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

Article co-occurrence relationship determination method and device and judgment model obtaining method and device

A determination model and relationship determination technology, which are applied in the field of a method and device for determining the co-occurrence relationship of items, and a method and device for obtaining a determination model, which can solve the problem that the unknown co-occurrence relationship between items cannot be discovered.

Pending Publication Date: 2021-12-07
BEIJING WODONG TIANJUN INFORMATION TECH CO LTD +1
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The above related technologies can discover the co-occurrence relationship of items known in history, but cannot discover the co-occurrence relationship of unknown items

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
  • Article co-occurrence relationship determination method and device and judgment model obtaining method and device
  • Article co-occurrence relationship determination method and device and judgment model obtaining method and device
  • Article co-occurrence relationship determination method and device and judgment model obtaining method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the present disclosure with reference to the drawings in the embodiments of the present disclosure.

[0054] Unless otherwise specified, descriptions such as "first" and "second" in the present disclosure are used to distinguish different objects, and are not used to indicate meanings such as size or timing.

[0055] The item co-occurrence relationship means that in a certain business scenario, different items often appear together, and these items are called item pairs with a co-occurrence relationship. For example, in the e-commerce shopping business, different items are often purchased at the same time, and these items are called co-shopping items, and the co-occurrence relationship at this time is represented as co-purchasing relationship. The co-occurrence relationship of the present disclosure is not limited to the illustrated examples.

[0056] figure 1 A schematic ...

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 an article co-occurrence relationship determination method and device and a judgment model obtaining method and device, and relates to the field of computer application. The article co-occurrence relationship determination method comprises the following steps: acquiring a first article pair of which the co-occurrence relationship is to be determined; obtaining feature information of each article in the first article pair, wherein the feature information comprises a graph embedding vector of articles determined on the basis of an article co-occurrence graph where each article is located, and each article co-occurrence graph is constructed on the basis of the plurality of articles with the co-occurrence relationship; inputting the feature information of each article in the first article pair into an article co-occurrence relationship judgment model for processing, wherein the article co-occurrence relationship judgment model is obtained by training a deep neural network by using article co-occurrence historical data; and obtaining a judgment result of whether the first article pair output by the article co-occurrence relationship judgment model has a co-occurrence relationship or not. By means of the article co-occurrence relationship judgment model, a historical known article co-occurrence relationship can be judged, an unknown article co-occurrence relationship can also be judged, and a judgment result is more objective.

Description

technical field [0001] The present disclosure relates to the field of computer applications, in particular to a method and device for determining the co-occurrence relationship of items and a method and device for obtaining a judgment model. Background technique [0002] In e-commerce, discovering the co-occurrence relationship of items and recommending items with co-occurrence relationship to users can help users choose items efficiently. [0003] In some related technologies, the number of times of co-occurrence of item pairs in historical data is counted, and the co-occurrence item pairs are found according to the statistical results. For example, count the number of times an item pair is purchased at the same time in the order history data, and the item pair whose number of times is greater than a preset value is regarded as a same-shopping item pair. [0004] The above-mentioned related technologies can discover historically known co-occurrence relationships of items, ...

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): G06Q30/02G06N3/04G06N3/08
CPCG06Q30/0201G06Q30/0224G06N3/08G06N3/045
Inventor 王蒙李建星史晓斌
Owner BEIJING WODONG TIANJUN INFORMATION TECH CO LTD