Unlock instant, AI-driven research and patent intelligence for your innovation.

A Restaurant Recommendation Method Fused with User Behavior Information

A recommendation method and user technology, applied in the field of recommendation system, can solve problems such as quantization error of user rating data, difficulty in reflecting user personalized behavior information, roughness, etc., and achieve the effect of improving the recommendation effect

Active Publication Date: 2021-10-29
ZHEJIANG UNIV OF TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Its shortcomings are also very prominent. It roughly represents the overview of user experience, and it is difficult to reflect the user's personalized behavior information, resulting in quantitative errors in user rating data.

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
  • A Restaurant Recommendation Method Fused with User Behavior Information
  • A Restaurant Recommendation Method Fused with User Behavior Information
  • A Restaurant Recommendation Method Fused with User Behavior Information

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The present invention will be further described below in conjunction with the accompanying drawings.

[0035] refer to Figure 1 ~ Figure 3 , a restaurant recommendation method that fuses user behavior information. The present invention uses a Yelp restaurant user empirical data set, which includes user IDs, restaurant IDs, time of occurrence of user dining behaviors, and user ratings.

[0036] The present invention comprises following four steps:

[0037] S1: According to the user's historical dining data, construct the user's dining behavior sequence network;

[0038] S2: Use the DeepWalk algorithm to perform representation learning on the network nodes of the user's dining behavior sequence;

[0039] S3: Combined with the user's historical dining behavior, reconstruct the cost characteristics of the user's dining behavior;

[0040] S4: Use user rating data and behavior cost features in parallel to build a restaurant recommendation model.

[0041] In the step S1, ...

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

A restaurant recommendation method that integrates user behavior information, comprising the following steps: 1) constructing a user dining behavior sequence network according to user history dining data; 2) using the DeepWalk algorithm to perform representation learning on the user dining behavior sequence network nodes; 3) combining The user's historical dining behavior is used to reconstruct the cost characteristics of the user's dining behavior; 4) The user rating data and behavioral cost characteristics are used in parallel to build a restaurant recommendation model. According to the user's historical dining behavior data, the invention reconstructs the dining behavior cost characteristics of the dining user, more reasonably reflects the personalized style of the user's dining consumption behavior, and provides a solid data quality foundation for further building the user's restaurant recommendation system.

Description

technical field [0001] The invention relates to the field of recommendation systems, in particular to a restaurant recommendation method that integrates user behavior information. Background technique [0002] With the development of Internet technology and mobile terminals, people are entering the era of information overload from the era of information scarcity. Both information consumers and information producers have encountered troubles from various aspects: as an information consumer, how to find the information they are interested in from a large amount of information is sometimes a very headache; as an information producer, how to It is also very difficult to make the information you put out stand out and attract attention. The recommendation system is an important tool to alleviate the current information overload. Its task is to connect users and information, help users find valuable points of interest for them, and make information accurately displayed in front of...

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): G06Q30/06G06Q50/12
CPCG06Q30/0631G06Q30/0639G06Q50/12
Inventor 傅晨波周鸣鸣余斌郑永立宣琦
Owner ZHEJIANG UNIV OF TECH