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

Sequence recommendation method and device fusing multi-aspect time domain information and medium

A recommendation method, a multi-faceted technology, applied in digital data information retrieval, character and pattern recognition, sales/lease transactions, etc., can solve the problem of insufficient consideration of time information, limited time information, and poor modeling Time information and other issues to achieve the effect of improving performance and enriching representation

Pending Publication Date: 2022-08-09
HARBIN ENG UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In this regard, related investigations have been carried out on the use of time information in sequence recommendation, and it is found that there are three types of time information, but these works only use one of the time information, and do not fully consider all time information, and There are still serious problems with the use of time information: (1) Absolute time information should be driven by items, rather than modeling user information, for example, slippers are usually purchased in summer, and down jackets are purchased in winter
(3) The use of time information is limited, and it cannot model time information well

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
  • Sequence recommendation method and device fusing multi-aspect time domain information and medium
  • Sequence recommendation method and device fusing multi-aspect time domain information and medium
  • Sequence recommendation method and device fusing multi-aspect time domain information and medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0031] like Figure 1 to Figure 3 As shown, the present invention provides a sequence recommendation method that integrates multi-faceted time domain information, which specifically includes the following steps:

[0032] Step 1: Obtain sequence data, preprocess the data set and divide it into training set, validation set and test set;

[0033] The step 1 specifically includes the following steps:

[0034] Step 1.1: From the sequence...

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 sequence recommendation method and device fusing multi-aspect time domain information and a medium. According to the method, three kinds of time domain information are considered to improve the performance of sequence recommendation, a sequence recommendation model fusing multi-aspect time domain information is constructed, the model comprises three parts, and each part utilizes one kind of multi-granularity time domain information to generate article representation possibly interested by a next user. The model specifically comprises an absolute time module, a relative article time interval module and a relative recommendation time interval module. And the three modules are effectively fused to generate an article representation which is interested by a final user at the next moment, so that the sequence recommendation performance is greatly improved.

Description

technical field [0001] The invention belongs to the technical field of sequence recommendation, and in particular relates to a sequence recommendation method, device and medium that integrates multi-faceted time domain information. Background technique [0002] As an effective tool for dealing with information overload, recommender systems have been widely used in many real-world scenarios, with the purpose of improving user usability, helping companies retain users, and promoting business development. Among the many fields of recommender systems, sequence recommendation has shown a strong ability to capture users' dynamic preferences and has become a research hotspot. Therefore, sequence recommendation is widely used in various scenarios, such as e-commerce, news recommendation and advertising recommendation, etc. Wait. [0003] Sequence recommendation aims to model user behavior sequences, such as the sequence of purchasing items, and learn user representations for predic...

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 Applications(China)
IPC IPC(8): G06F16/9535G06Q30/06G06K9/62
CPCG06F16/9535G06Q30/0631G06F18/25
Inventor 韩启龙梁国涛宋洪涛王也李丽洁张海涛
Owner HARBIN ENG UNIV