Smart contract configuration using unstructured data

Patent metadata

Field	Value
Publication number	US-2026017413-A1
Application number	US-202418769537-A
Country	US
Kind code	A1
Filing date	Jul 11, 2024
Priority date	Jul 11, 2024
Publication date	Jan 15, 2026
Grant date	—

Abstract

A system for configuring a smart contract may receive unstructured data and identifying, based on the unstructured data, an intent to perform a transfer of data. The system may then identify, based on the unstructured data, parameters associated with the transfer of data. The parameters may include an amount of data to be transferred, a transferee, and at least one condition associated with the transfer of data. The system may then retrieve identifier data from a storage module, the identifier data including a first unique identifier. The system may then send, to a Large Language Model (LLM) via a first prompt engine module and an LLM Application Programming Interface (API), a prompt based on the unstructured data and the identifier data. The system may then receive LLM output from the LLM, and based on the LLM output, configure a smart contract. The LLM may be an artificial intelligence model.

First claim

1 . A computer system for configuring a smart contract based on unstructured data, the computer system comprising:
a processor; a communications module coupled to the processor; a storage module coupled to the processor; and a memory coupled to the processor, the memory storing instructions that, when executed, configure the processor to:
receive unstructured data;
identify, based on the unstructured data, an intent to perform a transfer of data;
identify, based on the unstructured data, parameters associated with the transfer of data, the parameters including an amount of data to be transferred, a transferee, and at least one condition associated with the transfer of data;
retrieve identifier data from the storage module, the identifier data including a first unique identifier;
send, to a Large Language Model (LLM) via a first prompt engine module and an LLM Application Programming Interface (API), a prompt based on the unstructured data and the identifier data;
receive LLM output from the LLM; and
based on the LLM output, configure a smart contract.

2 . The computer system of claim 1 , wherein the processor is further caused to:
deploy the smart contract to a blockchain network.

3 . The computer system of claim 2 , wherein prior to deploying the smart contract, the processor is further caused to:
send, to a client device associated with the first unique identifier, a request for confirmation; and receive, from the client device, the confirmation.

4 . The computer system of claim 1 , wherein prior to configuring the smart contract, the processor is further caused to:
send, to a client device associated with the first unique identifier, a request for additional data; and receive, from the client device, the additional data,
wherein the smart contract is configured further based on the additional data.

5 . The computer system of claim 1 , wherein the identifier data further includes a second unique identifier, the second unique identifier being associated with the transferee.

6 . The computer system of claim 1 , wherein the unstructured data has been converted, using a speech recognition module, from an audio stream of data.

7 . The computer system of claim 1 , wherein identifying the intent to perform the transfer of data includes sending, via a second prompt engine module and the LLM API, the unstructured data to the LLM.

8 . The computer system of claim 1 , wherein identifying the intent to perform the transfer of data includes performing a keyword search of the unstructured data.

9 . The computer system of claim 1 , wherein identifying the parameters associated with the transfer of data includes sending, via a third prompt engine module and the LLM API, the unstructured data to the LLM.

10 . The computer system of claim 1 , wherein the at least one condition includes a triggering condition, and wherein the triggering condition is used to configure the smart contract.

11 . The computer system of claim 1 , wherein the at least one condition includes a condition to minimize an input-output modifier.

12 . The computer system of claim 1 , wherein configuring the smart contract includes configuring the smart contract using one or more further LLMs.

13 . The computer system of claim 12 , wherein configuring the smart contract using one or more further LLMs includes writing a smart contract using a second LLM and translating the written smart contract to a specific blockchain language using a third LLM.

14 . A computer-implemented method, the method comprising:
receiving unstructured data; identifying, based on the unstructured data, an intent to perform a transfer of data; identifying, based on the unstructured data, parameters associated with the transfer of data, the parameters including an amount of data to be transferred, a transferee, and at least one condition associated with the transfer of data; retrieving identifier data, the identifier data including a first unique identifier; sending, to an LLM via a first prompt engine module and an LLM API, a prompt based on the unstructured data and the identifier data; receiving LLM output from the LLM; and based on the LLM output, configuring a smart contract.

15 . The computer-implemented method of claim 14 , the method further comprising:
deploying the smart contract to a blockchain network.

16 . The computer-implemented method of claim 15 , wherein prior to deploying the smart contract, the method further comprises:
sending, to a client device associated with the first unique identifier, a request for confirmation; and receiving, from the client device, the confirmation.

17 . The computer-implemented method of claim 14 , wherein prior to configuring the smart contract, the method further comprises:
sending, to a client device associated with the first unique identifier, a request for additional data; and receiving, from the client device, the additional data,
wherein the smart contract is configured further based on the additional data.

18 . The computer-implemented method of claim 14 , wherein the identifier data further includes a second unique identifier, the second unique identifier being associated with the transferee.

19 . The computer-implemented method of claim 14 , wherein the unstructured data has been converted, using a speech recognition module, from an audio stream of data.

20 . (canceled)

21 . The computer system of claim 1 , wherein the LLM is a type of artificial intelligence model designed to understand and generate natural-language input.

Assignees

• Toronto Dominion Bank

Inventors

• Bajaj Hitesh
• Dunjic Milos
• Tax David Samuel
• Prendergast Jonathan Joseph
• Sharma Mohit
• Kelly Thomas Osman
• Gupta Pranay Chander
• Rastogi Kushank
• Singha Hazari Abhijit

Classifications

• G06F21/577

  Assessing vulnerabilities and evaluating computer system security · CPC title

• G06F16/90

  Details of database functions independent of the retrieved data types · CPC title

• G06F21/56

  Computer malware detection or handling, e.g. anti-virus arrangements · CPC title

• G06F16/2455

  Query execution · CPC title

• G06F16/285

  Clustering or classification · CPC title