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

Address validity classifier training and verification methods and related apparatuses

An effective and classifier technology, applied in the fields of instruments, digital data processing, buying and selling/lease transactions, etc., can solve the problems of seller loss, low verification efficiency, reduction of goods inventory, etc., to reduce manual intervention operations and improve verification. efficiency, the effect of improving efficiency

Inactive Publication Date: 2018-09-07
CAINIAO SMART LOGISTICS HLDG LTD
View PDF8 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Some malicious buyers fill in abnormal address information and phone number when placing an order, so that the seller cannot deliver normally, or, after delivery, due to abnormal address information or phone number, they cannot deliver or sign for delivery, and then use the loopholes in the rules of the online platform to complain and blackmail , leading to the loss of seller's capital, this loss is not only postage, but also the inventory of goods may be reduced
[0004] Of course, there are also some normal buyers who lack accurate knowledge of the address and fill in wrong address information, which will also bring losses to the seller.
[0005] At present, for abnormal and wrong address information, it basically depends on the seller's discovery, the logistics company's feedback, and the operator's screening. This method of manual intervention for verification is not only inefficient, but also error-prone. The cost of implementation in such environments is very large, making it unaffordable

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
  • Address validity classifier training and verification methods and related apparatuses
  • Address validity classifier training and verification methods and related apparatuses
  • Address validity classifier training and verification methods and related apparatuses

Examples

Experimental program
Comparison scheme
Effect test

example 2

[0258] Example 2 includes the method described in Example 1, wherein the step of generating address feature information according to the address information includes: mapping the address information into address elements of various levels; converting the address elements into address feature information .

example 3

[0259] Example 3 includes the method described in Example 2, wherein the address information includes address information in the order data; the step of generating address feature information according to the address information further includes: collecting statistics from the order data corresponding to the address information The transaction behavior data; set the transaction behavior data as address characteristic information; wherein, the transaction behavior data includes one or more of the following: the number of orders, the number of successful order transactions, the number of failed order transactions, the The number of successful sign-in for address information, and the number of failed sign-in for the address information.

example 4

[0260] Example 4 includes the method described in Example 2, wherein the step of generating address feature information according to the address information further includes: extracting extended address information from the address information; setting the extended address information as address feature information ; Wherein, the extended address information includes one or more of the following: the richness of the address information, the text length of address elements of a specified level, and urban and rural information.

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

Embodiments of the invention provide address validity classifier training and verification methods and related apparatuses. The address validity classifier training method comprises the steps of obtaining address information; according to the address information, generating address feature information; marking a validity tag for the address information; and by taking the address feature information and the validity tag as training samples, training an address validity classifier. Based on a classification thought, the address information is classified by the address validity classifier, the validity of the address information is identified, the valid and invalid address information is distinguished, and automatic verification of address information validity is realized, so that the manualintervention operation is greatly reduced, the verification efficiency and accuracy are improved, the cost is reduced, and implementation in environments such as massive transaction platforms is ensured.

Description

technical field [0001] This application relates to the technical field of computer processing, in particular to a training method for address validity classifiers, a training device for address validity classifiers, a verification method for address validity, and a verification method for address validity apparatus, an apparatus, and one or more computer-readable media. Background technique [0002] With the rapid development of the Internet, more and more consumers conduct transactions on online platforms, for example, shop on online shopping platforms. [0003] Some malicious buyers fill in abnormal address information and phone number when placing an order, so that the seller cannot deliver normally, or, after delivery, due to abnormal address information or phone number, they cannot deliver or sign for delivery, and then use the loopholes in the rules of the online platform to complain and blackmail , Leading to the loss of the seller's capital, this loss is not only th...

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): G06F17/30G06F17/27G06Q30/06
CPCG06Q30/0635G06F40/289
Inventor 郑恒王国印
Owner CAINIAO SMART LOGISTICS HLDG 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