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

A user feature and feature factor extraction and query method and system

A technology of user characteristics and eigenfactors, applied in special data processing applications, instruments, calculations, etc., can solve problems such as waste of resources and costs, low precision, induction, recording, etc., to save resources and training costs, and narrow the scope of search Effect

Active Publication Date: 2021-10-08
深圳市梦网视讯有限公司
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the embodiments of the present invention is to propose a method for extracting and querying user characteristics and characteristic factors, aiming at solving the problem of not combining the effectiveness of characteristics and factors in the prior art and systematically summarizing and recording the data characteristic screening. Re-searching for data in similar scenarios leads to low accuracy, waste of resources and costs

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
  • A user feature and feature factor extraction and query method and system
  • A user feature and feature factor extraction and query method and system
  • A user feature and feature factor extraction and query method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] figure 1 It is a flow chart of a user feature and feature factor extraction and query method in a preferred embodiment of the present invention; the method includes (S1-S3):

[0053] S1, creating a feature-factor two-dimensional matrix library of important user features and important factors in multiple scenarios;

[0054] Specifically, the method for creating a feature-factor two-dimensional matrix library of important user features and important factors of a scene includes the following steps (S101-S108):

[0055] figure 2 yes figure 1 A flowchart of a method for creating a feature-factor two-dimensional matrix library of important user features and important factors in one of the scenarios;

[0056] S101, extracting a user behavior data set from the user behavior statistics database in the first scene;

[0057] The user behavior data set includes at least one user feature and behavior prediction feature; the behavior prediction feature is generated according to ...

Embodiment 2

[0163] A method for extracting user features and feature factors, the method is the same as steps S101-S108 in Embodiment 1, and will not be repeated here.

Embodiment 3

[0165] Figure 8 It is a structural diagram of a user feature and feature factor extraction and query system in a preferred embodiment of the present invention;

[0166] A preferred embodiment of the present invention is a user feature and feature factor extraction and query system; the system includes:

[0167] A feature-factor two-dimensional matrix library creation device, which is used to create a feature-factor two-dimensional matrix library of important user features and important factors in multiple scenarios;

[0168] The scene-behavior two-dimensional matrix creation device is used to correlate the created feature-factor two-dimensional matrix libraries in different scenes according to the same or similar behavior prediction features to construct a scene-behavior two-dimensional matrix;

[0169] An important user feature and important feature factor query device is used to search for the same or similar behavior prediction features in the associated scene according t...

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 proposes a method and system for extracting and querying user features and feature factors. The method of the present invention first preprocesses the user behavior data of a certain scene, discretizes and reduces the dimensionality of user features, then optimizes the user features after dimensionality reduction, obtains important user features, and then performs eigenfactors in important user features Further filtering, find important feature factors, create two-dimensional matrix of important user characteristics and important feature factors of the scene; then according to the created two-dimensional matrix of important user features and important feature factors of different scenes, predict feature correlation through the same or similar user behavior Link to create a two-dimensional matrix of scene user behavior prediction features. Through the method of the present invention, when checking the characteristics and factors that may have an important impact on the decision-making results in similar scenarios, it is not necessary to spend a lot of money to search for data again, the search range can be narrowed, relatively accurate training results can be obtained, and a large amount of resources and training can be saved. cost.

Description

technical field [0001] The invention relates to the technical field of data mining, in particular to a user feature and feature factor extraction and query method and system. Background technique [0002] Existing feature screening technologies, such as PCA principal component analysis, Logistic regression, random forest feature importance judgment importance technology, BP backpropagation neural network for feature generalized weight technology evaluation, etc., have two defects: [0003] Depth: General dimensionality reduction only takes into account the dimensions of the features, but does not take into account the impact of different factors in the dimensions on the output. For example, in purchasing decisions, age is an important feature of influence, but age is divided into children, youth, middle-aged, Old age, the influence of different ages has not been distinguished, which makes it impossible to practice. I only know that age has an impact on purchases, but I don’t...

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): G06F16/2458
Inventor 慕畅
Owner 深圳市梦网视讯有限公司