Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Customer portrait model modeling method, system and equipment based on artificial intelligence

A customer portrait and artificial intelligence technology, applied in the field of artificial intelligence-based customer portrait model modeling, can solve problems such as the inability to reach consensus on team views, easy to ignore users, and no way to determine the proportion of user groups

Pending Publication Date: 2021-07-30
上海悟景信息科技有限公司
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Primary user portraits, primary user portraits do not need to be obtained through research, because each team member has different assumptions about the main user, these messy assumptions often make the team's views inconsistent, and the results cannot be accurately applied to real users
[0005] Qualitative user personas, because they are not based on a large sample, there is no way to determine the proportion of the user group represented by each role, and due to the small sample size, it is easy to ignore some users with unique characteristics
[0006] Statistical profiling, the division of labor for statistical profiling is expensive, time-consuming, and requires expertise in statistical analysis

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
  • Customer portrait model modeling method, system and equipment based on artificial intelligence
  • Customer portrait model modeling method, system and equipment based on artificial intelligence
  • Customer portrait model modeling method, system and equipment based on artificial intelligence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] See figure 1 , figure 1 A flow chart of a method modeling method based on manually intelligent customer portrait model provided herein, including:

[0067] S1, extract the original characteristics after data collection of the acquired customer data;

[0068] First, by processing the collected customer data, automatically adapt to different data environments such as high quality, low quality, making data become a state of Ai-Ready, effectively enhances data utilization. After the necessary cleaning of the raw data, the pretreatment analysis can be used to extract meaningful attributes or features as the original feature. The original feature can be a user name, gender, height, hobby, shopping preferences, and habits.

[0069] Exemplary In this embodiment, the data finishing is included:

[0070] Lacking value fill: Data fill can be set according to the average number, median and the number, etc., can set different processing strategies.

[0071] Sampling: When the amount of ...

Embodiment 2

[0108] See figure 2 The present application provides an artificial intelligent customer portrait model modeling system, including:

[0109] Data finishing module 100 for data finishing of the acquired customer data, then extracts the original feature;

[0110] Feature Derivative Module 200, the characteristic derivative module 200 is used to construct a new feature from the original feature;

[0111] The feature selection module 300, the feature selection module 300 is used to select a larger feature of the business prediction target from the original feature and the new feature, to cluster analysis of the same type, and obtain the corresponding feature set;

[0112] Model training module 400, the model training module 400 is used to train models;

[0113] Model optimization module 500, the model optimization module 500 is used to optimize the model;

[0114] Model selection module 600, the model selection module 600 is used for model selection.

[0115] First, the data finishing ...

Embodiment 3

[0125] See image 3 The present application embodiment provides an electronic device comprising: at least one processor 1, at least one memory 2, and data bus 3; wherein the processor 1 and the memory 2 are completed by the data bus 3. Communication; The memory 2 stores a program instruction that can be performed by the processor 1, and the processor 1 calls the program instruction to perform the methods provided in the above embodiments. For example, including:

[0126] Extract the original characteristics after data collection of the acquired customer data;

[0127] Based on the original characteristics, new features are derived based on field type information and data statistics;

[0128] The characteristics of the service prediction target are selected from the original feature and the new feature, and the characteristics of the same type are clustering, and the corresponding feature set is obtained.

[0129] All feature sets as the training sample of the customer portrait mode...

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 provides a customer portrait model modeling method, system and equipment based on artificial intelligence, and belongs to the technical field of user portray.The customer portrait modeling method based on artificial intelligence mainly comprises the steps of data arrangement, feature derivation, feature selection, model training, model optimization and model selection. According to the method and the system for establishing the user portrait based on artificial intelligence, the electronic equipment and the computer readable storage medium, the accuracy of the user portrait can be effectively improved, so that a personalized intelligent recommendation system, precise marketing and precise advertising can be constructed, and the method and the system have good popularization and application values.

Description

Technical field [0001] The present application relates to the field of user portrait technology, and in particular, a customer portrait model modeling method, system, and equipment based on manual intelligence. Background technique [0002] With the development of Internet technology, financial institutions have become increasingly rich, and online has become the main source of business. The diversity and risk of guest groups are increasing, and the application of customer portraits is increasingly wide. [0003] The existing user portrait has three types: primary user portrait, qualitative user portrait, and statistic user portrait. [0004] The portrait of the primary user, the portrait of the primary user does not need to be investigated. Since each team member has different ideas for the primary user, these messy assumptions often make the team's views unable to agree, and the results cannot be accurately applicable to real users. [0005] Qualitative user portraits, because ...

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): G06Q30/02G06Q10/04
CPCG06Q30/0201G06Q10/04
Inventor 苏靖
Owner 上海悟景信息科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com