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

Personalized recommendation method and system

A recommendation method and recommendation system technology, applied in the field of information search, to achieve the effect of solving the cold start problem, ensuring accuracy, and expanding the number of recalls

Inactive Publication Date: 2017-11-07
DATAGRAND TECH INC
View PDF6 Cites 20 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, in actual business scenarios, there are still many challenges i

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
  • Personalized recommendation method and system
  • Personalized recommendation method and system
  • Personalized recommendation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0046] In order to enable those skilled in the art to better understand the technical solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0047] Such as figure 1 As shown, the present invention provides a kind of personalized recommendation method, comprises the following steps:

[0048] S101, obtain input data, and input data comprises click data and object data, and wherein, click data is user's operation behavior to object of interest, and object data is interest object title and the category or label extracted according to title;

[0049] Specifically, the click data format is as follows:

[0050] ,

[0051] Each row represents an action (action) performed by a user (userid) on an item (itemid) at a time point (action_time). Operations include click, buy, collect, like, dislike, etc. Object data The information data of the object of interest (that is, the item), the format i...

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 personalized recommendation method and system. The method comprises the following steps that input data is obtained, wherein the input data comprises the click behavior data and the click object data of a user; the input data is preprocessed; a first searching model and a second searching engine so as to conduct interest analysis on the preprocessed input data, and a first candidate list and a second candidate list are obtained; the first candidate list and the second candidate list are set and analyzed respectively so as to obtain the algorithm weight of the first candidate list and the algorithm weight of the second candidate list, and weight fusion is conducted; the result obtained through the fusion is reordered so as to serve as a recommendation list, and then the recommendation list is output. By means of the personalized recommendation method and system, the semantic comprehension problem of an ambiguous text in a recommendation scene is effectively solved, the accuracy of personalized recommendation results is ensured, and the recall quantity of the recommendation results is increased.

Description

technical field [0001] The invention relates to the technical field of information search, in particular to a personalized recommendation method and system. Background technique [0002] In today's information society, personalized recommendation systems have become inseparable from our lives. When we read news, shop online, listen to music, and watch videos, we will see various "recommendation" lists in the form of "guess you like", "products you may be interested in", "with you Users with similar interests are still watching" and so on. Personalized recommendation through in-depth analysis and mining of user behavior data, recommends information or products that are really interesting to users. For individuals, personalized recommendations can help users solve the problem of being at a loss when faced with a wide variety of products, movies, songs, videos and other services. For enterprises, personalized recommendation can not only provide excellent user physical examin...

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): G06F17/30G06Q30/06
CPCG06F16/435G06F16/635G06F16/735G06F16/9535G06Q30/0631
Inventor 于敬桂洪冠张健陈运文文辉
Owner DATAGRAND TECH INC