and developer score data on task completion. The developer data set includes developer ID, developer skill label, developer task completion status, etc. , the task dataset contains information such as task ID, skill tags involved in the task, and submission time. The score dataset contains the scores of different developers for each task. Clean the data set and filter useful information. The features of different fields are encoded using the Step1 processing method, and the feature representations processed by the task and the developer are respectively summarized. Normalize the overall features.

[0105] (2) Construct the task and ...

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 hybrid recommendation method based on user commodity portrait and potential factor feature extraction. The hybrid recommendation method comprises the following steps of S100,extracting explicit feature representation of a user and a commodity through information of the user portrait and the commodity; s200, mapping the user and the commodity to a potential space to obtainpotential factor feature representation of the user and the commodity; and S300, performing feature extraction on the explicit features and the potential factor features by using a stack type noise reduction auto-encoder to obtain low-dimensional feature representation with higher robustness. According to the invention, the explicit feature space and the potential factor feature space of the userand the commodity are considered at the same time; two feature spaces are comprehensively considered, the defect of a single recommendation model is overcome, the problem of cold start of articles issolved, meanwhile, SDAE is adopted for extracting high-dimensional features, the problem of dimensionality disasters is effectively avoided, and due to the fact that random noise is added in the training process, the robustness of the algorithm is greatly improved.

Description

technical field [0001] The present invention relates to feature representation and cleaning of text information in user and product portraits, and a feature extraction method using score matrix decomposition, especially a hybrid recommendation method based on user product portraits and latent factor feature extraction, belonging to field of artificial intelligence. Background technique [0002] The recommendation system is a model that can predict users' preferences or ratings for products and information, and is an important channel for users to find information and products suitable for them from the vast amount of information on the Internet. Use the user's historical behavior of the product (such as: purchase, browse, click, evaluation, etc.) to mine each user's preferences, and then make personalized recommendations for users. The historical behavior of users on products is usually divided into two categories: one is explicit feedback, that is, the rating information o...

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): G06F16/9535G06Q30/06G06Q30/02G06F16/35G06F40/284G06N3/04
CPCG06F16/9535G06Q30/0631G06Q30/0201G06F16/35G06N3/045
Inventor 席亮刘越
Owner HARBIN UNIV OF SCI & TECH
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