A data integrity verification method and system applied to intelligent platforms

Abstract

This invention provides a data integrity verification method and system for intelligent platforms. The method includes: storing data on a blockchain and connecting each data block node using a circular linked list; optimizing data imbalance during data preprocessing using a multi-branch path tree balancing method; verifying data integrity using blockchain's hash algorithm and digital signature technology; recording parameter update processes on the blockchain and managing different versions of parameters using a circular linked list during AI model training; and recording inference requests and results on the blockchain during the inference phase, tracking inference task relationships using a circular linked list and a multi-branch path tree, and verifying the correctness of the inference results through blockchain data and an integrity verification scheme, while simultaneously optimizing inference path performance. The system includes corresponding modules or components to implement the above method. This invention combines the advantages of blockchain, circular linked lists, and multi-branch path trees to optimize the data integrity verification process, improve the performance and stability of AI model training and inference, and is of great significance to the development of artificial intelligence technology.

Description

Technical Field

[0001] This application relates to the field of network security technology, and in particular to a data integrity verification method and system applied to intelligent platforms. Background Technology

[0002] For intelligent platforms, the integrity of the data required for AI model training and inference is crucial. Traditional cloud storage data integrity verification is prone to imbalance due to multiple dynamic data operations, resulting in high time costs and low verification efficiency. Optimizing balancing methods for imbalanced states has become a pressing issue for intelligent platforms.

[0003] Therefore, there is an urgent need for a targeted data integrity verification method and system for intelligent platforms. Summary of the Invention

[0004] The purpose of this invention is to provide a data integrity verification method and system for intelligent platforms. By optimizing the data structure and verification process, the efficiency of data integrity verification for AI models on intelligent platforms is improved, while the data path tree structure is balanced to enhance the training and derivation effects of AI models.

[0005] Firstly, this application provides a data integrity verification method applied to an intelligent platform, the method comprising:

[0006] Data is stored on the blockchain, taking advantage of the distributed storage characteristics of the blockchain. Each data block is stored at a node on the blockchain, and these nodes are connected by a circular linked list.

[0007] When performing preprocessing operations such as data cleaning and normalization, the balancing method of multi-branch path trees is used to treat the data imbalance that occurs during the data preprocessing process as a path tree structure under imbalance, and optimize and balance it.

[0008] By utilizing blockchain's hash algorithm and digital signature technology, the integrity of the data used by the AI ​​model is verified.

[0009] Optimize the AI ​​model training process, including: recording the update process of model parameters on the blockchain during AI model training, using a circular linked list to manage the relationship between different versions of model parameters; after each parameter update, adding the new parameter as a node to the circular linked list and verifying it through the blockchain's consensus mechanism;

[0010] Optimize the AI ​​model inference process, including: during the AI ​​model inference stage, record inference requests and results on the blockchain, use circular linked lists to track the relationship between multiple inference requests and results of the same user or the same task, and record the association and dependency relationships between different inference tasks through multi-branch path trees.

[0011] When it is necessary to verify the correctness of the reasoning result, the data and integrity verification scheme on the blockchain are used to compare the reasoning process and result of this reasoning request with the reasoning process and result of similar previous requests. Combined with information such as the model version and data source recorded in the path tree, it is determined whether the current reasoning result is reasonable, thereby increasing users' trust in the reasoning results of the AI ​​model.

[0012] The performance of AI model inference is optimized by using a balancing method based on multi-branch path trees. To address the performance differences in inference paths caused by different input data, the inference path is treated as a branch of a multi-branch path tree. The optimized balancing method is used to reasonably adjust the resource allocation and scheduling of the inference path, enabling the model to run more efficiently during inference.

[0013] Secondly, this application provides a data integrity verification system applied to an intelligent platform, the system comprising:

[0014] The data storage module is used to store data on the blockchain. Utilizing the distributed storage characteristics of the blockchain, each data block's storage location on the blockchain is treated as a node, and these nodes are connected through a circular linked list.

[0015] The preprocessing module is used to treat the data imbalance that occurs during the data preprocessing process as an unbalanced path tree structure and optimize and balance it when performing data cleaning and normalization preprocessing operations.

[0016] The verification module is used to verify the integrity of the data used by the AI ​​model by utilizing the hash algorithm and digital signature technology of blockchain.

[0017] The AI ​​model training optimization module records the update process of model parameters on the blockchain during AI model training and uses a circular linked list to manage the relationship between different versions of model parameters. After each parameter update, the new parameter is added as a node to the circular linked list and verified through the blockchain's consensus mechanism.

[0018] The AI ​​model inference optimization module is used to record inference requests and results on the blockchain during the AI ​​model inference stage. It uses a circular linked list to track the relationship between multiple inference requests and results of the same user or the same task, and records the association and dependency relationships between different inference tasks through a multi-branch path tree.

[0019] When it is necessary to verify the correctness of the reasoning result, the data and integrity verification scheme on the blockchain are used to compare the reasoning process and result of this reasoning request with the reasoning process and result of similar previous requests. Combined with information such as the model version and data source recorded in the path tree, it is determined whether the current reasoning result is reasonable, thereby increasing users' trust in the reasoning results of the AI ​​model.

[0020] The performance of AI model inference is optimized by using a balancing method based on multi-branch path trees. To address the performance differences in inference paths caused by different input data, the inference path is treated as a branch of a multi-branch path tree. The optimized balancing method is used to reasonably adjust the resource allocation and scheduling of the inference path, enabling the model to run more efficiently during inference.

[0021] Thirdly, this application provides a data integrity verification system for intelligent platforms, the system comprising a processor and a memory:

[0022] The memory is used to store program code and transmit the program code to the processor;

[0023] The processor is configured to execute any one of the methods described in the first aspect according to the instructions in the program code.

[0024] Fourthly, this application provides a computer-readable storage medium for storing program code, which is executed by a processor to implement the method described in any one of the first aspects.

[0025] Beneficial effects

[0026] This invention provides a data integrity verification method and system for intelligent platforms. The method includes: storing data in a blockchain and connecting each data block node with a circular linked list; optimizing the data imbalance state using a multi-branch path tree balancing method during data preprocessing; verifying data integrity using the blockchain's hash algorithm and digital signature technology; recording the parameter update process in the blockchain and managing different versions of parameters using a circular linked list during AI model training; and recording inference requests and results in the blockchain during the inference phase, tracking the inference task relationships using a circular linked list and a multi-branch path tree, and verifying the correctness of the inference results through blockchain data and an integrity verification scheme, while simultaneously optimizing the performance of the inference path.

[0027] The method and system of the present invention have the following advantages and effects:

[0028] The method of this invention can effectively combine the advantages of blockchain, circular linked lists and multi-branch path trees, optimize the integrity verification process of AI model data, and improve the performance and stability of the model in the training and inference process, which is of great significance to promoting the development and application of artificial intelligence technology. Attached Figure Description

[0029] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, those skilled in the art can obtain other drawings based on these drawings without creative effort.

[0030] Figure 1 This is a flowchart of the present invention;

[0031] Figure 2 This is a system architecture diagram of the present invention. Detailed Implementation

[0032] The preferred embodiments of the present invention will now be described in detail with reference to the accompanying drawings, so that the advantages and features of the present invention can be more easily understood by those skilled in the art, thereby providing a clearer and more explicit definition of the scope of protection of the present invention.

[0033] Traditional cloud storage data integrity verification is prone to imbalance due to multiple dynamic data operations, resulting in high time costs and low verification efficiency. Optimizing the balancing method for imbalanced states has become a pressing issue for intelligent platforms.

[0034] By optimizing the data structure and verification process, the efficiency of AI model data integrity verification on the intelligent platform is improved, while the data path tree structure is balanced to enhance the training and derivation effects of the AI ​​model.

[0035] The data integrity verification method for intelligent platforms provided in this application includes:

[0036] Data is stored on the blockchain, taking advantage of the distributed storage characteristics of the blockchain. Each data block is stored at a node on the blockchain, and these nodes are connected by a circular linked list.

[0037] When performing preprocessing operations such as data cleaning and normalization, the balancing method of multi-branch path trees is used to treat the data imbalance that occurs during the data preprocessing process as a path tree structure under imbalance, and optimize and balance it.

[0038] By utilizing blockchain's hash algorithm and digital signature technology, the integrity of the data used by the AI ​​model is verified.

[0039] Optimize the AI ​​model training process, including: recording the update process of model parameters on the blockchain during AI model training, using a circular linked list to manage the relationship between different versions of model parameters; after each parameter update, adding the new parameter as a node to the circular linked list and verifying it through the blockchain's consensus mechanism;

[0040] Optimize the AI ​​model inference process, including: during the AI ​​model inference stage, record inference requests and results on the blockchain, use circular linked lists to track the relationship between multiple inference requests and results of the same user or the same task, and record the association and dependency relationships between different inference tasks through multi-branch path trees.

[0041] When it is necessary to verify the correctness of the reasoning result, the data and integrity verification scheme on the blockchain are used to compare the reasoning process and result of this reasoning request with the reasoning process and result of similar previous requests. Combined with information such as the model version and data source recorded in the path tree, it is determined whether the current reasoning result is reasonable, thereby increasing users' trust in the reasoning results of the AI ​​model.

[0042] The performance of AI model inference is optimized by using a balancing method based on multi-branch path trees. To address the performance differences in inference paths caused by different input data, the inference path is treated as a branch of a multi-branch path tree. The optimized balancing method is used to reasonably adjust the resource allocation and scheduling of the inference path, enabling the model to run more efficiently during inference.

[0043] Meanwhile, a circular linked list is used to record the performance metrics of different inference paths, which facilitates subsequent analysis and optimization of inference performance.

[0044] In some preferred embodiments, each data update or transmission generates a corresponding hash value, which is recorded on the blockchain. By comparing the hash value with the hash value recorded on the blockchain, it is possible to quickly detect whether the data has been tampered with.

[0045] In some preferred embodiments, in complex scenarios, an integrity verification scheme combining circular linked lists and multi-branch path trees is used to perform efficient hash value verification along the branches of the circular linked lists and path trees, ensuring that the AI ​​model uses complete and accurate data.

[0046] In some preferred embodiments, the parameter update path during model training is optimized using a multi-branch path tree balancing method. If an imbalance in parameter updates occurs during training, it is considered an imbalanced state of the path tree. The parameter update rhythm is adjusted using the optimized balancing method, so that the model converges more stably during training.

[0047] The system may further include the following process: the verifier issues a challenge request, performs integrity verification, and feeds back the verification result to the data owner.

[0048] Cloud storage servers store data and generate auxiliary information to return to the blockchain.

[0049] Blockchain needs to store data integrity verification information, forward integrity verification challenge requests, and return auxiliary information returned by the cloud storage server as evidence to the verifier.

[0050] Figure 2 This application provides an architecture diagram of a data integrity verification system applied to an intelligent platform, the system comprising:

[0051] The data storage module is used to store data on the blockchain. Utilizing the distributed storage characteristics of the blockchain, each data block's storage location on the blockchain is treated as a node, and these nodes are connected through a circular linked list.

[0052] The preprocessing module is used to treat the data imbalance that occurs during the data preprocessing process as an unbalanced path tree structure and optimize and balance it when performing data cleaning and normalization preprocessing operations.

[0053] The verification module is used to verify the integrity of the data used by the AI ​​model by utilizing the hash algorithm and digital signature technology of blockchain.

[0054] The AI ​​model training optimization module records the update process of model parameters on the blockchain during AI model training and uses a circular linked list to manage the relationship between different versions of model parameters. After each parameter update, the new parameter is added as a node to the circular linked list and verified through the blockchain's consensus mechanism.

[0055] The AI ​​model inference optimization module is used to record inference requests and results on the blockchain during the AI ​​model inference stage. It uses a circular linked list to track the relationship between multiple inference requests and results of the same user or the same task, and records the association and dependency relationships between different inference tasks through a multi-branch path tree.

[0056] When it is necessary to verify the correctness of the reasoning result, the data and integrity verification scheme on the blockchain are used to compare the reasoning process and result of this reasoning request with the reasoning process and result of similar previous requests. Combined with information such as the model version and data source recorded in the path tree, it is determined whether the current reasoning result is reasonable, thereby increasing users' trust in the reasoning results of the AI ​​model.

[0057] The performance of AI model inference is optimized by using a balancing method based on multi-branch path trees. To address the performance differences in inference paths caused by different input data, the inference path is treated as a branch of a multi-branch path tree. The optimized balancing method is used to reasonably adjust the resource allocation and scheduling of the inference path, enabling the model to run more efficiently during inference.

[0058] This application provides a data integrity verification system for an intelligent platform, the system comprising: a processor and a memory.

[0059] The memory is used to store program code and transmit the program code to the processor;

[0060] The processor is configured to execute the method described in any one of the embodiments of the first aspect according to the instructions in the program code.

[0061] This application provides a computer-readable storage medium for storing program code, which is executed by a processor to implement the method described in any one of the embodiments of the first aspect.

[0062] In a specific implementation, the present invention also provides a computer storage medium, wherein the computer storage medium may store a program, and the program, when executed, may include some or all of the steps in the various embodiments of the present invention. The storage medium may be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0063] Those skilled in the art will clearly understand that the techniques in the embodiments of the present invention can be implemented using software plus necessary general-purpose hardware platforms. Based on this understanding, the technical solutions in the embodiments of the present invention, or the parts that contribute to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments or certain parts of the embodiments of the present invention.

[0064] The same or similar parts between the various embodiments in this specification can be referred to mutually. In particular, the embodiments are basically similar to the method embodiments, so the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0065] The embodiments of the present invention described above do not constitute a limitation on the scope of protection of the present invention.

Claims

1. A data integrity verification method applied to an intelligent platform, characterized in that, The method includes: Data is stored on the blockchain, taking advantage of the distributed storage characteristics of the blockchain. Each data block is stored at a node on the blockchain, and these nodes are connected by a circular linked list. When performing data cleaning and normalization preprocessing operations, the balancing method of multi-branch path tree is used to treat the data imbalance that occurs during the data preprocessing process as a path tree structure under imbalance, and optimize and balance it. By utilizing blockchain's hash algorithm and digital signature technology, the integrity of the data used by the AI ​​model is verified. Optimize the AI ​​model training process, including: recording the update process of model parameters on the blockchain during AI model training, using a circular linked list to manage the relationship between different versions of model parameters; after each parameter update, adding the new parameter as a node to the circular linked list and verifying it through the blockchain's consensus mechanism; Optimize the AI ​​model inference process, including: during the AI ​​model inference stage, record inference requests and results on the blockchain, use circular linked lists to track the relationship between multiple inference requests and results of the same user or the same task, and record the association and dependency relationships between different inference tasks through multi-branch path trees. When it is necessary to verify the correctness of the reasoning result, the data and integrity verification scheme on the blockchain are used to compare the reasoning process and result of this reasoning request with the reasoning process and result of similar previous requests, and combined with the model version and data source recorded in the path tree, to determine whether the current reasoning result is reasonable, thereby increasing users' trust in the reasoning results of the AI ​​model. The performance of AI model inference is optimized by using a balancing method based on multi-branch path trees. To address the performance differences in inference paths caused by different input data, the inference path is treated as a branch of a multi-branch path tree. The optimized balancing method is used to reasonably adjust the resource allocation and scheduling of the inference path, enabling the model to run more efficiently during inference.

2. The method according to claim 1, characterized in that: Every data update or transmission generates a corresponding hash value, which is recorded on the blockchain. By comparing the hash value with the hash value recorded on the blockchain, it is possible to quickly detect whether the data has been tampered with.

3. The method according to claim 2, characterized in that: In complex scenarios, a combination of circular linked lists and multi-branch path trees is used for integrity verification. Efficient hash value verification is performed along the branches of the circular linked lists and path trees to ensure that the AI ​​model uses complete and accurate data.

4. The method according to claim 2, characterized in that: The parameter update path during model training is optimized using a multi-branch path tree balancing method. If an imbalance in parameter updates occurs during training, it is considered an imbalanced state of the path tree. The optimized balancing method is used to adjust the parameter update rhythm, making the model converge more stably during training.

5. A data integrity verification system applied to an intelligent platform, characterized in that, The system includes: The data storage module is used to store data on the blockchain. Utilizing the distributed storage characteristics of the blockchain, each data block's storage location on the blockchain is treated as a node, and these nodes are connected through a circular linked list. The preprocessing module is used to treat the data imbalance that occurs during the data preprocessing process as an unbalanced path tree structure and optimize and balance it when performing data cleaning and normalization preprocessing operations. The verification module is used to verify the integrity of the data used by the AI ​​model by utilizing the hash algorithm and digital signature technology of blockchain. The AI ​​model training optimization module records the update process of model parameters on the blockchain during AI model training and uses a circular linked list to manage the relationship between different versions of model parameters. After each parameter update, the new parameter is added as a node to the circular linked list and verified through the blockchain's consensus mechanism. The AI ​​model inference optimization module is used to record inference requests and results on the blockchain during the AI ​​model inference stage. It uses a circular linked list to track the relationship between multiple inference requests and results of the same user or the same task, and records the association and dependency relationships between different inference tasks through a multi-branch path tree. When it is necessary to verify the correctness of the reasoning result, the data and integrity verification scheme on the blockchain are used to compare the reasoning process and result of this reasoning request with the reasoning process and result of similar previous requests, and combined with the model version and data source recorded in the path tree, to determine whether the current reasoning result is reasonable, thereby increasing users' trust in the reasoning results of the AI ​​model. The performance of AI model inference is optimized by using a balancing method based on multi-branch path trees. To address the performance differences in inference paths caused by different input data, the inference path is treated as a branch of a multi-branch path tree. The optimized balancing method is used to reasonably adjust the resource allocation and scheduling of the inference path, enabling the model to run more efficiently during inference.

6. A data integrity verification system applied to an intelligent platform, characterized in that, The system includes a processor and a memory: The memory is used to store program code and transmit the program code to the processor; The processor is configured to execute instructions in the program code to implement the method according to any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium is used to store program code, which is executed by a processor to implement the method of any one of claims 1-4.

Images