Data right confirmation method and device based on privacy calculation, equipment, medium and product

Abstract

The invention discloses a data right confirmation method and device based on privacy calculation, equipment, a medium and a product. The data right confirmation method based on privacy calculation comprises the following steps: a data provider encrypts original data to be subjected to right confirmation to obtain ciphertext data, and constructs a data fingerprint based on the ciphertext data; correspondingly uploading the data fingerprint and the ownership information of the original data to a block chain for evidence storage; the plurality of data participants cooperatively execute multi-party privacy calculation based on the ciphertext data, determine the contribution degree of each data feature to a preset business model, and determine a basic value evaluation result based on the contribution degree; and in response to a data transaction request initiated by a data demander, verifying transaction compliance through the smart contract, and executing an ownership transfer operation on the block chain after verification is passed. According to the technical scheme provided by the embodiment of the invention, data right confirmation in a secret state environment can be realized, and the value evaluation accuracy is improved.

Description

Technical Field

[0001] This invention relates to the field of blockchain technology, and in particular to a data ownership confirmation method, apparatus, device, medium, and product based on privacy computing. Background Technology

[0002] Data is a key element of the digital economy and a core factor of production in the new era. Therefore, in data sharing scenarios, implementing data ownership mechanisms while ensuring data privacy, as well as data value assessment, are crucial for the standardized use of data.

[0003] In traditional data sharing, ownership verification relies on registration by a central node, such as database records, which poses a single point of failure risk. Blockchain's method of publicly disclosing data hash values ​​for ownership verification may leak data characteristics.

[0004] Furthermore, existing data value assessments are mostly based on broad indicators such as data volume and coverage, failing to quantify the actual contribution of data to business operations. Therefore, how to implement data ownership mechanisms while ensuring data privacy, and how to reasonably assess data value, have received widespread attention. Summary of the Invention

[0005] This invention provides a data ownership confirmation method, apparatus, device, medium, and product based on privacy computing, to solve the problems of data leakage and inaccurate data value assessment in existing data ownership confirmation schemes.

[0006] According to one aspect of the present invention, a data ownership confirmation method based on privacy computing is provided, comprising:

[0007] The data provider encrypts the original data to be confirmed, obtaining ciphertext data, and constructs a data fingerprint based on the ciphertext data;

[0008] The data fingerprint and the ownership information of the original data are uploaded to the blockchain for evidence storage.

[0009] Multiple data participants collaborate to perform multi-party privacy computations based on the encrypted data, determine the contribution of each data feature to the preset business model, and determine the basic value assessment result based on the contribution.

[0010] In response to a data transaction request initiated by a data demander, the system verifies the compliance of the transaction through a smart contract and executes the ownership transfer operation on the blockchain after the verification is successful.

[0011] According to another aspect of the present invention, a data ownership confirmation device based on privacy computing is provided, comprising:

[0012] The data provider encrypts the original data to be confirmed, obtaining ciphertext data, and constructs a data fingerprint based on the ciphertext data;

[0013] The data fingerprint and the ownership information of the original data are uploaded to the blockchain for evidence storage.

[0014] Multiple data participants collaborate to perform multi-party privacy computations based on the encrypted data, determine the contribution of each data feature to the preset business model, and determine the basic value assessment result based on the contribution.

[0015] In response to a data transaction request initiated by a data demander, the system verifies the compliance of the transaction through a smart contract and executes the ownership transfer operation on the blockchain after the verification is successful.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the privacy-based computation-based data ownership method according to any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the data ownership determination method based on privacy computing as described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is provided, including a computer program that, when executed by a processor, implements a data ownership determination method based on privacy computing according to any embodiment of the present disclosure.

[0022] The technical solution of this invention involves the data provider encrypting the original data to be confirmed, obtaining ciphertext data, and constructing a data fingerprint based on the ciphertext data. The data fingerprint and the ownership information of the original data are then uploaded to the blockchain for notarization. Multiple data participants collaboratively perform multi-party privacy computation based on the ciphertext data to determine the contribution of each data feature to a preset business model. Based on the contribution, a basic value assessment result is determined. Finally, in response to a data transaction request initiated by a data requester, the transaction compliance is verified through a smart contract. After successful verification, the ownership transfer operation is executed on the blockchain. This method of constructing data fingerprints based on ciphertext data and uploading them to the blockchain enables data ownership confirmation in a secure environment, ensuring that the original data does not leave the domain. Furthermore, data value assessment based on the contribution of data features to the business model improves the accuracy of value assessment compared to methods based on data volume and coverage.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a data ownership confirmation method based on privacy computing according to Embodiment 1 of the present invention;

[0026] Figure 2 This is a flowchart of a data ownership confirmation method based on privacy computing according to Embodiment 2 of the present invention;

[0027] Figure 3 This is a schematic diagram of a data ownership confirmation device based on privacy computing according to Embodiment 3 of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of an electronic device that implements the privacy-based computation-based data ownership confirmation method according to an embodiment of the present invention. Detailed Implementation

[0029] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0030] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0031] Example 1

[0032] Figure 1 This is a flowchart illustrating a privacy-based computation-based data ownership confirmation method according to Embodiment 1 of the present invention. This embodiment is applicable to situations involving data ownership confirmation and data value assessment in a closed environment. The method can be executed by a privacy-based computation-based data ownership confirmation device, which can be implemented in hardware and / or software and can be configured in various general-purpose computing devices. Figure 1 As shown, the method includes:

[0033] S110. The data provider encrypts the original data to be confirmed, obtaining ciphertext data, and constructs a data fingerprint based on the ciphertext data.

[0034] A data provider is an entity that owns or has the right to use the original data and needs to establish ownership of the original data. For example, a data provider may be a financial institution or a data supplier. Original data is data that needs to be established and its value assessed. For example, original data may be financial data held by financial institutions, such as tax data, transaction records, and credit records.

[0035] Data fingerprints are extracted from raw data using specific algorithms. They are summaries that uniquely identify the raw data and are unique and tamper-proof.

[0036] In this embodiment of the invention, the data provider first encrypts the original data to be verified, obtaining ciphertext data, which ensures the confidentiality of the original data. For example, the encryption method can be additive homomorphic encryption, such as the Paillier encryption method. Further, a data fingerprint is constructed based on the ciphertext data. Specifically, multi-dimensional feature information can be extracted from the ciphertext data, and homomorphic hashing is performed on each dimension of feature information. The hash values ​​corresponding to the multiple dimensions of feature information are combined to obtain the data fingerprint. Using homomorphic hashing to generate data fingerprints ensures the verifiability of the fingerprint generation process while avoiding the exposure of the original data.

[0037] In addition, the initial fingerprint can be further hashed using a cryptographic hash algorithm to obtain the final data fingerprint.

[0038] In a specific example, basic features, business tags, and usage records are extracted from the encrypted data. Homomorphic hashing is then performed on each of these three types of features, and the hash values ​​corresponding to these three types of feature information are combined to obtain the initial fingerprint. Furthermore, the initial fingerprint is further hashed using a quantum attack hashing scheme to obtain the data fingerprint. The application of quantum-resistant hashing algorithms ensures the long-term security of the data fingerprint in future quantum computing environments, meeting the long-term ownership verification requirements of financial data assets.

[0039] S120. Upload the data fingerprint and the ownership information of the original data to the blockchain for evidence storage.

[0040] Ownership information is information used to prove ownership or right to use data. For example, ownership information includes the identity information of the data provider, proof of data source, and scope of authorization.

[0041] In this embodiment of the invention, a pre-consortium blockchain-based evidence storage system is constructed, using the Chang'an Chain as the underlying blockchain platform. Data fingerprints and ownership information are bound together via smart contracts, and the bound information is stored on the blockchain to form an immutable record of ownership. Zero-knowledge proof technology can be used to verify the legality of the on-chain data fingerprints, ensuring that no original data information is leaked during the evidence storage process. A unique blockchain address is generated for each data asset, serving as its unique identifier. By storing data fingerprints and corresponding ownership information on the blockchain, the immutability of the blockchain ensures the credibility and authority of the data ownership record.

[0042] S130. Multiple data participants collaborate to perform multi-party privacy computations based on encrypted data, determine the contribution of each data feature to the preset business model, and determine the basic value assessment result based on the contribution.

[0043] Data participants are the data users who participate in collaborative computation. For example, financial institutions A and B each hold a portion of the original data but do not share it. Multi-party privacy computation refers to a method in which multiple participants jointly complete computational tasks using cryptographic techniques without disclosing their respective original data (only using encrypted data for collaborative computation).

[0044] In this embodiment of the invention, each data participant splits its encrypted data into multiple data fragments and distributes them to other data participants. Based on multiplication triples, the value function of different feature subsets to a preset business model is jointly calculated on each data fragment. Finally, the Shapley value algorithm is used to quantify the contribution of each feature based on the value function calculation results of each feature subset. Local contributions are summarized through additive homomorphic encryption, and the server decrypts the data to obtain a global Shapley value vector as the basic value assessment result. Through the above value assessment method, accurate data value assessment can be performed without disclosing the original data.

[0045] Feature contribution is a quantitative assessment of the performance improvement of a single data feature on the overall business model, reflecting the relative importance of that feature in the model. The basic value assessment result is the benchmark value of the data asset calculated based on feature contribution, without considering the impact of market dynamics on data value.

[0046] S140. In response to a data transaction request initiated by a data requester, verify the compliance of the transaction through a smart contract, and execute the ownership transfer operation on the blockchain after the verification is successful.

[0047] Data demanders are entities that need to use data; transaction compliance refers to whether data transaction activities comply with relevant laws, regulations, regulatory requirements, and authorized scope.

[0048] In this embodiment of the invention, the data requester initiates a data transaction request through a blockchain client. The data transaction request includes the target data asset, data purpose, and pricing information. The compliance of the transaction is verified through a smart contract. Specifically, this verification may include whether the data purpose is within the authorized scope, whether the requester's qualifications meet the requirements, whether the transaction price reaches a preset threshold, and whether special scenarios such as data export have passed security assessments. The regulatory node in the blockchain verifies the compliance of the transaction details using homomorphic encryption technology without decrypting the specific content. After successful verification, the smart contract locks the transaction funds from the requester's account and updates the data asset ownership record on the blockchain. This cryptographic compliance verification technology ensures the effectiveness of supervision while protecting the commercial privacy of both parties. Furthermore, the end-to-end blockchain record provides an immutable chain of evidence for transaction disputes, reducing legal risks.

[0049] In addition, when abnormal transaction patterns are detected, such as high-frequency trading, a risk warning can be triggered and the data can be stored on the blockchain. The dynamic risk monitoring mechanism can promptly detect and prevent abnormal transactions, ensuring the security of data transactions.

[0050] The technical solution of this invention involves the data provider encrypting the original data to be confirmed, obtaining ciphertext data, and constructing a data fingerprint based on the ciphertext data. The data fingerprint and the ownership information of the original data are then uploaded to the blockchain for notarization. Multiple data participants collaboratively perform multi-party privacy computation based on the ciphertext data to determine the contribution of each data feature to a preset business model. Based on the contribution, a basic value assessment result is determined. Finally, in response to a data transaction request initiated by a data requester, the transaction compliance is verified through a smart contract. After successful verification, the ownership transfer operation is executed on the blockchain. This method of constructing data fingerprints based on ciphertext data and uploading them to the blockchain enables data ownership confirmation in a secure environment, ensuring that the original data does not leave the domain. Furthermore, data value assessment based on the contribution of data features to the business model improves the accuracy of value assessment compared to methods based on data volume and coverage.

[0051] Example 2

[0052] Figure 2 This is a flowchart of a data ownership confirmation method based on privacy computation provided in Embodiment 2 of the present invention. This embodiment further refines the above embodiment, providing specific steps for the data provider to encrypt the original data to be confirmed, obtaining ciphertext data, and constructing a data fingerprint based on the ciphertext data. It also includes specific steps for multiple data participants to collaboratively perform multi-party privacy computation based on the ciphertext data, determine the contribution of each data feature to a preset business model, and determine the basic value assessment result based on the contribution. Figure 2 As shown, the method includes:

[0053] S210. Using a homomorphic encryption algorithm, the original data to be confirmed is encrypted to obtain ciphertext data.

[0054] Homomorphic encryption algorithms are a special encryption technique that allows arithmetic operations to be performed directly on the ciphertext, and the decrypted result is identical to the result of performing the same operation on the plaintext. Examples of homomorphic encryption algorithms include additive homomorphic, multiplicative homomorphic, and fully homomorphic encryption. Ciphertext data is encrypted data generated from the original data using a homomorphic encryption algorithm, supporting specific cryptomorphic operations.

[0055] In this embodiment of the invention, the original data D can first undergo standardized preprocessing, including data cleaning, data format standardization, and outlier filtering. Then, the preprocessed data is encrypted using a homomorphic encryption algorithm to obtain ciphertext data E(D). For example, an additive homomorphic encryption algorithm is used to encrypt the original data to obtain ciphertext data. The use of homomorphic encryption technology allows the data to still participate in subsequent calculations while encrypted, laying a secure foundation for subsequent fingerprint generation.

[0056] S220. Extract multi-dimensional feature information from the ciphertext data, perform homomorphic hash operation on each dimension of feature information, and combine the hash values ​​corresponding to the feature information of multiple dimensions to obtain the initial fingerprint.

[0057] Multi-dimensional feature information is a set of business-meaning features extracted from encrypted data, which can include basic features, business features, and usage features. Basic features can include data type and data distribution, etc.; business features can be "credit risk control related"; usage records can include the number of times data was shared and the authorization period, etc.

[0058] In this embodiment of the invention, multi-dimensional feature information is extracted from the encrypted data, and homomorphic hashing is performed on the feature information of each dimension. Then, the hash values ​​corresponding to the feature information of multiple dimensions are combined, and homomorphic hashing is performed on the feature information of each dimension separately. The hash values ​​corresponding to the feature information of each dimension are then combined according to a set concatenation rule to obtain the initial fingerprint.

[0059] In a specific example, three core dimensions of feature information are extracted from the encrypted data. These three dimensions include basic features C, such as structural features including field type, data length, and numerical range; business tags B, such as business-related features including business tags, classification information, and risk level; and usage records U, such as usage trajectory features including creation time, modification records, and access history.

[0060] Furthermore, a hash function supporting additive homomorphism is used to process the encryption features, ensuring that the hashing process does not corrupt the original encryption state and maintains data confidentiality. Specifically, the calculation formula is as follows:

[0061]

[0062] in, It is a collision homomorphic hash function. , and These are the basic characteristics of the encrypted data, business tags, and usage records.

[0063] The hash outputs from the three dimensions are then combined in a fixed order to obtain the initial fingerprint. .

[0064] By encrypting the original data and extracting multi-dimensional feature information from the ciphertext data for homomorphic hashing, an initial fingerprint is generated based on the hashing result. This allows data fingerprints to be constructed without exposing the original data. Furthermore, multi-dimensional feature extraction ensures that the data fingerprint contains comprehensive data features, avoiding fingerprint conflicts between different data.

[0065] S230. The initial fingerprint is hashed using a cryptographic hash algorithm to obtain the data fingerprint.

[0066] In this embodiment of the invention, an encrypted hash algorithm, such as SHA-3-256, is used to perform final hash processing on the initial fingerprint to obtain the data fingerprint. The specific calculation formula is as follows:

[0067]

[0068] Where r is a random number and x is the initial fingerprint for hashing. The collision resistance is enhanced by the "one-time pad" mechanism to ensure the security of data fingerprints in the quantum computing era.

[0069] By further hashing the initial fingerprint using a cryptographic hash algorithm, the problems of the original fingerprint being too long and easily tampered with can be solved, thereby generating a short-byte, collision-resistant data fingerprint, which is suitable for blockchain evidence storage.

[0070] Optionally, the cryptographic hash algorithm is a quantum-resistant SHA-3 hash function.

[0071] S240. Upload the data fingerprint and the ownership information of the original data to the blockchain for evidence storage.

[0072] S250. Each data participant splits the encrypted data into multiple data fragments using a secret sharing protocol, based on the number of data participants.

[0073] In this embodiment of the invention, to achieve data sharing, each data participant securely splits its encrypted data using a secret sharing protocol, based on the number of participants. Specifically, each participant uses its own encrypted data as input and generates multiple data fragments corresponding to the number of participants through a secret sharing algorithm. The specific calculation formula is as follows:

[0074]

[0075] Where p is a large prime number, It refers to the data shards held by each data participant.

[0076] Furthermore, the resulting data shards can be distributed using a distributed strategy, with each participant receiving one data shard, and the original data information cannot be reconstructed from a single data shard. During the shard distribution process, authentication and encrypted transmission mechanisms can be employed to ensure the security of the data shards. Data sharding technology achieves distributed and secure data storage, effectively reducing the risk of single-point data leakage.

[0077] S260. Using multiplication triples, the value of each feature subset to the preset business model is jointly calculated on each data shard.

[0078] A feature subset is a selection of features from the set of features in the data. It is used to evaluate the contribution of a specific feature combination to a pre-defined business model. A feature subset can also be a single feature. The pre-defined business model is the financial business algorithm model to be evaluated, such as a risk control model.

[0079] In this embodiment of the invention, in a secure computing environment, each data participant satisfies the following conditions based on the multiplication triple (a, b, c): Privacy-preserving computations are performed on each party's respective data shards. During the computation, for each feature subset to be evaluated, the parties collaborate through a secure multi-party computation protocol to jointly calculate the value v(S) of that feature subset to a predefined business model without exposing the content of their respective data shards. For example, the model training process can be simulated in a cryptographic environment to evaluate the model's performance metrics, such as accuracy, recall, or AUC, when using that feature subset. The entire computation process is secured through cryptographic protocols, ensuring that none of the data participants can access the data information of other parties. The secure multi-party computation protocol ensures that the data privacy of each participant is fully protected, achieving collaborative value computation without the data leaving its domain.

[0080] Optionally, multiplication triples are used to jointly calculate the value of each feature subset to the preset business model on each data shard, including:

[0081] Using multiplication triples, the initial value of each feature subset to the preset business model is jointly calculated on each data shard;

[0082] By employing the Laplace noise function and introducing differential privacy noise into the initial value, the value of each feature subset to the preset business model is obtained.

[0083] In this optional embodiment, a specific method is provided for jointly calculating the value of each feature subset to the preset business model on each data shard using multiplication triples: Each data participant performs secure multi-party computation on distributed data shards based on pre-generated multiplication triples. For each feature subset to be evaluated, each participant collaboratively calculates the model performance index corresponding to that feature subset in a encrypted environment using a secure multiplication protocol. During the computation, complex encrypted multiplication operations are transformed into secure addition operations using multiplication triples, ensuring that each participant cannot obtain the original data shard content of other parties throughout the computation process. Through multiple rounds of iterative computation, the performance evaluation value of each feature subset to the preset business model is finally obtained in a encrypted state, forming an initial value result without noise.

[0084] Furthermore, after obtaining the initial value assessment results, the system calculates the scale parameters of the Laplace noise based on preset privacy budget parameters. For the initial value of each feature subset, random noise conforming to a Laplace distribution is generated, and the noise is synthesized with the initial value. The noise addition process is completed in a closed-state environment, ensuring that the noise addition operation itself does not leak any intermediate results. By adding noise, the final noisy value result satisfies the strict definition of differential privacy, ensuring that multiple data participants cannot collaboratively infer the original data information from the value assessment results.

[0085] S270. Based on the value of feature subsets, the Shapley value algorithm is used to calculate the contribution of each feature and aggregate the contributions of each feature to obtain a Shapley value vector as the basic value assessment result.

[0086] The Shapley value algorithm originates from the fair allocation algorithm in cooperative game theory and is used to quantify the marginal contribution of multiple participants in cooperation.

[0087] In this embodiment of the invention, based on the value evaluation results of each feature subset obtained in the aforementioned steps, the Shapley value algorithm is used to quantify the feature-level contribution. Specifically, according to the basic principles of cooperative game theory, the average marginal contribution of each feature in all possible feature combinations is calculated. The specific formula for calculating the contribution of the i-th feature is as follows:

[0088]

[0089] Where S is a feature subset, n is the number of features in the data, and v(S) is the value of the feature subset S to the preset business model.

[0090] To address the high dimensionality of financial data, optimization methods such as Monte Carlo sampling are employed to reduce computational complexity. After each participant calculates its contribution locally, the distributed computation results are aggregated through a secure aggregation protocol to form a complete Shapley value vector. The final contribution vector is standardized to ensure that the sum of the contributions of each feature is consistent with the overall improvement in model value, serving as an objective basis for assessing the basic value of data assets. The Shapley value algorithm provides a fair feature contribution allocation scheme, overcoming the subjectivity and opacity of traditional assessment methods.

[0091] Optionally, based on the value of the feature subset, the Shapley value algorithm is used to calculate the contribution of each feature, which further includes:

[0092] Calculate the sum of the absolute values ​​of the gradients corresponding to each feature, and based on the sum of the absolute values ​​of the gradients, select a set number of target features from all features;

[0093] Based on the value of the aforementioned feature subset, the Shapley value algorithm is used to calculate the contribution of each target feature.

[0094] In this optional embodiment, a specific method is provided for calculating the contribution of each feature based on the value of the feature subset using the Shapley value algorithm: After completing the feature subset value evaluation, a feature importance pre-screening process is first initiated. For each independent feature, the sum of its absolute gradient values ​​across multiple training batches during model training is calculated. Specifically, the gradient value of each feature during backpropagation is recorded, and the absolute value is taken and accumulated across samples according to the feature dimension to form the sum of the absolute gradient values ​​of each feature. The specific calculation formula is as follows:

[0095] Based on a preset screening ratio or absolute quantity threshold, all features are sorted in descending order of the sum of absolute gradient values, and the features with the highest ranking are selected as the target features.

[0096] Furthermore, based on the feature subset value evaluation results obtained from the aforementioned steps and the selected target feature set, the Shapley value algorithm is used for refined contribution calculation. First, a simplified feature set containing only the target features is constructed, significantly reducing the number of feature subsets that need to be evaluated. Then, for each target feature, its marginal contribution across all relevant feature subsets is calculated, i.e., the value increment brought by adding the feature to different subsets. The Shapley value for each target feature is obtained by weighted averaging of all possible marginal contribution values. Monte Carlo sampling can be used to further optimize computational efficiency during the calculation process, approximating the complete Shapley value calculation by randomly sampling feature permutations. The specific calculation formula is as follows:

[0097]

[0098] in, The feature subset of the sample, where M is the number of samplings and n is the number of features in the data. It is a feature subset The value of a pre-defined business model.

[0099] By combining feature pre-screening based on the sum of absolute gradient values ​​with the Shapley value algorithm, an efficient and accurate feature contribution evaluation system is constructed. This system not only solves the problem of excessive computational complexity of Shapley values ​​in high-dimensional feature environments, but also ensures the scientific rigor and fairness of the evaluation of important feature contributions.

[0100] S280: In response to a data transaction request initiated by a data requester, verify the compliance of the transaction through a smart contract, and execute the ownership transfer operation on the blockchain after the verification is passed.

[0101] Optionally, before responding to a data transaction request initiated by a data requester, verifying the compliance of the transaction through a smart contract, and executing the ownership transfer operation on the blockchain after successful verification, the process also includes:

[0102] Based on the timeliness factor, scarcity factor, and compliance factor corresponding to the original data, the basic value assessment result is dynamically adjusted to obtain the dynamic value of the encrypted data.

[0103] The timeliness factor, scarcity factor, and compliance factor mentioned above are obtained by analyzing and predicting historical transaction data and regulatory texts using machine learning models.

[0104] In this optional embodiment, specific steps are provided before responding to a data transaction request initiated by a data requester, verifying transaction compliance through a smart contract, and executing the ownership transfer operation on the blockchain after successful verification: Based on the basic value assessment results, a three-dimensional dynamic value adjustment mechanism is initiated. First, a dynamic adjustment model including timeliness factors, scarcity factors, and compliance factors is constructed, and the dynamic value is calculated using the following formula:

[0105]

[0106] Where V is the basic value assessment result, T is the timeliness factor, R is the scarcity factor, and C is the compliance factor. These are the weight coefficients for each factor.

[0107] The timeliness factor is calculated using an exponential decay model, taking into account the interval between the data update time and the current time. The specific calculation formula is as follows:

[0108]

[0109] Where t is the current time, For data update time, This is the attenuation coefficient.

[0110] The scarcity factor is calculated through market supply and demand analysis, taking into account the supply and demand of similar data in the current market. The specific calculation formula is as follows:

[0111]

[0112] in, D represents the baseline supply, and D represents the current market supply.

[0113] The compliance factor is calculated through multi-dimensional compliance checks, including elements such as data authorization integrity, compliance with the scope of use, and cross-border transfer compliance. The specific calculation formula is as follows:

[0114]

[0115] in, These are the scores for each compliance indicator. It's the weight.

[0116] The weight coefficients of each factor are obtained through training on historical transaction data, ensuring the scientific validity and adaptability of the adjustment model. Through a three-dimensional factor adjustment mechanism, real-time linkage between data value and the market environment is achieved, improving the market adaptability of value assessment.

[0117] Among them, the timeliness factor, scarcity factor, and compliance factor are obtained by analyzing and predicting historical transaction data and regulatory texts using machine learning models. The calculation of each dynamic factor employs intelligent prediction methods based on machine learning. For the timeliness factor, a Transformer model is used to analyze time series patterns in historical transaction data to predict the value decay patterns of different data categories. For the scarcity factor, time series analysis and market supply and demand models are combined, and reinforcement learning algorithms are used to dynamically adjust the scarcity assessment parameters. For the compliance factor, natural language processing technology is used to analyze the latest regulatory and policy texts, construct a compliance knowledge graph, and update compliance assessment standards in real time. Machine learning prediction improves the accuracy and timeliness of dynamic factor calculation, enabling rapid response to market and regulatory changes.

[0118] The technical solution of this invention employs a homomorphic encryption algorithm to encrypt the original data to be verified, obtaining ciphertext data. Multi-dimensional feature information is extracted from the ciphertext data, and homomorphic hashing is performed on each dimension of the feature information. The hash values ​​corresponding to the multiple dimensions of the feature information are combined to obtain an initial fingerprint. A cryptographic hashing algorithm is then used to hash the initial fingerprint to obtain a data fingerprint. The data fingerprint and the ownership information of the original data are uploaded to the blockchain for notarization. Each data participant, based on the number of participants, splits the ciphertext data into multiple data fragments through a secret sharing protocol, using multiplication... In each data shard, the triplet jointly calculates the value of each feature subset to the preset business model. Based on the value of the feature subset, the Shapley value algorithm is used to calculate the contribution of each feature and aggregate the contributions of each feature to obtain a Shapley value vector as the basic value assessment result. In response to the data requester's data transaction request, the transaction compliance is verified through a smart contract, and the ownership transfer operation is executed on the blockchain after verification. The Shapley value algorithm provides a fair feature contribution allocation scheme, overcoming the subjectivity and opacity of traditional value assessment methods.

[0119] Example 3

[0120] Figure 3 This is a schematic diagram of a data ownership confirmation device based on privacy computing provided in Embodiment 3 of the present invention. Figure 3 As shown, the device includes:

[0121] The data fingerprint construction module 310 is used by the data provider to encrypt the original data to be confirmed, obtain ciphertext data, and construct a data fingerprint based on the ciphertext data.

[0122] The data on-chain module 320 is used to upload the data fingerprint and the ownership information of the original data to the blockchain for evidence storage.

[0123] The data value assessment module 330 is used by multiple data participants to collaboratively perform multi-party privacy calculations based on the encrypted data, determine the contribution of each data feature to the preset business model, and determine the basic value assessment result based on the contribution.

[0124] The data ownership transfer module 340 is used to respond to data transaction requests initiated by data requesters, verify transaction compliance through smart contracts, and execute ownership transfer operations on the blockchain after verification.

[0125] The technical solution of this invention involves the data provider encrypting the original data to be confirmed, obtaining ciphertext data, and constructing a data fingerprint based on the ciphertext data. The data fingerprint and the ownership information of the original data are then uploaded to the blockchain for notarization. Multiple data participants collaboratively perform multi-party privacy computation based on the ciphertext data to determine the contribution of each data feature to a preset business model. Based on the contribution, a basic value assessment result is determined. Finally, in response to a data transaction request initiated by a data requester, the transaction compliance is verified through a smart contract. After successful verification, the ownership transfer operation is executed on the blockchain. This method of constructing data fingerprints based on ciphertext data and uploading them to the blockchain enables data ownership confirmation in a secure environment, ensuring that the original data does not leave the domain. Furthermore, data value assessment based on the contribution of data features to the business model improves the accuracy of value assessment compared to methods based on data volume and coverage.

[0126] Optionally, the data fingerprint building module 310 is specifically used for:

[0127] Homomorphic encryption algorithm is used to encrypt the original data to be confirmed, resulting in ciphertext data;

[0128] Multi-dimensional feature information is extracted from the encrypted data, and homomorphic hash operation is performed on each dimension of feature information. The hash values ​​corresponding to the feature information of multiple dimensions are combined to obtain the initial fingerprint.

[0129] The initial fingerprint is hashed using a cryptographic hash algorithm to obtain the data fingerprint.

[0130] Optional, the data value assessment module 330 includes:

[0131] A data sharding unit is used by each data participant to split the encrypted data into multiple data shards according to the number of data participants through a secret sharing protocol;

[0132] The value calculation unit is used to jointly calculate the value of each feature subset to the preset business model on each data shard using multiplication triples;

[0133] The evaluation result determination unit is used to calculate the contribution of each feature based on the value of the feature subset using the Shapley value algorithm, and aggregate the contribution of each feature to obtain a Shapley value vector as the basic value evaluation result.

[0134] Optionally, the data ownership confirmation device based on privacy computing also includes:

[0135] The value dynamic adjustment module is used to dynamically adjust the basic value assessment result based on the timeliness factor, scarcity factor, and compliance factor corresponding to the original data in response to the data transaction request initiated by the data requester, verify the compliance of the transaction through a smart contract, and execute the ownership transfer operation on the blockchain after the verification is passed, so as to obtain the dynamic value of the encrypted data.

[0136] The timeliness factor, scarcity factor, and compliance factor mentioned above are obtained by analyzing and predicting historical transaction data and regulatory texts using machine learning models.

[0137] Optionally, the cryptographic hash algorithm is a quantum-resistant SHA-3 hash function.

[0138] Optional, value calculation unit, specifically used for:

[0139] Using multiplication triples, the initial value of each feature subset to the preset business model is jointly calculated on each data shard;

[0140] By employing the Laplace noise function and introducing differential privacy noise into the initial value, the value of each feature subset to the preset business model is obtained.

[0141] Optionally, the evaluation result determination unit is specifically used for:

[0142] Calculate the sum of the absolute values ​​of the gradients corresponding to each feature, and based on the sum of the absolute values ​​of the gradients, select a set number of target features from all features;

[0143] Based on the value of the aforementioned feature subset, the Shapley value algorithm is used to calculate the contribution of each target feature.

[0144] The data ownership confirmation device based on privacy computing provided in the embodiments of the present invention can execute the data ownership confirmation method based on privacy computing provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the method.

[0145] In the technical solution of this invention, the information collected is information and data authorized by the user or fully authorized by all parties. The collection, storage, use, processing, transmission, provision, disclosure and application of related data all comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entry points for users to choose to authorize or refuse.

[0146] Example 4

[0147] According to embodiments of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.

[0148] Figure 4 A schematic diagram of an electronic device 10 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, application processors, blade application processors, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0149] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory 12 or a random access memory 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the read-only memory 12 or a computer program loaded from storage unit 18 into the random access memory 13. The random access memory 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, read-only memory 12, and random access memory 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0150] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0151] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, central processing units, graphics processing units, various special-purpose artificial intelligence computing chips, various processors running machine learning model algorithms, digital signal processors, and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as data ownership verification in privacy computing.

[0152] In some embodiments, data ownership verification for privacy computing can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 10 via read-only memory 12 and / or communication unit 19. When the computer program is loaded into random access memory 13 and executed by processor 11, one or more steps of data ownership verification for privacy computing described above can be performed. Alternatively, in other embodiments, processor 11 can be configured to perform data ownership verification for privacy computing by any other suitable means (e.g., by means of firmware).

[0153] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays, application-specific integrated circuits (ASICs), application-specific standard products (ASICs), systems-on-a-chip (SoCs), complex programmable logic devices, computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0154] Computer programs used to implement the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs can be executed entirely on a machine, partially on a machine, as a standalone software package partially on a machine and partially on a remote machine, or entirely on a remote machine or application.

[0155] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory, read-only memory, erasable programmable read-only memory, optical fibers, portable compact disk read-only memory, optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0156] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a cathode ray tube or liquid crystal display monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0157] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data application processors), or computing systems that include middleware components (e.g., application application processors), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0158] A computing system can include clients and applications. Clients and applications are generally geographically separated and typically interact via communication networks. The client-application relationship is established by computer programs running on the respective computers and having a client-application relationship with each other. An application can be a cloud application, also known as a cloud computing application or cloud host, which is a host product within the cloud computing application architecture to address the shortcomings of traditional physical hosts and virtual private services, such as high management difficulty and weak business scalability.

[0159] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0160] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A data ownership confirmation method based on privacy computing, characterized in that, include: The data provider encrypts the original data to be confirmed, obtaining ciphertext data, and constructs a data fingerprint based on the ciphertext data; The data fingerprint and the ownership information of the original data are uploaded to the blockchain for evidence storage. Multiple data participants collaborate to perform multi-party privacy computations based on the encrypted data, determine the contribution of each data feature to the preset business model, and determine the basic value assessment result based on the contribution. In response to a data transaction request initiated by a data demander, the system verifies the compliance of the transaction through a smart contract and executes the ownership transfer operation on the blockchain after the verification is successful.

2. The method according to claim 1, characterized in that, The data provider encrypts the original data to be confirmed, obtaining ciphertext data, and constructs a data fingerprint based on the ciphertext data, including: Homomorphic encryption algorithm is used to encrypt the original data to be confirmed, resulting in ciphertext data; Multi-dimensional feature information is extracted from the encrypted data, and homomorphic hash operation is performed on the feature information of each dimension. The hash values ​​corresponding to the feature information of multiple dimensions are combined to obtain the initial fingerprint. The initial fingerprint is hashed using a cryptographic hash algorithm to obtain the data fingerprint.

3. The method according to claim 1, characterized in that, Multiple data participants collaboratively perform multi-party privacy computations based on the encrypted data to determine the contribution of each data feature to a preset business model, and based on the contribution, determine a basic value assessment result, including: Each data participant, based on the number of data participants, splits the encrypted data into multiple data fragments using a secret sharing protocol; Using multiplication triples, the value of each feature subset to the preset business model is jointly calculated on each data shard; Based on the value of the aforementioned feature subset, the Shapley value algorithm is used to calculate the contribution of each feature, and the contribution of each feature is aggregated to obtain a Shapley value vector as the basic value assessment result.

4. The method according to claim 1, characterized in that, Before responding to a data transaction request initiated by a data requester, verifying the compliance of the transaction through a smart contract, and executing the ownership transfer operation on the blockchain after verification, the process also includes: Based on the timeliness factor, scarcity factor, and compliance factor corresponding to the original data, the basic value assessment result is dynamically adjusted to obtain the dynamic value of the encrypted data. The timeliness factor, scarcity factor, and compliance factor mentioned above are obtained by analyzing and predicting historical transaction data and regulatory texts using machine learning models.

5. The method according to claim 2, characterized in that, The cryptographic hash algorithm is the quantum-resistant SHA-3 hash function.

6. The method according to claim 3, characterized in that, Using multiplication triples, the value of each feature subset to the preset business model is jointly calculated on each data shard, including: Using multiplication triples, the initial value of each feature subset to the preset business model is jointly calculated on each data shard; By employing the Laplace noise function and introducing differential privacy noise into the initial value, the value of each feature subset to the preset business model is obtained.

7. The method according to claim 3, characterized in that, Based on the value of the aforementioned feature subset, the Shapley value algorithm is used to calculate the contribution of each feature, which also includes: Calculate the sum of the absolute values ​​of the gradients corresponding to each feature, and based on the sum of the absolute values ​​of the gradients, select a set number of target features from all features; Based on the value of the aforementioned feature subset, the Shapley value algorithm is used to calculate the contribution of each target feature.

8. A data ownership confirmation device based on privacy computing, characterized in that, include: The data fingerprint construction module is used by the data provider to encrypt the original data to be confirmed, obtain ciphertext data, and construct a data fingerprint based on the ciphertext data. The data on-chain module is used to upload the data fingerprint and the ownership information of the original data to the blockchain for evidence storage. The data value assessment module is used by multiple data participants to collaboratively perform multi-party privacy calculations based on the encrypted data, determine the contribution of each data feature to the preset business model, and determine the basic value assessment result based on the contribution. The data ownership transfer module is used to respond to data transaction requests initiated by data requesters, verify transaction compliance through smart contracts, and execute ownership transfer operations on the blockchain after verification.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the data ownership determination method based on privacy computing as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the data ownership method based on privacy computing as described in any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the data ownership determination method based on privacy computing according to any one of claims 1-7.

Images