US-20260128904-A1 - BIOMETRIC-BASED CONSENT OF DIGITAL SIGNATURE

US20260128904A1US 20260128904 A1US20260128904 A1US 20260128904A1US-20260128904-A1

Abstract

An example operation may include receiving document content from a software application, including a digital document with a digital signature of a user embedded therein, dynamically determining a type of biometric to verify the user based on the document content, receiving biometric data of the type of biometric from a device of the user based on an input via the software application, identifying a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier, verifying the biometric data based on a comparison of the biometric data to the baseline biometric data and the digital signature based on the digital signature verification data, editing the digital document to indicate the digital document is validly signed. A portion of the example operation: integrates with, interacts with, is performed by an AI chatbot or an AI agent, and/or is associated with an AI model.

Inventors

Breena Patricia GORMLEY
Ana Isabel Almeida Pacheco

Assignees

THE TORONTO-DOMINION BANK

Dates

Publication Date: 20260507
Application Date: 20241101

Claims (20)

1 . An apparatus, comprising: a memory; and a processor communicatively coupled to the memory, the processor configured to: receive document content from a software application, the document content comprising a digital document with a digital signature of a user embedded therein, dynamically determine at least one type of biometric to be used to verify the user based on the document content, receive biometric data of the at least one type of biometric from a device of the user based on an input via the software application, identify a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier of the software application, verify the biometric data based on a comparison of the biometric data to the baseline biometric data and verify the digital signature based on the digital signature verification data, and in response to verification of the biometric data and the digital signature, edit the digital document to indicate the digital document is validly signed.
2 . The apparatus of claim 1 , wherein the processor is further configured to receive a request to view the digital document, determine that the request is from a different user that is not a party to the digital document, and in response, hide the digital signature and display the digital document with the digital signature hidden.
3 . The apparatus of claim 1 , wherein the processor is further configured to determine a type of the digital document based on document content within the digital document, determine the at least one type of biometric data to obtain based on the type of the digital document, and send a request to the software application with an identifier of the at least one type of biometric data to obtain prior to receiving the biometric data.
4 . The apparatus of claim 1 , wherein the digital document comprises different digital signatures of different users, respectively, and the processor is further configured to determine a type of the digital document, determine respective types of biometric data to be provided by each of the different users based on the type of the digital document, and transmit requests to different devices of the different users, respectively, with indicators of the respective types of biometric data to be provided, wherein an AI agent coordinates actions related to the biometric data.
5 . The apparatus of claim 1 , wherein the processor is configured to receive a geographic location of the device from the software application, and verify the geographic location of the device based on previous geographic locations of the device registered by the software application.
6 . The apparatus of claim 1 , wherein the processor is further configured to train an artificial intelligence (AI) model with neural network capability to determine a likelihood of a match between a biometric sample and a baseline biometric sample based on at least one of input biometric data samples, baseline biometric data samples matched with the input biometric data samples, and model feedback data, and execute the trained AI model on the biometric data and the baseline biometric data to generate a confidence score.
7 . The apparatus of claim 6 , wherein the processor is further configured to determine that the biometric data and the baseline biometric data are not identical but are within a threshold of similarity to be considered a match based on the confidence score generated by the AI model, and in response, add the biometric data and the confidence score as an additional biometric sample to a set of valid existing biometric samples related to the biometric data.
8 . A method comprising: receiving document content from a software application, the document content comprising a digital document with a digital signature of a user embedded therein; dynamically determining at least one type of biometric to be used to verify the user based on the document content; receiving biometric data of the at least one type of biometric from a device of the user based on an input via the software application; identifying a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier of the software application; verifying the biometric data based on a comparison of the biometric data to the baseline biometric data and verifying the digital signature based on the digital signature verification data; and in response to verifying the biometric data and the digital signature, editing the digital document to indicate the digital document is validly signed.
9 . The method of claim 8 , comprising receiving a request to view the digital document, determining that the request is from a different user that is not a party to the digital document, and in response, hiding the digital signature and displaying the digital document with the digital signature hidden.
10 . The method of claim 8 , comprising determining a type of the digital document based on document content within the digital document, determining the at least one type of biometric data to obtain based on the type of the digital document, and sending a request to the software application with an identifier of the at least one type of biometric data to obtain prior to receiving the biometric data.
11 . The method of claim 8 , wherein the digital document comprises different digital signatures of different users, respectively, and the method further comprises determining a type of the digital document, determining respective types of biometric data to be provided by each of the different users based on the type of the digital document, and transmitting requests to different devices of the different users, respectively, with indicators of the respective types of biometric data to be provided, wherein an AI agent coordinates actions related to the biometric data.
12 . The method of claim 8 , wherein the receiving further comprises receiving a geographic location of a device associated with the biometric data from the software application, and the verifying the digital signature further comprises verifying the geographic location of the device based on previous geographic locations of the device registered by the software application.
13 . The method of claim 8 , further comprising training an artificial intelligence (AI) model with neural network capability to determine a likelihood of a match between a biometric sample and a baseline biometric sample based on at least one of input biometric data samples, baseline biometric data samples matched with the input biometric data samples, and model feedback data, wherein the verifying comprises executing the trained AI model on the biometric data and the baseline biometric data to generate a confidence score.
14 . The method of claim 13 , comprising determining that the biometric data and the baseline biometric data are not identical but are within a threshold of similarity to be considered a match based on the confidence score generated by the AI model, and in response, adding the biometric data and the confidence score as an additional biometric sample to a set of valid existing biometric samples related to the biometric data.
15 . A computer-readable storage medium comprising instructions which when executed by a computer cause a processor to perform: receiving document content from a software application, the document content comprising a digital document with a digital signature of a user embedded therein; dynamically determining at least one type of biometric to be used to verify the user based on the document content; receiving biometric data of the at least one type of biometric from a device of the user based on an input via the software application; identifying a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier of the software application; verifying the biometric data based on a comparison of the biometric data to the baseline biometric data and verifying the digital signature based on the digital signature verification data; and in response to verifying the biometric data and the digital signature, editing the digital document to indicate the digital document is validly signed.
16 . The computer-readable storage medium of claim 15 , wherein the processor is further configured to perform receiving a request to view the digital document, determining that the request is from a different user that is not a party to the digital document, and in response, hiding the digital signature and displaying the digital document with the digital signature hidden.
17 . The computer-readable storage medium of claim 15 , wherein the processor is further configured to perform determining a type of the digital document based on document content within the digital document, determining the at least one type of biometric data to obtain based on the type of the digital document, and sending a request to the software application with an identifier of the at least one type of biometric data to obtain prior to receiving the biometric data.
18 . The computer-readable storage medium of claim 15 , wherein the digital document comprises different digital signatures of different users, respectively, and the processor is further configured to perform determining a type of the digital document, determining respective types of biometric data to be provided by each of the different users based on the type of the digital document, and transmitting requests to different devices of the different users, respectively, with indicators of the respective types of biometric data to be provided, wherein an AI agent coordinates actions related to the biometric data.
19 . The computer-readable storage medium of claim 15 , wherein the processor is further configured to perform training an artificial intelligence (AI) model with neural network capability to determine a likelihood of a match between a biometric sample and a baseline biometric sample based on at least one of input biometric data samples, baseline biometric data samples matched with the input biometric data samples, and model feedback data, wherein the verifying comprises executing the trained AI model on the biometric data and the baseline biometric data to generate a confidence score.
20 . The computer-readable storage medium of claim 19 , wherein the processor is further configured to perform determining that the biometric data and the baseline biometric data are not identical but are within a threshold of similarity to be considered a match based on the confidence score generated by the AI model, and in response, adding the biometric data and the confidence score as an additional biometric sample to a set of valid existing biometric samples related to the biometric data.

Description

BACKGROUND Digital signatures (also referred to as electronic signatures or e-signatures) are generally considered more secure than wet signatures. A digital signature added to a digital document may rely on encryption and cryptographic algorithms to secure electronically signed documents, guaranteeing their integrity, authenticity, and non-repudiation. These cryptographic techniques create a digital “fingerprint” of the document, making any alterations detectable, thus bolstering trust and confidence in digital transactions. However, a digital signature can be stolen through various means including phishing, hacking, manipulating, or otherwise stealing the digital signature. Once the digital signature is stolen, it can be used by the thief to forge the digital signature on documents such as deeds, purchases of sale, and the like. SUMMARY One example embodiment provides an apparatus that includes a memory communicatively coupled to a processor, wherein the processor may at least one of receive document content from a software application, the document content including a digital document with a digital signature of a user embedded therein, dynamically determine at least one type of biometric to be used to verify the user based on the document content, receive biometric data of the at least one type of biometric from a device of the user based on an input via the software application, identify a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier of the software application, verify the biometric data based on a comparison of the biometric data to the baseline biometric data and verify the digital signature based on the digital signature verification data, and in response to verification of the biometric data and the digital signature, edit the digital document to indicate the digital document is validly signed. Another example embodiment provides a method that includes at least one of receiving document content from a software application, the document content including a digital document with a digital signature of a user embedded therein, dynamically determining at least one type of biometric to verify the user based on the document content, receiving biometric data of the at least one type of biometric from a device of the user based on an input via the software application, identifying a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier of the software application, verifying the biometric data based on a comparison of the biometric data to the baseline biometric data and verifying the digital signature based on the digital signature verification data, and in response to verifying the biometric data and the digital signature, editing the digital document to indicate the digital document is validly signed. A further example embodiment provides a computer readable storage medium comprising instructions, that when read by a processor, cause the processor to perform at least one of receiving document content from a software application, the document content including a digital document with a digital signature of a user embedded therein, dynamically determining at least one type of biometric to verify the user based on the document content, receiving biometric data of the at least one type of biometric from a device of the user based on an input via the software application, identifying a baseline biometric data and digital signature verification data associated with the software application based on a unique identifier of the software application, verifying the biometric data based on a comparison of the biometric data to the baseline biometric data and verifying the digital signature based on the digital signature verification data, and in response to verifying the biometric data and the digital signature, editing the digital document to indicate the digital document is validly signed. Another example embodiment provides an apparatus that includes a memory communicatively coupled to a processor, wherein the processor may at least one of receive an authorization request message from a computer network, the authorization request message comprising details of a data transfer from a sender to a receiver, dynamically determine at least one type of biometric to be used to verify the sender based on the details of the data transfer, receive biometric data of the at least one type of biometric from the sender based on an input via a software application, obtain baseline biometric data of the sender from a database, verify an identity of the sender based on a comparison of the biometric data and the baseline biometric data, and in response to successful verification of the identity of the sender, modify the authorization request message to indicate the identity of the sender is verified, and transmit the modified authorization request message to a compu