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

Cold start recommendation method and device based on user interest migration and storage equipment

A technology of user interest and recommendation method, which is applied in the fields of user cold start recommendation, device and storage device, and can solve the problems of enhanced accuracy and inability to accurately predict user interest, etc.

Pending Publication Date: 2021-04-16
HANGZHOU ZHICONG NETWORK TECH LOMITED CO
View PDF1 Cites 11 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] This patent effectively utilizes third-party user data, but the user data it involves are basically demographic characteristics, and such characteristics cannot accurately predict user interests in the actual operation process
At the same time, in the sorting of candidate sets, the patent uses a single factor for sorting, and the accuracy of push needs to be strengthened

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
  • Cold start recommendation method and device based on user interest migration and storage equipment
  • Cold start recommendation method and device based on user interest migration and storage equipment
  • Cold start recommendation method and device based on user interest migration and storage equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0071] Step S21 is based on the user-topic probability distribution as the user characteristic feature, including the following steps:

[0072] Step S211. Utilize the user access log to construct a user-term matrix, including:

[0073] Step S2111. Eliminate noise data in the log data, including content without tag information and log data with too little user behavior. Among them, the content without label information means that the corresponding label cannot be matched in the content label library. In order to reduce the calculation cost, it is directly filtered; cause some disturbance. Generally, a threshold (such as 10, 20, etc.) can be determined according to the distribution of user access times, and user logs that do not meet the threshold can be directly filtered. Thus, for each user u, the user behavior vector [a 1 ,a 2 …a s ], where a i Represents content.

[0074] Step S2112. According to the content-tag dictionary, map the content in the user history browsing...

Embodiment 2

[0082] Embodiment 2: In a situation similar to Embodiment 1, the embedding method is used as the user's feature vector. Unlike the LDA model, this method only needs to use the user's access footprint. The ID feature of the content is mapped to another low-dimensional space through item2vec, and the vectorized expression of the content is obtained. Then, according to the user's recent access content records, the user's vectorized expression is obtained through weighted average. The main steps are as follows: Divide the user's access content list into multiple session fragments. Specifically, the list of user behaviors is sorted by time, and the time interval between two previous behaviors is calculated. If the interval is greater than a certain threshold (for example, 30s, 60s, etc.), segmentation is performed. At this point, the user's behavior sequence is converted into a conversation sequence. Based on the conversation sequence, the word2vec training method skip-gram is us...

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 technical problem to be solved by the invention is to extract interests and preferences of users to complete personalized user cold start recommendation by utilizing historical behavior information of new e-commerce users on a content platform in allusion to defects in the prior art. In order to achieve the purpose, according to the cold start recommendation method and device based on user interest migration and the storage equipment, group attributes of the users are constructed by utilizing behavior footprints of new users on other platforms. Then clustering is carried out based on the theory of human grouping according to the interest characteristics of the users, the users are divided into a plurality of subsets, and then commodity preferences are obtained through calculation according to the historical behaviors of the users of the subsets and serve as candidate sets of the users of the type. By the adoption of the technical scheme, the commodities which the new user may like can be predicted more accurately, the new user can find the commodities which the user may like more quickly and find a social circle suitable for the user himself / herself more quickly, the new user can obtain more friendly use experience on a new platform, and therefore the retention rate of the new user is increased.

Description

technical field [0001] The present application relates to the field of information processing technology, and in particular to a user cold-start recommendation method based on user interest migration, an apparatus and a storage device involved in the cold-start recommendation method. Background technique [0002] With the continuous expansion of the scale of e-commerce, the categories and products of various e-commerce platforms are growing rapidly, and customers need to spend a lot of time to find the products they want to buy. This behavior of browsing a large number of irrelevant products not only greatly improves user The cost of shopping time will also cause consumers to lose patience after exhaustion, which will damage the interests of merchants. Therefore, how to allow users to quickly find the products they need in the product library, and how to allow merchants to maximize the exposure benefits of products, thus the recommendation system came into being. [0003] A...

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): G06F16/9535G06F16/35G06F16/34G06K9/62G06Q30/06
Inventor 不公告发明人
Owner HANGZHOU ZHICONG NETWORK TECH LOMITED CO
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com