Collaborative filtering method, collaborative filtering device and system

A collaborative filtering and aggregation technology, which is applied in the directions of instruments, marketing, and data processing applications, can solve problems such as hardware resource occupation, poor correlation, and high time complexity, and achieve reduced complexity, accurate similarity, and reduced time and effort. The effect of hardware resources

Active Publication Date: 2021-08-17
KE COM (BEIJING) TECHNOLOGY CO LTD
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to provide a collaborative filtering method, collaborative filtering device and system to solve the problem of low recall rate of high-correlation effective listings, long similar calculation time, Technical issues such as high time complexity and excessive hardware resource occupation

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
  • Collaborative filtering method, collaborative filtering device and system
  • Collaborative filtering method, collaborative filtering device and system
  • Collaborative filtering method, collaborative filtering device and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] The embodiment of the present invention provides a collaborative filtering method, such as figure 1 , the collaborative filtering method includes:

[0075] S1) Determine the first set of house sources, and form the preference data of the houses in the first set of house sources into a first preference data set corresponding to the selected user, wherein the houses in the first set of house sources are recorded have behavioral data of said selected users;

[0076] S2) Determine the range of the location area, and select some users according to the range of the location area, and then determine the second set of house sources, and form the preference data of the houses in the second set of house sources into a list corresponding to the part of users A second preference data set, wherein the houses in the second house source set are recorded with the behavior data of the part of the users;

[0077] S3) Determine the vector decomposition model to be trained, use at least ...

Embodiment 2

[0126] Based on the inventive concept of Embodiment 1, the embodiment of the present invention provides a collaborative filtering device, which may include:

[0127] The first selection module can be used to determine a first house source set, and form the preference data of the house sources in the first house source set into a first preference data set corresponding to the selected user, wherein the first house source The listings in the collection are recorded with the behavior data of the selected users;

[0128] The second selection module can be used to determine the range of the location area, select some users according to the range of the location area, and then determine the second set of house sources, and form the preference data of the house sources in the second set of house sources with the The second preference data set corresponding to the part of users, wherein the houses in the second house source set are recorded with the behavior data of the part of the us...

Embodiment 3

[0149] Based on the inventive concept of Embodiment 1, the embodiment of the present invention provides a system for recommending house sources, the system includes: one or more programs, one or more programs can form one or more services in some production environments, Each program or each service can execute one or more steps; in some specific implementations, one or more programs can be compiled or encrypted to become an executable engine, which can call some executable programs The output data of the engine can also rely on or have some function libraries and model libraries; the engine can be a recommendation engine, and the processing granularity of the recommendation engine can be the granularity determined by the administrative region;

[0150] The recommendation engine is configured to execute instructions corresponding to the method described in Embodiment 1.

[0151] The present invention utilizes administrative area granularity constraints and the co-occurrence st...

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 collaborative filtering method, a collaborative filtering device and a system, and belongs to the technical field of housing information processing. The method includes: determining a first set of housing sources, forming the preference data of the housing sources in the first set of housing sources into a first preference data set corresponding to the selected user; determining the scope of the location area, and selecting For some users, determine the second set of house sources, and form the preference data of houses in the second set of house sources into a second preference data set corresponding to some users; obtain the trained vector decomposition model through the second preference data set, and use the first The second preference data set and the trained vector decomposition model are used to obtain the feature vector set corresponding to the houses in the second house source set, the similarity of the feature vector set is calculated, and a similarity set is formed after the calculation is completed. The invention is used for determining recommended house sources with user preference characteristics through similar calculation.

Description

technical field [0001] The present invention relates to the technical field of house information processing, in particular to a collaborative filtering method, a recommendation method, a collaborative filtering device, a recommendation device, a system, a device and a computer-readable storage medium. Background technique [0002] In an item-based collaborative filtering algorithm, the similarity between items is usually used to generate a recommendation list, and this type of algorithm has a time complexity of O(n 2 ). However, in the current era of information overload, there are countless item information, such as housing information (housing source, as an item to be processed); as the amount of data n gradually increases, the calculation between any two Items The time cost and hardware resource consumption of similarity are very high, so an effective computing strategy is needed to reduce the computing cost and save computing resources. Contents of the invention [0...

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): G06F16/9536G06F16/9537G06Q30/02G06Q50/16
CPCG06Q30/0255G06Q30/0259G06Q30/0261G06Q30/0271G06Q50/16G06F16/9536G06F16/9537
Inventor 李政浩董天南
Owner KE COM (BEIJING) TECHNOLOGY CO LTD
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap