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

Internet credit evaluation method and system

An Internet and post-evaluation technology, applied in the field of communication, can solve problems such as low accuracy, poor application effect, and unreasonable Internet credit evaluation, and achieve the effect of improving application effect, rationality and accuracy

Pending Publication Date: 2018-09-14
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] During the research and practice of the existing technology, the inventor of the present invention found that the existing Internet credit evaluation is not reasonable enough, the accuracy is not high, resulting in poor application effect

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
  • Internet credit evaluation method and system
  • Internet credit evaluation method and system
  • Internet credit evaluation method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0033] This embodiment will be described from the perspective of an Internet credit evaluation system. The Internet credit evaluation system may specifically be integrated in a server, such as an evaluation server and other devices.

[0034] An Internet credit investigation evaluation method, comprising: obtaining a plurality of user data, selecting training samples from the user data to obtain a training data set, setting weights for each training sample in the training data set according to a preset strategy, and obtaining a weighted The training data set uses the weighted training data set to train the preset evaluation model to obtain the post-training evaluation model, and evaluates the user's Internet credit information based on the post-training evaluation model.

[0035] like Figure 1b As shown, the specific process of the Internet credit evaluation method can be as follows:

[0036] 101. Obtain multiple user data.

[0037] Wherein, the user data may include data su...

Embodiment 2

[0102] According to the method described in Embodiment 1, an example will be given below for further detailed description.

[0103] In this embodiment, it will be described by taking that the Internet credit evaluation system is specifically integrated in the evaluation server and the loss function is defined by the mean square error as an example.

[0104] like figure 2 As shown, an Internet credit evaluation method, the specific process can be as follows:

[0105] 201. The evaluation server acquires multiple pieces of user data.

[0106] For example, multiple user data can be collected from the Internet or other channels, and then stored locally or on other storage devices, and when needed, the evaluation server can read from the local or other storage devices; or, it can also be used by The evaluation server directly collects the user data from the Internet or other channels, and so on.

[0107] Wherein, the user data may include data such as user attribute data, behavi...

Embodiment 3

[0168] In order to better implement the above method, an embodiment of the present invention further provides an Internet credit evaluation system, and the Internet credit evaluation system may specifically be integrated in a server, such as an evaluation server and other devices.

[0169] like Figure 3a As shown, the Internet credit evaluation system includes an acquisition unit 301, a selection unit 302, a setting unit 303, a training unit 304 and an evaluation unit 305, as follows:

[0170] (1) acquisition unit 301;

[0171] The obtaining unit 301 is configured to obtain a plurality of user data, the user data including user attribute data, behavior data and credit records.

[0172] Among them, the user's attribute data may include the user's registration on the platform or user information obtained from other channels, such as the user's gender, age, region, and / or educational background and other demographic attribute information; the user's behavior data may include th...

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 an Internet credit evaluation method and system. According to the method, after a training data set is acquired, weights can be respectively set for each training sample in thetraining data set according to the preset strategy, secondly, a preset evaluation model is trained through utilizing the weighted training data set to acquire a post-training evaluation model, basedon the post-training evaluation model, the user Internet credit is evaluated. The Internet credit evaluation method is advantaged in that rationality and accuracy of evaluation can be greatly improved, and the application performance is improved.

Description

technical field [0001] The invention relates to the field of communication technology, in particular to an Internet credit evaluation method and system. Background technique [0002] With the advent of the era of big data, the application of Internet credit information is becoming more and more extensive. In addition to being applied to Internet finance, it can also cover other life scenarios, such as taxis, car rentals, or hotel reservations. Therefore, How to ensure the accuracy and fairness of Internet credit evaluation has gradually become a concern of people. [0003] In the existing technology, it is generally possible to collect user behavior data during the training period as a training data set, and then extract user features from it, and use machine learning algorithms such as decision trees and logistic regression to establish a credit scoring model, and based on The credit scoring model evaluates the user's creditworthiness. Among them, the training data set is...

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): G06Q10/06
CPCG06Q10/06375G06Q10/06G06F16/00
Inventor 黎新
Owner TENCENT TECH (SHENZHEN) CO LTD
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