User portrait label modeling method and device, electronic equipment and readable storage medium

A modeling method and labeling technology, applied in data processing applications, business, instruments, etc.

Pending Publication Date: 2019-06-25
BEIJING SANKUAI ONLINE TECH CO LTD
View PDF0 Cites 29 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The present invention provides a user portrait label modeling method, device, electronic equipment and readable storage medium to partially or completely solve the above-mentioned problems related to the user portrait label modeling process in the prior art

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
  • User portrait label modeling method and device, electronic equipment and readable storage medium
  • User portrait label modeling method and device, electronic equipment and readable storage medium
  • User portrait label modeling method and device, electronic equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0035] A user portrait label modeling method provided by an embodiment of the present invention is introduced in detail.

[0036] refer to figure 1 , shows a flow chart of steps of a method for modeling user portrait tags in an embodiment of the present invention.

[0037] In step 110, training sample data is obtained, and the training sample data includes portrait label sample data of a plurality of portrait labels and user feature sample data.

[0038] In the embodiment of the present invention, in order to solve the problems existing in the existing user portrait label modeling method, two improvements are mainly made. First, in order to solve the problem of insufficient samples when mining a single label, by fusing samples of multiple labels, the data is increased and expanded, so that the accuracy of the trained model is higher; second, a multi-task model is used to mine multiple users at the same time Portrait tags replace traditional multiple single-task models, there...

Embodiment 2

[0052] A user portrait label modeling method provided by an embodiment of the present invention is introduced in detail.

[0053] refer to figure 2 , shows a flow chart of steps of a method for modeling user portrait tags in an embodiment of the present invention.

[0054] Step 210, acquiring the portrait tag sample data based on the basic user data.

[0055] In the embodiment of the present invention, in order to determine the portrait label sample data of each user in the training sample data, the portrait label sample data of the corresponding user may first be obtained based on the user basic data. The user basic data may include encrypted ID card data, questionnaire data, telephone return visit data, user registration information data, etc. through the platform. Specifically, the specific content included in the basic user data can be preset according to requirements, which is not limited in this embodiment of the present invention.

[0056] For example, if the portra...

Embodiment 3

[0119] A user portrait label modeling device provided by an embodiment of the present invention is introduced in detail.

[0120] refer to Figure 4 , shows a schematic structural diagram of an apparatus for modeling user portrait tags in an embodiment of the present invention.

[0121] The training data collection module 310 is used to obtain training sample data; the training sample data includes portrait label sample data and user feature sample data of a plurality of portrait labels;

[0122] The label learning model training module 320 is used to train a preset training model according to the user feature sample data and the portrait label sample data to obtain a user portrait label learning model; wherein, the loss function of the preset training model is each A weighted sum of the loss functions for the portrait labels.

[0123] In the first aspect, according to the user portrait label modeling method of the present invention, training sample data can be obtained; the...

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 user portrait label modeling method and device, electronic equipment and a readable storage medium. The method comprises the steps of obtaining training sample data; Whereinthe training sample data comprises portrait label sample data of a plurality of portrait labels and user feature sample data; Training a preset training model according to the user feature sample dataand the portrait label sample data to obtain a user portrait label learning model; Wherein the loss function of the preset training model is determined based on the loss function of each portrait label. The technical problems that an existing user portrait label modeling method is not high in prediction accuracy and too large in development cost, calculation resource and maintenance cost are solved. The beneficial effects of improving the portrait label prediction accuracy and reducing the development and maintenance cost are achieved.

Description

technical field [0001] The present invention relates to the technical field of data mining, in particular to a user portrait label modeling method, device, electronic equipment and readable storage medium. Background technique [0002] Compared with traditional offline membership management and questionnaire surveys, big data technology enables companies to more conveniently obtain various information about users through the Internet, and understand users' behavioral habits and consumption habits more accurately. The user portrait obtained through big data mining can be applied in the precise marketing and targeted marketing activities of enterprises. Among them, user portrait refers to a tagged user model abstracted based on user attributes, user preferences, user behavior and other information. Tags are highly refined feature identifiers obtained through analysis of user information. The label development of user portraits generally uses methods such as statistical analys...

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): G06Q30/02G06Q30/00
Inventor 吕兵
Owner BEIJING SANKUAI ONLINE TECH 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