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

An electronic contract handwritten signature authentication method based on twin neural networks

A handwritten signature, neural network technology, applied in biological neural network models, neural learning methods, neural architectures, etc., to ensure legal validity, save signing costs, and reduce losses.

Inactive Publication Date: 2019-03-01
成都优易数据有限公司
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0022] The purpose of the present invention is: in order to solve the existing third-party electronic contract platform, the parties to the contract need reliable third-party authentication when signing electronic signatures online, and only the certified electronic signatures have the same legal effect as handwritten signatures. The present invention provides a A method for identifying handwritten signatures of electronic contracts based on twin neural networks, which can realize the identification of handwritten signatures in electronic contract signing, and replace or improve electronic signatures with handwritten signatures

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
  • An electronic contract handwritten signature authentication method based on twin neural networks
  • An electronic contract handwritten signature authentication method based on twin neural networks

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0045] like figure 1 As shown, the principle of the twin neural network is: the twin neural network model is used to measure the similarity of two inputs, the twin neural network has two inputs Input1 and Input2, and the two inputs are respectively input into two neural networks Network1 and Network2, The two neural networks share the weight Weights, and map their respective inputs to a new space to form a representation of the input in the new space. Through the calculation of the loss function Loss Function, the similarity between two inputs is evaluated, that is, the distance.

[0046] like figure 2 As shown, the present embodiment provides a method for identifying a handwritten signature of an electronic contract based on a twin neural network, including the following steps:

[0047] S1: In the real-name authentication link, carry out several user handwritten signatures, and save several handwritten signatures as image files to form a training set;

[0048] S2: Randoml...

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 electronic contract handwritten signature authentication method based on twin neural networks, which relates to the technical field of electronic contract handwritten signature authentication. The invention comprises the following steps: S1, a plurality of user handwritten signatures are left behind in a real name authentication link, and the handwritten signatures are saved as image files; 2, selecting two of a plurality of handwritten signature image files and one of that non-user handwritten signature image file, inputting the two handwritten signature image filesinto a twin neural network model for vector calculation, obtaining a loss function, and obtaining a training set cost function through the loss function; 3, train other handwritten signature image files of that user through an optimization algorithm, and outputting an authentication model; S4: When signing on line, the handwritten signature on the touch screen input device is saved as an image immediately, the identification model is input, the identification result is output, and the preservation and the identification of the handwritten signature are completed. The invention can realize theidentification of the handwritten signature in the electronic contract signing, and the electronic signature is replaced or perfected by the handwritten signature.

Description

technical field [0001] The invention relates to the technical field of electronic contract handwritten signature identification, and more specifically relates to a method for electronic contract handwritten signature identification based on a twin neural network. Background technique [0002] The civil legal act of electronic contract is the legal act of two or more civil subjects. The purpose of establishing, changing, and terminating property civil rights and obligations between the parties is electronic. A new form of contract. The entire signing process is in electronic form, and electronic contracts are negotiated, signed and performed through e-mail, communication tools, etc. This contract method greatly saves transaction costs and improves economic benefits. [0003] Different from the conclusion of traditional contracts, the conclusion of electronic contracts takes place in a virtual space. The two parties to the transaction generally do not meet each other, and the...

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): G06K9/00G06N3/04G06N3/08G06Q50/18
CPCG06N3/08G06Q50/18G06V40/30G06N3/045
Inventor 李槛栖
Owner 成都优易数据有限公司
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