Eureka AIR delivers breakthrough ideas for toughest innovation challenges, trusted by R&D personnel around the world.

A restaurant recommendation algorithm based on score and feature similarity in social networks

A social network and recommendation algorithm technology, applied in the field of food and beverage recommendation algorithms, can solve the problems of vulnerable systems and low recommendation accuracy, and achieve the effects of improving anti-attack capability, increasing attack costs, and improving accuracy.

Active Publication Date: 2018-02-02
NANJING UNIV OF POSTS & TELECOMM
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] In view of the shortcomings of traditional recommendation algorithms, in order to solve the problems of low recommendation accuracy and system vulnerability, and at the same time when big data is widely used in e-commerce, by comprehensively examining the connections of social networks and with the help of a large amount of effective data aggregation, To achieve a more accurate catering recommendation service, the present invention proposes a catering recommendation algorithm based on similar scores and features in social networks

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 algorithm based on score and feature similarity in social networks
  • A restaurant recommendation algorithm based on score and feature similarity in social networks
  • A restaurant recommendation algorithm based on score and feature similarity in social networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0040] In order to make the purpose, technical solution and advantages of the present invention more clear, the utility model will be further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present invention, not to limit the present invention.

[0041] Suppose U a I am from Beijing, and I am in Nanjing on a business trip. Because I am not familiar with the local conditions, I need to provide U a Recommend meals or delicacies that suit their habits.

[0042] The specific implementation steps of the algorithm are:

[0043] Step 1) Traverse all currently registered users (to simplify the description, a total of 6 users are selected, and the users may come from all over the country), and obtain the historical rating data of all users on surrounding restaurants, as shown in Table 1. According to the historical rating data of all users Determ...

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 restaurant recommendation algorithm based on rating and feature similarity in a social network, which mainly includes the following steps: 1) establishing a user rating database in the current social network; 2) calculating the rating similarity between Ua and other users in the user rating database ; 3) Select the k users with the highest rating similarity with Ua to obtain a set of recommended users with similar ratings; 4) Construct a feature similarity model M=(χa, i, δa, i, σa, i, γa, i); 5) Calculate the feature similarity recommendation degree and recommend the top-ranked items to the target users. In the present invention, the feature similarity between users is used as the second basis for the recommendation algorithm in addition to the conventional scoring similarity, and the calculation of various user features not only greatly increases the attack cost, but also greatly improves the anti-attack ability, and Improve the accuracy of recommendation.

Description

technical field [0001] The invention relates to the field of recommendation algorithms in social networks, in particular to a food and beverage recommendation algorithm based on score and feature similarity and applied to social networks. Background technique [0002] As a hot issue, personalized service has been concerned and studied by many research fields. An important research content of personalized service is personalized recommendation, which can find user groups with similar interests according to user interests, and then recommend information of interest to each other among user groups. Use personalized recommendation technology to recommend restaurants suitable for users, so that users can quickly obtain food and restaurant information that conforms to their consumption habits. For the system, it can not only gain the trust of users, but also gain more favor and use. , It also makes the content recommended by the system more accurate and can better serve users. ...

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): G06F17/30G06Q50/00
Inventor 黄海平李峰沙超王汝传吴敏赵孔阳秦宇翔杜建澎
Owner NANJING UNIV OF POSTS & TELECOMM
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
Eureka Blog
Learn More
PatSnap group products