Data integrity verification method and system applied to intelligent platform

Abstract

The invention provides a data integrity verification method and system applied to an intelligent platform. The method comprises the steps that data are stored in a block chain, and data block nodes are connected through a circular linked list; during data preprocessing, a multi-branch path tree balance method is utilized to optimize a data imbalance state; performing data integrity verification by means of a hash algorithm and a digital signature technology of the block chain; in AI model training, a parameter updating process is recorded in a block chain, and different version parameters are managed by using a circular linked list; in a reasoning stage, a reasoning request and a result are recorded in a block chain, a cyclic chain table and a multi-branch path tree are utilized to track a reasoning task relationship, correctness of the reasoning result is verified through block chain data and an integrity verification scheme, and meanwhile reasoning path performance is optimized. The system comprises corresponding modules or components to realize the method. According to the method, the advantages of the block chain, the circular linked list and the multi-branch path tree are combined, the data integrity verification process is optimized, the AI model training and reasoning performance and stability are improved, and the method is of great significance to artificial intelligence technology development.

Description

Technical Field

[0001] The present application relates to the field of network security technology, and in particular to a data integrity verification method and system applied to an intelligent platform. Background Art

[0002] For intelligent platforms, the integrity of the data required for AI model training and derivation is crucial. Traditional cloud storage data integrity verification is prone to imbalance due to multiple dynamic data operations, resulting in high time consumption and low verification efficiency. Optimizing balancing methods for imbalanced data has become an urgent challenge 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 the present invention is to provide a data integrity verification method and system for intelligent platforms, which improves the efficiency of AI model data integrity verification on intelligent platforms by optimizing data structure and verification process, while balancing the data path tree structure and improving the training and derivation effects of AI models.

[0005] In a first aspect, the present application provides a data integrity verification method applied to an intelligent platform, the method comprising:

[0006] The data is stored on the blockchain. Utilizing the distributed storage characteristics of the blockchain, the storage location of each data block on the blockchain is regarded as a node, and these nodes are connected through a circular linked list.

[0007] When performing pre-processing operations such as cleaning and normalization on the data, the balancing method of the multi-branch path tree is used to treat the data imbalance that occurs during the data pre-processing process as an unbalanced path tree structure, and optimize and balance it;

[0008] Use blockchain’s hashing algorithm and digital signature technology to verify the integrity of data used by AI models;

[0009] Optimizing 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 consensus mechanism;

[0010] Optimizing the AI ​​model inference process, including: During the AI ​​model inference phase, recording inference requests and results on the blockchain, using a circular linked list to track the relationship between multiple inference requests and results for the same user or task, and recording the associations and dependencies between different inference tasks through a multi-branch path tree;

[0011] When the correctness of the inference result needs to be verified, the data and integrity verification scheme on the blockchain are used to compare the inference process and results of the current inference request with those of previous similar requests. In combination with information such as the model version and data source recorded in the path tree, the current inference result is judged to be reasonable, thereby improving the user's trust in the AI ​​model inference result.

[0012] The performance of the AI ​​model inference process is optimized using a balancing method of a multi-branch path tree. In view of the performance differences of the inference path caused by different input data, the inference path is regarded as a branch of the multi-branch path tree. The resource allocation and scheduling of the inference path are reasonably adjusted through the optimized balancing method, making the model run more efficiently during the inference process.

[0013] In a second aspect, the present 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. By utilizing the distributed storage characteristics of the blockchain, the storage location of each data block on the blockchain is regarded as a node, and these nodes are connected through a circular linked list;

[0015] The preprocessing module is used to use the balancing method of the multi-branch path tree when performing cleaning and normalization preprocessing operations on the data. The data imbalance that occurs during the data preprocessing process is regarded as an unbalanced path tree structure and optimized and balanced.

[0016] A verification module, which uses blockchain’s hashing algorithm and digital signature technology to verify the integrity of the data used by the AI ​​model;

[0017] The AI ​​model training optimization module is used to record the update process of model parameters on the blockchain during AI model training, and use 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 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 phase. It uses a circular linked list to track the relationship between multiple inference requests and results for the same user or the same task, and records the associations and dependencies between different inference tasks through a multi-branch path tree.

[0019] When the correctness of the inference result needs to be verified, the data and integrity verification scheme on the blockchain are used to compare the inference process and results of the current inference request with those of previous similar requests. In combination with information such as the model version and data source recorded in the path tree, the current inference result is judged to be reasonable, thereby improving the user's trust in the AI ​​model inference result.

[0020] The performance of the AI ​​model inference process is optimized using a balancing method of a multi-branch path tree. In view of the performance differences of the inference path caused by different input data, the inference path is regarded as a branch of the multi-branch path tree. The resource allocation and scheduling of the inference path are reasonably adjusted through the optimized balancing method, making the model run more efficiently during the inference process.

[0021] In a third aspect, the present application provides a data integrity verification system for an intelligent platform, 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 possible methods of the first aspect according to instructions in the program code.

[0024] In a fourth aspect, the present application provides a computer-readable storage medium, wherein the computer-readable storage medium is used to store program code, and the program code is used to be executed by a processor to implement any one of the methods described in the first aspect.

[0025] Beneficial effects

[0026] The present invention provides a data integrity verification method and system for an intelligent platform, the method comprising: storing data in a blockchain and connecting each data block node with a circular linked list; during data preprocessing, optimizing the data imbalance state using a balancing method of a multi-branch path tree; performing data integrity verification with the help of a hash algorithm and digital signature technology of the blockchain; during AI model training, recording the parameter update process in the blockchain and managing different versions of parameters with a circular linked list; during the inference stage, recording inference requests and results in the blockchain, tracking the inference task relationship using a circular linked list and a multi-branch path tree, verifying the correctness of the inference result using blockchain data and an integrity verification scheme, and optimizing the inference path performance.

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

[0028] The method of the present 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 during training and inference, which is of great significance to promoting the development and application of artificial intelligence technology. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0030] Figure 1 is a flow chart of the present invention;

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

[0032] The preferred embodiments of the present invention are described in detail below 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 making a clearer and more precise definition of the protection scope of the present invention.

[0033] Traditional cloud storage data integrity verification is prone to imbalances due to multiple dynamic data operations, resulting in high time consumption and low verification efficiency. Optimizing the balancing method for imbalanced states has become an urgent challenge for intelligent platforms.

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

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

[0036] The data is stored on the blockchain. Utilizing the distributed storage characteristics of the blockchain, the storage location of each data block on the blockchain is regarded as a node, and these nodes are connected through a circular linked list.

[0037] When performing pre-processing operations such as cleaning and normalization on the data, the balancing method of the multi-branch path tree is used to treat the data imbalance that occurs during the data pre-processing process as an unbalanced path tree structure, and optimize and balance it;

[0038] Use blockchain’s hashing algorithm and digital signature technology to verify the integrity of data used by AI models;

[0039] Optimizing 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 consensus mechanism;

[0040] Optimizing the AI ​​model inference process, including: During the AI ​​model inference phase, recording inference requests and results on the blockchain, using a circular linked list to track the relationship between multiple inference requests and results for the same user or task, and recording the associations and dependencies between different inference tasks through a multi-branch path tree;

[0041] When the correctness of the inference result needs to be verified, the data and integrity verification scheme on the blockchain are used to compare the inference process and results of the current inference request with those of previous similar requests. In combination with information such as the model version and data source recorded in the path tree, the current inference result is judged to be reasonable, thereby improving the user's trust in the AI ​​model inference result.

[0042] The performance of the AI ​​model inference process is optimized using a balancing method of a multi-branch path tree. In view of the performance differences of the inference path caused by different input data, the inference path is regarded as a branch of the multi-branch path tree. The resource allocation and scheduling of the inference path are reasonably adjusted through the optimized balancing method, making the model run more efficiently during the inference process.

[0043] At the same time, a circular linked list is used to record the performance indicators of different reasoning paths to facilitate subsequent analysis and optimization of reasoning performance.

[0044] In some preferred embodiments, each time data is updated or transmitted, a corresponding hash value is generated and recorded on the blockchain. By comparing it 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, the integrity verification scheme of the circular linked list and the multi-branch path tree is combined to perform efficient hash value verification along the branches of the circular linked list and the path tree to ensure that the AI ​​model uses complete and accurate data.

[0046] In some preferred embodiments, a balancing method of a multi-branch path tree is used to optimize the parameter update path during the model training process. If an unbalanced parameter update occurs during the training process, it is regarded as an unbalanced state of the path tree. The parameter update rhythm is adjusted through the optimized balancing method to make the model converge more stably during the training process.

[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] The cloud storage server stores data information and generates auxiliary information and returns it to the blockchain.

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

[0050] Figure 2 This is an architectural diagram of the data integrity verification system for an intelligent platform provided in this application. The system includes:

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

[0052] The preprocessing module is used to use the balancing method of the multi-branch path tree when performing cleaning and normalization preprocessing operations on the data. The data imbalance that occurs during the data preprocessing process is regarded as an unbalanced path tree structure and optimized and balanced.

[0053] A verification module, which uses blockchain’s hashing algorithm and digital signature technology to verify the integrity of the data used by the AI ​​model;

[0054] The AI ​​model training optimization module is used to record the update process of model parameters on the blockchain during AI model training, and use 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 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 phase. It uses a circular linked list to track the relationship between multiple inference requests and results for the same user or the same task, and records the associations and dependencies between different inference tasks through a multi-branch path tree.

[0056] When the correctness of the inference result needs to be verified, the data and integrity verification scheme on the blockchain are used to compare the inference process and results of the current inference request with those of previous similar requests. In combination with information such as the model version and data source recorded in the path tree, the current inference result is judged to be reasonable, thereby improving the user's trust in the AI ​​model inference result.

[0057] The performance of the AI ​​model inference process is optimized using a balancing method of a multi-branch path tree. In view of the performance differences of the inference path caused by different input data, the inference path is regarded as a branch of the multi-branch path tree. The resource allocation and scheduling of the inference path are reasonably adjusted through the optimized balancing method, making the model run more efficiently during the inference process.

[0058] The present application provides a data integrity verification system applied to an intelligent platform, the system comprising: 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 all embodiments of the first aspect according to instructions in the program code.

[0061] The present application provides a computer-readable storage medium, which is used to store program code, and the program code is used to be executed by a processor to implement any one of the methods in all embodiments of the first aspect.

[0062] In a specific implementation, the present invention further provides a computer storage medium, wherein the computer storage medium may store a program that, when executed, may include some or all of the steps of 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).

[0063] Those skilled in the art will clearly understand that the technology in the embodiments of the present invention can be implemented by means of software plus the necessary general-purpose hardware platform. Based on this understanding, the technical solutions in the embodiments of the present invention, or the portion that contributes 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, a magnetic disk, or an optical disk, and includes a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods described in various embodiments of the present invention or certain portions of the embodiments.

[0064] In particular, for the embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the description in the method embodiments.

[0065] The above-described embodiments of the present invention do not limit the protection scope of the present invention.

Claims

1. A data integrity verification method applied to an intelligent platform, characterized in that: The method comprises: The data is stored on the blockchain. Utilizing the distributed storage characteristics of the blockchain, the storage location of each data block on the blockchain is regarded as a node, and these nodes are connected through a circular linked list. When cleaning and normalizing the data, the balancing method of the multi-branch path tree 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. Use blockchain’s hashing algorithm and digital signature technology to verify the integrity of data used by AI models; Optimizing 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 consensus mechanism; Optimizing the AI ​​model inference process, including: During the AI ​​model inference phase, recording inference requests and results on the blockchain, using a circular linked list to track the relationship between multiple inference requests and results for the same user or task, and recording the associations and dependencies between different inference tasks through a multi-branch path tree; When the correctness of the inference result needs to be verified, the data and integrity verification scheme on the blockchain are used to compare the inference process and results of the current inference request with those of previous similar requests. In combination with information such as the model version and data source recorded in the path tree, the current inference result is judged to be reasonable, thereby improving the user's trust in the AI ​​model inference result. The performance of the AI ​​model inference process is optimized using a balancing method of a multi-branch path tree. In view of the performance differences of the inference path caused by different input data, the inference path is regarded as a branch of the multi-branch path tree. The resource allocation and scheduling of the inference path are reasonably adjusted through the optimized balancing method, making the model run more efficiently during the inference process.

2. The method according to claim 1, wherein: Every time data is updated or transmitted, a corresponding hash value will be generated and recorded on the blockchain. By comparing it 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, wherein: In complex scenarios, the integrity verification scheme of the circular linked list and multi-branch path tree is combined to perform efficient hash value verification along the branches of the circular linked list and path tree to ensure that the AI ​​model uses complete and accurate data.

4. The method according to claim 2, wherein: The parameter update path during model training is optimized using a balancing method using a multi-branch path tree. If an unbalanced parameter update occurs during training, it is considered an unbalanced state of the path tree. The parameter update rhythm is adjusted using the optimized balancing method, allowing the model to converge more stably during training.

5. A data integrity verification system applied to an intelligent platform, characterized in that: The system comprises: The data storage module is used to store data on the blockchain. By utilizing the distributed storage characteristics of the blockchain, the storage location of each data block on the blockchain is regarded as a node, and these nodes are connected through a circular linked list; The preprocessing module is used to use the balancing method of the multi-branch path tree when performing cleaning and normalization preprocessing operations on the data. The data imbalance that occurs during the data preprocessing process is regarded as an unbalanced path tree structure and optimized and balanced. A verification module, which uses blockchain’s hashing algorithm and digital signature technology to verify the integrity of the data used by the AI ​​model; The AI ​​model training optimization module is used to record the update process of model parameters on the blockchain during AI model training, and use 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 consensus mechanism; The AI ​​model inference optimization module is used to record inference requests and results on the blockchain during the AI ​​model inference phase. It uses a circular linked list to track the relationship between multiple inference requests and results for the same user or the same task, and records the associations and dependencies between different inference tasks through a multi-branch path tree. When the correctness of the inference result needs to be verified, the data and integrity verification scheme on the blockchain are used to compare the inference process and results of the current inference request with those of previous similar requests. In combination with information such as the model version and data source recorded in the path tree, the current inference result is judged to be reasonable, thereby improving the user's trust in the AI ​​model inference result. The performance of the AI ​​model inference process is optimized using a balancing method of a multi-branch path tree. In view of the performance differences of the inference path caused by different input data, the inference path is regarded as a branch of the multi-branch path tree. The resource allocation and scheduling of the inference path are reasonably adjusted through the optimized balancing method, making the model run more efficiently during the inference process.

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 implement the method according to any one of claims 1 to 4 according to the instructions in the program code.

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

Images