Method for recommending system data abstraction and automation characteristic engineering

A recommendation system and feature engineering technology, applied in the field of recommendation systems, can solve the problems of not being able to meet the requirements of fast launch, spending a lot of time and energy, and frequent changes, etc., to achieve high promotion and application value, reduce development workload, and improve the effect of iteration speed

Active Publication Date: 2019-12-03
青岛创新奇智科技集团股份有限公司
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The case-by-case strategy requires engineers to understand the specific business meaning of the data in each recommendation project, and spend a lot of time and energy writing data processing codes and feature construction codes. These codes are often due to model adjustments. Frequent changes

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
  • Method for recommending system data abstraction and automation characteristic engineering

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0030] The present invention will be described in further detail below in conjunction with the examples.

[0031] The invention discloses a method for recommending system data abstraction and automatic feature engineering. For recommending system data in any scene, it is only necessary to understand the keywords and specified processing functions in the field generated after adapting the recommending system data. You can use general data processing and feature engineering codes to complete feature generation, including the following steps:

[0032] Step a, data abstraction, based on the field setting principle, adapt the original data provided by Party A into standard abstract data;

[0033] Step b. Configure schema for standard abstract data, develop corresponding general processing functions, and generate feature data through automated feature engineering.

[0034] The principle of field setting in step a is: the standard abstract data after adaptation includes three types ...

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 relates to a method for recommending system data abstraction and automation characteristic engineering. For recommending system data for any scene, only keywords and specified processingfunctions in fields generated after the recommendation system data are adapted need to be understood, universal data processing and feature engineering codes can be used for completing feature generation, and the method comprises the two steps of data abstraction, schema configuration for standard abstract data and corresponding universal processing function development. According to the method,the development workload of engineers is reduced, so that the engineers have more sufficient time and energy to perform model tuning work.

Description

technical field [0001] This patent application belongs to the technical field of recommendation systems, and more specifically relates to a method for data abstraction and automatic feature engineering of recommendation systems. Background technique [0002] At present, a case-by-case processing strategy is generally adopted for data processing and feature engineering. In the case-by-case strategy, the development process of a new recommendation scenario is as follows: [0003] (1) Developers communicate with Party A to clarify development scenarios and requirements, and understand available data and business meanings; [0004] (2) Developers perform data cleaning, feature engineering, and offline POC testing (repeat (2) based on test results); [0005] (3) The developer puts the algorithm model and corresponding features online, and conducts a small flow test (repeat (2) and (3) based on the test results); [0006] (4) Select the algorithm model and features to obtain the...

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): G06F8/10
CPCG06F8/10
Inventor 张发恩冯元吴腾虎
Owner 青岛创新奇智科技集团股份有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products