User identification method and system based on data burying points

A technology of user identification and identification system, which is applied in the field of user identification method and system based on data embedding, can solve the problems of low quality of user portraits, partial and complete portraits, and difficult collection of behavior data, so as to achieve accurate and efficient user portraits high effect

Pending Publication Date: 2022-04-29
ZHEJIANG LISHI TECH
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The difficulty of the existing technology is that it is difficult to collect user data and too little data will lead to problems such as low quality and too one-sided user portraits
At present, user portraits are mainly based on user basic attribute data, behavior data, transaction data and other information, but the behavior data is difficult to collect, and most of them only collect the basic behavior of users, such as registration time, source channel, order time and other information
And most user portraits do not involve contextual data, but users have different needs in different contexts. If contextual content is missing in user portraits, the portraits will be incomplete.

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 identification method and system based on data burying points
  • User identification method and system based on data burying points
  • User identification method and system based on data burying points

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0050] refer to figure 1 and 2 As shown, this embodiment provides a user identification method based on data buried points, including the following steps:

[0051] S1 initializes, standardizes the buried point data in the database, and stores the newly generated label data into the database;

[0052] S2 receives the rules of the user portrait model, and calculates the embedded point tag data in the database according to the rules, and obtains the user tag sample data;

[0053] S3 tests the user portrait model based on the sample data, and improves the model according to the inspection standard;

[0054] S4 builds a user identification system based on the model in S3, and displays various data of user portraits when user information needs to be obtained.

[0055] This embodiment further provides a data standardization process, standardizes the buried point data in the database according to the buried point label rules, and labels each buried point data of each user id with a c...

Embodiment 2

[0061] In terms of specific implementation, this embodiment provides a data standardization process on the basis of Embodiment 1, specifically as follows:

[0062] In this embodiment, the buried point database stores the buried point data entered according to the buried point design, and the buried point data field contains the unique identification field of each user—user id (ip address, micro signal, etc.), and the id is included in the program Information data such as all operation behaviors, operation objects, page addresses, operation creation time, equipment used, location, etc. Then create the buried point label rules through the data standardization process, the specific process is as follows image 3 shown.

[0063] In this embodiment, firstly, the professional person in charge formulates the buried point label specification including various detailed rules, and the specific content of each detailed rule. According to the actual situation, clearly stipulate the corr...

Embodiment 3

[0072] In terms of specific implementation, this embodiment provides a user portrait modeling process on the basis of Embodiment 1. The user portrait modeling process in this embodiment is the process of labeling users as users, and it is also the process of converting buried point labels into The process of user tagging. Can be divided into 4 categories:

[0073] Statistical labels in this embodiment: indicators obtained directly through statistical analysis of data. For example, according to the statistics of the number of "Avalokitesvara" tags, there are 3-5 tags that can be marked as "interested in Avalokitesvara", 6-10 tags that can be marked as "very interested in Avalokitesvara", and 10 or more of this tag can be marked as "very interested in Guanyin Bodhisattva".

[0074] In this embodiment, the rule-type tag: convert the buried point tag according to the business rule. If you have more than 20 history-related tags such as "Historical Articles", "Zhu Yuanzhang", and...

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 the technical field of user identification, in particular to a user identification method and system based on data burying points, and the method comprises the following steps: carrying out the standardization processing of burying point data in a database, and storing newly generated label data in the database; receiving a user portrait model rule, and calculating the buried point label data in the database according to the rule to obtain user label sample data; testing the user portrait model based on the sample data, and improving the model according to an inspection standard; and building a user identification system according to the model, and displaying various data of a user portrait when user information needs to be acquired. Relatively complex and abstract user behaviors and current situations are converted into quantifiable calculation formulas and applied to a database, data processing based on the formulas is achieved, the data has a unified index, efficiency is higher, business developers can obtain user information more efficiently, and the auxiliary effect on subsequent data analysis and decision making is achieved.

Description

technical field [0001] The invention relates to the technical field of user identification, in particular to a method and system for user identification based on data embedding. Background technique [0002] At present, the common user identification method on the Internet is to create user portraits for users. It usually needs to collect multi-dimensional data sources such as user attribute data, behavior data, context data, and commodity data, and index and label these data to establish a reasonable model. Data labeling system, and then continue to refine data labels into user labels according to business rules. Finally, assign user labels to corresponding users to generate user portraits. [0003] The difficulty of the existing technology is that it is difficult to collect user data and too little data will lead to problems such as low quality and one-sided user portraits. At present, user portraits are mainly based on user basic attribute data, behavior data, transacti...

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): G06F16/951G06F16/9535G06F16/9537
CPCG06F16/951G06F16/9535G06F16/9537
Inventor 郑楚琪陈海江
Owner ZHEJIANG LISHI TECH
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