Quasi-real-time label portrait construction method and system

A construction method and quasi-real-time technology, applied in market data collection, marketing, etc., can solve problems such as low acceptance, high cost, and dependence on personal experience, and achieve the effect of meeting label requirements, short construction cycle, and easy understanding

Pending Publication Date: 2022-05-13
CHINA SOUTHERN POWER GRID DIGITAL GRID RES INST CO LTD
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The main disadvantages of the existing technology are: training machine learning needs to collect and label enough training sample data, which is costly; the label construction cycle is long, and it cannot flexibly and quickly meet the labeling needs of business personnel; designing and training machine learning models requires high-quality Data research and development talents, model parameter debugging rely heavily on personal experience, talents are relatively scarce, and the threshold for technology development is high; the label results predicted by training machine learning models are difficult to interpret, and marketing personnel have difficulty understanding and accepting portrait label values.

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
  • Quasi-real-time label portrait construction method and system
  • Quasi-real-time label portrait construction method and system
  • Quasi-real-time label portrait construction method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0042] An embodiment of the present invention provides a method for constructing a quasi-real-time tag portrait. The method for constructing a quasi-real-time tag portrait is as follows: figure 1 As shown, specifically, the following steps may be included:

[0043] S101, acquiring user data;

[0044] In this embodiment, the original user data is specifically obtained from the data platform, and data cleaning is performed on the original user data to obtain standard user data.

[0045] As an example, the original user data may be a data set of multiple fields, including various aspects of a user's data, such as basic information data, historical behavior data, and the like.

[0046] More specifically, firstly, filter the original user data, delete invalid data and abnormal data in the original user data, and obtain effective standard user data; The duplicate data after duplicate checking is deleted to obtain the final standard user data.

[0047] S102, extract feature data f...

Embodiment 2

[0054] An embodiment of the present invention provides a system for constructing quasi-real-time tag portraits, such as figure 2 As shown, the construction system of the quasi-real-time label portrait can specifically include the following modules:

[0055] Obtaining module, used to obtain user data;

[0056]In this embodiment, the original user data is specifically obtained from the data platform, and data cleaning is performed on the original user data to obtain standard user data.

[0057] As an example, the original user data may be a data set of multiple fields, including various aspects of a user's data, such as basic information data, historical behavior data, and the like.

[0058] More specifically, firstly, filter the original user data, delete invalid data and abnormal data in the original user data, and obtain effective standard user data; The duplicate data after duplicate checking is deleted to obtain the final standard user data.

[0059] An extraction modul...

Embodiment 3

[0066] An embodiment of the present invention provides a device for constructing quasi-real-time label portraits, such as image 3 As shown, the construction equipment of the quasi-real-time label portrait can specifically include the following modules:

[0067] The communication bus is used to realize the connection and communication between the processor and the memory;

[0068] The memory is used to store computer programs; the memory may include a high-speed RAM memory, and may also include a non-volatile memory, such as at least one disk memory. The memory may optionally comprise at least one storage device.

[0069] A processor, configured to execute the above computer program to achieve the following steps:

[0070] First, get user data;

[0071] In this embodiment, the original user data is specifically obtained from the data platform, and data cleaning is performed on the original user data to obtain standard user data.

[0072] As an example, the original user da...

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 quasi-real-time label portrait construction method and system. The method comprises the following steps: obtaining user data; extracting feature data from the user data; and setting a tag portrait of the user according to the feature data. The method has the advantages of no need of training models and low cost; the label construction period is short, the label requirements of different persons can be flexibly and quickly met, the threshold is low, understanding is easy, and the acceptability is high.

Description

technical field [0001] The invention relates to the technical field of computer data processing, in particular to a method and system for constructing quasi-real-time label portraits. Background technique [0002] User portrait is a virtual representative of real users and a target user model based on a series of real data. Through user research to understand users, according to differences in their goals, behaviors and opinions, they are divided into different types, and then typical features are extracted from each type, and descriptions such as names, photos, some demographic elements, and scenes are given , forming a character prototype. In other words, user portrait is a tagged user model abstracted based on information such as user social attributes, living habits, and consumption behavior. [0003] The core work of constructing user portraits is to put "labels" on users, and labels are highly refined feature identifications obtained through the analysis of user info...

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): G06Q30/02
CPCG06Q30/0201
Inventor 萧展辉孙刚邹文景
Owner CHINA SOUTHERN POWER GRID DIGITAL GRID RES INST CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap