Search

US-20260127235-A1 - ARTIFICIAL INTELLIGENCE BASED (AI-BASED) SYSTEM AND METHOD FOR MANAGING DIGITAL CONTRACT CODES IN A BLOCKCHAIN ECOSYSTEM

US20260127235A1US 20260127235 A1US20260127235 A1US 20260127235A1US-20260127235-A1

Abstract

An AI-based system and method for managing digital contract codes in a blockchain ecosystem, is disclosed. The AI-based method includes receiving data from data sources, pre-processing data to generate pre-processed data, extracting semantic information to determine requirements and objectives based on the pre-processed data, using an AI model, generating the digital contract codes based on the determined requirements and objectives, using the AI model, analyzing digital contract codes to identify static properties of digital contract codes, for determining vulnerabilities and issues within the digital contract codes, segregating the digital contract codes into steps indicating characteristics of digital contract codes, processing prompts associated with tasks related to the digital contract codes to generate responses for each auditing process, using the AI model, generating audit reports based on a combination of responses, and providing the audit reports, as an output, through user interfaces associated with communication devices of the users.

Inventors

  • Ilan Rakhmanov

Assignees

  • ChainGPT LLC

Dates

Publication Date
20260507
Application Date
20250602

Claims (20)

  1. 1 . An artificial intelligence based (AI-based) method for managing one or more digital contract codes in a blockchain ecosystem, the AI-based method comprising: receiving, by one or more hardware processors, data associated with at least one of: one or more parameters, one or more requirements, and one or more specifications, of the one or more digital contract codes to be generated, from one or more data sources; pre-processing, by the one or more hardware processors, the data to generate pre-processed data, wherein pre-processing the data comprises at least one of: tokenization, natural language parsing, and cleaning, of the data, to make the data in an optimized format for a digital contract code process; extracting, by the one or more hardware processors, semantic information associated with at least one of: an underlying meaning, intent, and relevant details, of the one or more digital contract codes, to determine one or more requirements and objectives of at least one of: one or more users and one or more external sources, in a context of the one or more digital contract codes, based on the pre-processed data, using an AI model; generating, by the one or more hardware processors, the one or more digital contract codes based on the determined one or more requirements and objectives of one or more users and one or more external sources, using the AI model; analyzing, by the one or more hardware processors, the one or more digital contract codes to identify one or more static properties comprising control flow and structure, of the one or more digital contract codes, for determining one or more vulnerabilities and issues within the one or more digital contract codes, using one or more predefined models; segregating, by the one or more hardware processors, the one or more digital contract codes into one or more steps indicating one or more characteristics of the one or more digital contract codes; generating, by the one or more hardware processors, one or more tasks for each step of one or more auditing processes, based on at least one of: the one or more characteristics of the one or more digital contract codes and the one or more vulnerabilities within the one or more digital contract codes; processing, by the one or more hardware processors, one or more prompts associated with the one or more tasks related to the one or more digital contract codes to generate one or more responses for each auditing process, using the AI model; generating, by the one or more hardware processors, one or more audit reports based on a combination of the one or more responses generated for each auditing process, wherein the one or more audit reports comprise at least one of: a summary of one or more contract structures and purposes, one or more details of at least one of: the one or more vulnerabilities and issues found within the one or more digital contract codes, one or more recommendations for addressing identified problems, and compliance with security standards and optimized practices; and providing, by the one or more hardware processors, the one or more audit reports, as an output, through one or more user interfaces associated with one or more communication devices of the one or more users.
  2. 2 . The AI-based method of claim 1 , further comprising: extracting, by the one or more hardware processors, the one or more requirements and objectives of at least one of: the one or more users and the one or more external sources, from the semantic information; identifying, by the one or more hardware processors, at least one of: one or more actions, one or more commands, and one or more conditions implied by the data, for determining one or more actions to be performed by the one or more digital contract codes; and generating, by the one or more hardware processors, the one or more digital contract codes based on the one or more requirements and objectives.
  3. 3 . The AI-based method of claim 1 , further comprising optimizing, by the one or more hardware processors, the one or more digital contract codes using one or more tasks comprising at least one of: gas cost reduction, elimination of redundant functions, implementation of code patterns optimizing an execution speed of the one or more digital contract codes, wherein optimizing the one or more digital contract codes allows an AI-based system to at least one of: meet the one or more requirements and objectives of at least one of: the one or more users and the one or more external sources, and execute optimally on a selected blockchain network.
  4. 4 . The AI-based method of claim 1 , further comprising validating, by the one or more hardware processors, the one or more digital contract codes to identify at least one of: the one or more vulnerabilities, one or more errors, and one or more security risks, for determining whether the one or more digital contract codes are compliance with at least one of: coding standards, security protocols, and blockchain-based optimized practices, by performing at least one of: comprehensive static analysis and automated testing procedures.
  5. 5 . The AI-based method of claim 1 , wherein pre-processing the data comprises: collecting, by the one or more hardware processors, the data from a data receiving subsystem; structuring, by the one or more hardware processors, the collected data with optimized format; and generating, by the one or more hardware processors, one or more prompts against the structured data.
  6. 6 . The AI-based method of claim 1 , further comprising training, by the one or more hardware processors, the AI model, by: obtaining, by the one or more hardware processors, one or more training datasets comprising the structured data in form of at least one of: smart contracts code, book chapters, solidity documentation, use cases, and blockchain related information; and training, by the one or more hardware processors, the AI model for generating the one or more digital contract codes, by: processing, by the one or more hardware processors, the structured data in form of at least one of: texts and images to convert into one or more tokens; mapping, by the one or more hardware processors, the one or more tokens to one or more identifiers; preparing, by the one or more hardware processors, the structured data for one or more subsequent tasks comprising at least one of: embedding and attention; and training, by the one or more hardware processors, the AI model with tokenized datasets comprising a number of tokens for generating the one or more digital contract codes.
  7. 7 . The AI-based method of claim 6 , further comprising: generating, by the one or more hardware processors, descriptions for each data points associated with the structured data, using a Blackbox model; processing, by the one or more hardware processors, at least one of: the structured data comprising the descriptions with smart contracts, to determine quality and relevance of the one or more digital contract codes; determining, by the one or more hardware processors, whether the descriptions comprising one or more aspects of the smart contracts, wherein the smart contracts comprise at least one of: interfaces, functions, and logic, associated with the one or more digital contract codes; determining, by the one or more hardware processors, whether the one or more digital contract codes for at least one of: a compilation process and an error checking process; and sending, by the one or more hardware processors, the one or more digital contract codes for fine-tuning the AI model.
  8. 8 . The AI-based method of claim 7 , further comprising fine-tuning, by the one or more hardware processors, the AI model with the one or more digital contract codes, to optimize the performance of the AI model, using a feedback loop, by: assessing, by the one or more hardware processors, the one or more digital contract codes for one or more feedback on the compilation of the one or more digital contract codes by a Text-to-Code large language model (LLM); generating, by the one or more hardware processors, the one or more responses upon successful compilation of the one or more digital contract codes; and updating, by the one or more hardware processors, the AI model to generate one or more embeddings until the AI model generates the one or more responses.
  9. 9 . An artificial intelligence based (AI-based) system for managing one or more digital contract codes in a blockchain ecosystem, the AI-based system comprising: one or more hardware processors; a memory coupled to the one or more hardware processors, wherein the memory comprises a plurality of subsystems in form of programmable instructions executable by the one or more hardware processors, and wherein the plurality of subsystems comprises: a data receiving subsystem configured to receive data associated with at least one of: one or more parameters, one or more requirements, and one or more specifications, of the one or more digital contract codes to be generated, from one or more data sources; a data pre-processing subsystem configured to pre-process the data to generate pre-processed data, wherein pre-processing the data comprises at least one of: tokenization, natural language parsing, and cleaning, of the data, to make the data in an optimized format for a digital contract code process; a semantic analysis subsystem configured to extract semantic information associated with least one of: an underlying meaning, intent, and relevant details, of the one or more digital contract codes, to determine one or more requirements and objectives of at least one of: one or more users and one or more external sources, in a context of the one or more digital contract codes, based on the pre-processed data, using an AI model; a solidity code generating subsystem configured to generate the one or more digital contract codes based on the determined one or more requirements and objectives of one or more users and one or more external sources, using the AI model; a contract code analysis subsystem configured to analyze the one or more digital contract codes to identify one or more static properties comprising control flow and structure, of the one or more digital contract codes, for determining one or more vulnerabilities and issues within the one or more digital contract codes, using one or more predefined models; a task decomposition subsystem configured to: segregate the one or more digital contract codes into one or more steps indicating one or more characteristics of the one or more digital contract codes; and generate one or more tasks for each step of one or more auditing processes, based on at least one of: the one or more characteristics of the one or more digital contract codes and the one or more vulnerabilities within the one or more digital contract codes; a contract code processing subsystem configured to process one or more prompts associated with the one or more tasks related to the one or more digital contract codes to generate one or more responses for each auditing process, using the AI model; a report generating subsystem configured to: generate one or more audit reports based on a combination of the one or more responses generated for each auditing process, wherein the one or more audit reports comprise at least one of: a summary of one or more contract structures and purposes, one or more details of at least one of: the one or more vulnerabilities and issues found within the one or more digital contract codes, one or more recommendations for addressing identified problems, and compliance with security standards and optimized practices; and provide the one or more audit reports, as an output, through one or more user interfaces associated with one or more communication devices of the one or more users.
  10. 10 . The AI-based system of claim 9 , further comprising an intent extraction subsystem configured to: extract the one or more requirements and objectives of at least one of: the one or more users and the one or more external sources, from the semantic information; identify at least one of: one or more actions, one or more commands, and one or more conditions implied by the data, for determining one or more actions to be performed by the one or more digital contract codes; and generate the one or more digital contract codes based on the one or more requirements and objectives.
  11. 11 . The AI-based system of claim 9 , further comprising a code optimization subsystem configured to optimize the one or more digital contract codes using one or more tasks comprising at least one of: gas cost reduction, elimination of redundant functions, implementation of code patterns optimizing an execution speed of the one or more digital contract codes, wherein optimizing the one or more digital contract codes allows an AI-based system to at least one of: meet the one or more requirements and objectives of at least one of: the one or more users and the one or more external sources, and execute optimally on a selected blockchain network.
  12. 12 . The AI-based system of claim 9 , further comprising a code verification subsystem configured to validate the one or more digital contract codes to identify at least one of: the one or more vulnerabilities, one or more errors, and one or more security risks, for determining whether the one or more digital contract codes are compliance with at least one of: coding standards, security protocols, and blockchain-based optimized practices, by performing at least one of: comprehensive static analysis and automated testing procedures.
  13. 13 . The AI-based system of claim 9 , wherein the data pre-processing subsystem is configured to: collect the data from a data receiving subsystem; structure the collected data with optimized format; and generate one or more prompts against the structured data.
  14. 14 . The AI-based system of claim 9 , further comprising a data training subsystem configured to train the AI model, by: obtaining one or more training datasets comprising the structured data in form of at least one of: smart contracts code, book chapters, solidity documentation, use cases, and blockchain related information; training the AI model for generating the one or more digital contract codes, by: processing the structured data in form of at least one of: texts and images to convert into one or more tokens; mapping the one or more tokens to one or more identifiers; preparing the structured data for one or more subsequent tasks comprising at least one of: embedding and attention; and training the AI model with tokenized datasets comprising a number of tokens for generating the one or more digital contract codes.
  15. 15 . The AI-based system of claim 14 , wherein the data training subsystem is further configured to: generate descriptions for each data points associated with the structured data, using a Blackbox model; process at least one of: the structured data comprising the descriptions with smart contracts, to determine quality and relevance of the one or more digital contract codes; determine whether the descriptions comprising one or more aspects of the smart contracts, wherein the smart contracts comprise at least one of: interfaces, functions, and logic, associated with the one or more digital contract codes; determine whether the one or more digital contract codes for at least one of: a compilation process and an error checking process; and sending the one or more digital contract codes for fine-tuning the AI model.
  16. 16 . The AI-based system of claim 15 , wherein the data training subsystem is further configured to: fine-tune the AI model with the one or more digital contract codes, to optimize the performance of the AI model, using a feedback loop, by; assess the one or more digital contract codes for one or more feedback on the compilation of the one or more digital contract codes by a Text-to-Code large language model (LLM); generate the one or more responses upon successful compilation of the one or more digital contract codes; and update the AI model to generate one or more embeddings until the AI model generates the one or more responses.
  17. 17 . A non-transitory computer-readable storage medium having instructions stored therein that when executed by one or more hardware processors, cause the one or more hardware processors to execute operations of: receiving data associated with at least one of: one or more parameters, one or more requirements, and one or more specifications, of the one or more digital contract codes to be generated, from one or more data sources; pre-processing the data to generate pre-processed data, wherein pre-processing the data comprises at least one of: tokenization, natural language parsing, and cleaning, of the data, to make the data in an optimized format for a digital contract code process; extracting semantic information associated with least one of: an underlying meaning, intent, and relevant details, of the one or more digital contract codes, to determine one or more requirements and objectives of at least one of: one or more users and one or more external sources, in a context of the one or more digital contract codes, based on the pre-processed data, using an AI model; generating the one or more digital contract codes based on the determined one or more requirements and objectives of one or more users and one or more external sources, using the AI model; analyzing the one or more digital contract codes to identify one or more static properties comprising control flow and structure, of the one or more digital contract codes, for determining one or more vulnerabilities and issues within the one or more digital contract codes, using one or more predefined models; segregating the one or more digital contract codes into one or more steps indicating one or more characteristics of the one or more digital contract codes; generating one or more tasks for each step of one or more auditing processes, based on at least one of: the one or more characteristics of the one or more digital contract codes and the one or more vulnerabilities within the one or more digital contract codes; processing one or more prompts associated with the one or more tasks related to the one or more digital contract codes to generate one or more responses for each auditing process, using the AI model; generating one or more audit reports based on a combination of the one or more responses generated for each auditing process, wherein the one or more audit reports comprise at least one of: a summary of one or more contract structures and purposes, one or more details of at least one of: the one or more vulnerabilities and issues found within the one or more digital contract codes, one or more recommendations for addressing identified problems, and compliance with security standards and optimized practices; and providing the one or more audit reports, as an output, through one or more user interfaces associated with one or more communication devices of the one or more users.
  18. 18 . The non-transitory computer-readable storage medium of claim 17 , further comprising training the AI model, by: obtaining one or more training datasets comprising the structured data in form of at least one of: smart contracts code, book chapters, solidity documentation, use cases, and blockchain related information; training the AI model for generating the one or more digital contract codes, by: processing the structured data in form of at least one of: texts and images to convert into one or more tokens; mapping the one or more tokens to one or more identifiers; preparing the structured data for one or more subsequent tasks comprising at least one of: embedding and attention; and training the AI model with tokenized datasets comprising a number of tokens for generating the one or more digital contract codes.
  19. 19 . The non-transitory computer-readable storage medium of claim 18 , further comprising: generating descriptions for each data points associated with the structured data, using a Blackbox model; processing at least one of: the structured data comprising the descriptions with smart contracts, to determine quality and relevance of the one or more digital contract codes; determining whether the descriptions comprising one or more aspects of the smart contracts, wherein the smart contracts comprise at least one of: interfaces, functions, and logic, associated with the one or more digital contract codes; determining whether the one or more digital contract codes for at least one of: a compilation process and an error checking process; and sending the one or more digital contract codes for fine-tuning the AI model.
  20. 20 . The non-transitory computer-readable storage medium of claim 19 , further comprising fine-tuning the AI model with the one or more digital contract codes, to optimize the performance of the AI model, using a feedback loop, by; assessing the one or more digital contract codes for one or more feedback on the compilation of the one or more digital contract codes by a Text-to-Code large language model (LLM); generating the one or more responses upon successful compilation of the one or more digital contract codes; and updating the AI model to generate one or more embeddings until the AI model generates the one or more responses.

Description

CROSS REFERENCE TO RELATED APPLICATION(S) This Application is a continuation of a non-provisional patent application filed in the US having Ser. No. 18/939,662 , filed on Nov. 7, 2024, titled “ARTIFICIAL INTELLIGENCE BASED (AI-BASED) SYSTEM AND METHOD FOR GENERATING NEWS ARTICLES IN A BLOCKCHAIN ECOSYSTEM”. TECHNICAL FIELD Embodiments of the present disclosure relate to blockchain technology, and more particularly relate to an artificial intelligence based (AI-based) system for managing one or more digital contract codes in multi-faceted blockchain ecosystem by leveraging artificial intelligence (AI) and data analysis techniques to streamline processes, improve security, and make blockchain technology more accessible to a diverse user base. BACKGROUND Blockchain technology has gained significant prominence as a decentralized and secure digital ledger system. The blockchain technology underpins various applications, including news aggregation, cryptocurrencies, digital contracts, non-fungible tokens (NFTs), and decentralized finance (DeFi). The distributed nature of blockchain technology ensures transparency and trust among participants, making blockchain technology a cornerstone of innovation in numerous industries. Despite the considerable potential of blockchain technology, it presents challenges for mainstream adoption. For instance, digital contract development demands proficiency in blockchain-specific languages like Solidity, creating a barrier to entry for non-developers and impeding the swift deployment of blockchain solutions. Furthermore, ensuring the security and integrity of digital contracts is of paramount importance, as vulnerabilities result in severe and catastrophic consequences. Additionally, the realm of cryptocurrency landscapes is characterized by instability and complexity, creating hurdles for both investors and enthusiasts seeking to navigate this cryptocurrency landscape. While the cryptocurrency landscape is vital to stay informed about cryptocurrency trends and market data, accomplishing this often requires a significant investment of time and expertise. Moreover, the rise of NFTs has brought about a new and distinctive digital asset category. However, the creation and management of NFTs generally entail proficiency in coding and a deep understanding of blockchain technology. In addition to the challenges in blockchain technology and cryptocurrency management, staying up to date with the rapidly evolving world of blockchain technology and digital currencies is crucial for informed decision-making. The proliferation of news and information on the internet overwhelms individuals seeking reliable and relevant updates on blockchain, cryptocurrencies, and related technologies. There are various technical problems with blockchain technology in the prior art. These technical problems encompass complexities related to digital contract development, which demand expertise in blockchain-specific languages and pose barriers for non-developers. Additionally, the security and integrity of digital contracts present ongoing concerns, as vulnerabilities have severe consequences. The cryptocurrency landscape is marked by volatility and intricacies, making it challenging for investors and enthusiasts to navigate and stay informed about market trends. Moreover, the emergence of NFTs has introduced a unique digital asset class, but the process of creating and managing NFTs typically involves specialized coding skills and blockchain knowledge. Therefore, there is a need for a system to address the aforementioned issues by providing an AI-based system and method to streamline blockchain processes, enhance security, simplify digital contract development (i.e., generating and auditing of digital contract codes), automate NFT management, offer insights into cryptocurrency trends, and facilitate efficient news aggregation. SUMMARY This summary is provided to introduce a selection of concepts, in a simple manner, which is further described in the detailed description of the disclosure. This summary is neither intended to identify key or essential inventive concepts of the subject matter nor to determine the scope of the disclosure. In accordance with an embodiment of the present disclosure, an artificial intelligence based (AI-based) method for managing one or more digital contract codes in a blockchain ecosystem, is disclosed. The AI-based method includes receiving, by one or more hardware processors, data associated with at least one of: one or more parameters, one or more requirements, and one or more specifications, of the one or more digital contract codes to be generated, from one or more data sources. The AI-based method further includes pre-processing, by the one or more hardware processors, the data to generate pre-processed data, wherein pre-processing the data comprises at least one of: tokenization, natural language parsing, and cleaning, of the data, to make the data in an optimized format for