Privacy-preserving advertising attribution method, system, device, and medium based on blockchain

Abstract

The present invention discloses a privacy-preserving blockchain-based advertising attribution method, system, apparatus, computer device, and storage medium. The method comprises: utilizing the immutable and privacy-preserving intersection characteristics of blockchain to allow participants in the attribution to obtain intersection data with any other party without leaking any data outside the intersection; the participants include multiple traffic providers and advertisers; utilizing the decentralization, immutability, consensus mechanism, and trusted execution environment of blockchain to associate the intersection data with advertiser data, perform attribution operations according to specific time windows and attribution logic, and enable each advertising platform, each advertiser, and each traffic provider to obtain attribution details. By leveraging the characteristics of blockchain, the method provided by the present invention effectively addresses the trust and privacy issues in the advertising attribution process.

Description

Technical Field

[0001] The invention belongs to the field of computer network security technology, and in particular relates to a privacy-protected advertising attribution method, system, device, computer equipment and storage medium based on blockchain. Background Art

[0002] In the digital marketing era, advertising has become an indispensable part of the business. One of the core challenges is advertising attribution, which involves evaluating the contribution of each channel's traffic to a conversion.

[0003] Without attribution, marketers have no way of understanding the true effectiveness of marketing campaigns and making informed marketing decisions for subsequent campaigns, which can easily lead to misalignment or overspending of advertising budgets. Therefore, attribution is considered one of the most critical aspects of digital advertising. Marketers need to employ appropriate attribution methods to effectively allocate budgets across different advertising channels and improve their return on investment. Traffic providers possess data on when and for which product ads users viewed, while advertisers possess user conversion data. Ad conversion attribution, commonly referred to in the advertising industry, essentially intersects traffic providers' impression and click data with advertisers' conversion data at the user level. Marketers then analyze the conversion data using an attribution model to derive attribution results. However, this process carries significant security risks and may infringe on the data privacy of both traffic providers and advertisers.

[0004] Depending on the attribution platform, advertising attribution can be categorized as third-party platform attribution, advertising platform attribution, or advertiser attribution. However, regardless of the attribution method, all raw data must be transmitted to the attribution party for attribution. This raises issues of trust and data privacy. The attribution party can not only falsify attribution but also exploit the data for profit. Although various countries have introduced data security laws and regulations, legislation alone cannot fully resolve privacy and trust issues. Therefore, improvements to existing attribution methods are necessary.

[0005] Blockchain is a specialized data structure introduced to address the double-spending issue in Bitcoin. Each block contains multiple transactions, and nodes on the chain are responsible for maintaining the block status and transactions. Essentially, it is a distributed ledger. Blockchains can be categorized into three types, public, private, and consortium, based on their openness and consensus mechanisms. Consensus is achieved by mutually untrusted nodes in a blockchain network reaching data consistency through mutually agreed-upon rules. Existing consensus mechanisms include Proof of Work (PoW), Proof of Stake (PoS), and Deposit-based Proof of Stake (DPOS). These mechanisms can also be adapted into new consensus mechanisms. Transactions in a blockchain are permanently recorded on the chain and shared with other nodes. Because each block contains the hash value of the previous block, transactions recorded on the chain are generally difficult to tamper with. Summary of the Invention

[0006] To address the shortcomings of the aforementioned prior art, the present invention provides a privacy-preserving blockchain-based advertising attribution method, system, apparatus, computer device, and storage medium. This method combines blockchain with advertising attribution, leveraging blockchain's decentralization, immutability, and consensus mechanism to address the trust issues inherent in existing attribution processes, ensuring the authenticity and credibility of the attribution process and results. Furthermore, privacy-preserving intersection and trusted execution environment technologies address privacy leaks during the attribution process, achieving the goal of privacy-preserving advertising attribution. Therefore, the approach provided by the present invention achieves the goal of trusted computing for advertising attribution.

[0007] The first object of the present invention is to provide a privacy-preserving advertising attribution method based on blockchain.

[0008] The second object of the present invention is to provide a privacy-preserving advertising attribution system based on blockchain.

[0009] The third object of the present invention is to provide a privacy-preserving advertising attribution device based on blockchain.

[0010] A fourth object of the present invention is to provide a computer device.

[0011] A fifth object of the present invention is to provide a storage medium.

[0012] The first object of the present invention can be achieved by adopting the following technical solutions:

[0013] A privacy-preserving advertising attribution method based on blockchain, comprising:

[0014] Leveraging the blockchain's immutability and privacy-preserving intersection features, participants in this attribution process can obtain the intersection data with any other party without leaking any data outside of the intersection. The participants include multiple traffic providers and advertisers.

[0015] By leveraging the decentralization, immutability, consensus mechanism, and trusted execution environment of blockchain, the intersection data is associated with the advertiser's data, and attribution operations are performed according to a specific time window and attribution logic, so that each advertising platform, each advertiser, and each traffic party can obtain attribution details.

[0016] Furthermore, the aforementioned use of the blockchain's immutable and private intersection characteristics allows the participants in this attribution to obtain the intersection data with any other party, including:

[0017] After the advertising platform receives the ads from each advertiser, the data storage machines of each traffic party related to the advertiser are added to the channel after identity authentication service. When the user generates data, the real-time evidence service is called. When the advertiser configures the attribution touchpoints on the front end, the storage machines of each traffic party combine the advertiser's identity with the attribution touchpoints to select a specific range of data as the attribution data.

[0018] Each party hashes the user ID of the attribution data to obtain a hash value of the user ID. Channel monitoring and the Idemix service in Hyperledger Fabric are activated, and each party sends the hash value of the user ID to the channel in the form of a transaction. The parties are the traffic providers and advertisers.

[0019] Each party obtains all transaction hash values ​​in the channel through the channel monitoring service and obtains the transaction content. Based on the transaction content, each party performs intersection calculation locally to obtain the intersection data.

[0020] After each party locally obfuscates the intersection data, it uploads the obfuscated data to the distributed storage system IPFS through the off-chain storage service; each party obtains the hash value returned by the distributed storage system IPFS and performs threshold encryption, and then uses the public key disclosed by the advertising platform to perform double encryption to obtain a double-encrypted hash value; each party uses the shared service within the channel to send the double-encrypted hash value and the ID registered on the advertising platform to the advertising platform.

[0021] Furthermore, the parties obtain all transaction hash values ​​in the channel through the channel monitoring service and obtain the transaction content, including:

[0022] Each party obtains all transaction hash values ​​in the channel through the channel monitoring service, removes its own transaction hash value and obtains the transaction hash value sent by other participants;

[0023] Each party obtains the transaction content based on the transaction hash value sent by other participating parties.

[0024] Furthermore, the double-encrypted hash value can only be decrypted by the advertising platform, and the threshold ciphertext after decryption by the advertising platform can correspond one-to-one with the corresponding registration ID.

[0025] Furthermore, by utilizing the decentralization, immutability, consensus mechanism, and trusted execution environment of the blockchain, the intersection data is associated with the advertiser data, and attribution operations are performed according to a specific time window and attribution logic, enabling each advertising platform, each advertiser, and each traffic party to obtain attribution details, including:

[0026] Based on the double-encrypted hash values of each advertiser and each traffic party obtained, the advertising platform uses the private key to decrypt and obtain the threshold ciphertext, and sends the threshold ciphertext to be shared within the channel. The attribution machine obtains the threshold ciphertexts of all participating parties;

[0027] The attribution machine decrypts the threshold ciphertext in the TEE trusted execution environment, and after decryption, obtains the IPFS hash value of the distributed storage system; according to the IPFS hash value of the distributed storage system, the off-chain storage service is called to obtain the corresponding obfuscated data; the obfuscated data is aligned according to the hash value of the user ID;

[0028] If there is an intersection between the aligned data and the advertiser conversion data, the data party closest to the conversion time is taken as the attribution contributor for this user, and the remaining data is discarded, where the attribution adopts the LTA model; the attribution machine takes [user ID hash value, threshold ciphertext] as the attribution result, and uploads all the corresponding relationships of this attribution to the distributed storage system IPFS. After achieving attribution consensus, the attribution result is transmitted to the advertising platform;

[0029] According to the correspondence between the threshold ciphertext and the registration ID, the advertising platform analyzes the attribution result, obtains the result of the user ID hash value and the contributing traffic party, and sends the result to the traffic party and the advertiser. Only the traffic party / advertiser with the private key can know the attribution result sent by the advertising platform.

[0030] Furthermore, the attribution machine decrypts the threshold ciphertext in the TEE trusted execution environment. The private key used for decryption is divided into M pieces and stored on M machines participating in this attribution respectively. Only when N machines are combined can this private key be restored for decryption. Let P be the attribution machine provided by the advertising platform, then P < N < M, where N is a positive integer greater than or equal to 3.

[0031] The second object of the present invention can be achieved by adopting the following technical solutions:

[0032] A privacy-preserving advertising attribution system based on blockchain, comprising an underlying architecture and a system architecture. The underlying architecture uses Hyperledger Fabric in a consortium chain, and in the Hyperledger Fabric, traffic parties and advertisers under an advertising platform are used as running nodes. The system architecture implements the privacy-preserving advertising attribution method according to any one of claims 1 to 6.

[0033] Furthermore, the system architecture includes identity authentication services, real-time evidence storage services, user dimension intersection services, off-chain storage services, in-channel sharing services, attribution services, and scalable services, among which:

[0034] The real-time evidence storage service is used for traffic providers, advertisers, and advertising platforms to join the alliance chain after passing the system's identity authentication. Traffic providers and advertisers store their respective data locally and perform hash calculations, and then upload the hash values ​​to the chain through the real-time evidence storage service.

[0035] The user dimension intersection service is used when traffic providers and advertisers store their data on the chain and then join the same channel to perform a user dimension intersection operation using private intersection. The non-time data in the intersection result is hashed, and the time data is obfuscated using a unified shift cipher.

[0036] The attribution service is used to add the attribution servers provided by the advertising platform, traffic source, and advertiser into the same channel. The advertising platform uses the in-channel sharing service to share the attribution tasks, rules, and hash values ​​with the traffic source and advertiser on the chain. The participating attribution server then obtains the obfuscated intersection data through the Go-IPFS-API and performs the attribution operation according to a specific consensus mechanism. After the attribution operation is completed, the attribution result is returned to the advertising platform, which then transmits the attribution result to the corresponding traffic source or advertiser through the in-channel sharing service.

[0037] The scalable service is used to dynamically configure according to the privacy protection requirements of traffic providers, advertisers or advertising platforms, including zero-knowledge proof, blind signature, time obfuscation mechanism in user-dimensional intersection operations, and incentive and penalty mechanism in attribution operations.

[0038] Furthermore, in the Hyperledger Fabric, multiple advertising platforms constitute an organization in the Hyperledger Fabric. Each organization includes a traffic department and an advertiser department. The traffic department includes multiple traffic parties under the advertising platform, and the advertiser department includes multiple advertisers under the advertising platform.

[0039] The third object of the present invention can be achieved by adopting the following technical solutions:

[0040] A privacy-preserving advertising attribution device based on blockchain, comprising:

[0041] The private intersection module is used to leverage the immutability and private intersection properties of the blockchain to allow participants in this attribution to obtain the intersection data with any other party without leaking any data outside the intersection; the participants include multiple traffic providers and advertisers;

[0042] The advertising attribution module is used to utilize the decentralization, immutability, consensus mechanism and trusted execution environment of the blockchain to associate the intersection data with the advertiser's data, and perform attribution operations according to a specific time window and attribution logic, so that each advertising platform, each advertiser and each traffic party can obtain attribution details.

[0043] The fourth object of the present invention can be achieved by adopting the following technical solutions:

[0044] A computer device includes a processor and a memory for storing a program executable by the processor. When the processor executes the program stored in the memory, the above-mentioned privacy-preserving advertising attribution method is implemented.

[0045] The fifth object of the present invention can be achieved by adopting the following technical solutions:

[0046] A storage medium stores a program, which, when executed by a processor, implements the above-mentioned privacy-preserving advertising attribution method.

[0047] The present invention has the following beneficial effects compared to the prior art:

[0048] 1. The method provided by this invention combines blockchain with advertising attribution, leveraging blockchain's decentralization, immutability, and consensus mechanism to address the trust issues inherent in existing attribution processes, ensuring the authenticity and credibility of the attribution process and results. Furthermore, privacy-preserving intersection and trusted execution environment technologies address privacy leaks during the attribution process, achieving the goal of privacy-preserving advertising attribution. Taking these two aspects into consideration, the method provided by this invention achieves the goal of trusted computing for advertising attribution by leveraging the characteristics of blockchain.

[0049] 2. The method provided by the present invention completes the advertising attribution operation without collecting the traffic party's data on the advertising platform, and the traffic party, advertiser and advertising platform can all obtain their respective attribution details.

[0050] 3. The present invention also provides a privacy-preserving blockchain-based advertising attribution system, a privacy-preserving architecture that allows traffic providers and advertisers to store data in real time on the blockchain network. The blockchain's decentralization, immutability, and corresponding consensus mechanism ensure the credibility of attribution results. Privacy protection methods such as privacy intersection and zero-knowledge proofs can also ensure data privacy. This invention differs from traditional attribution methods in that it allows multiple advertising platforms to participate and complete advertising attribution operations. Traffic providers, advertisers, and advertising platforms can all obtain their own attribution details. This architecture is designed for all types of traffic providers and advertisers, enabling them to implement attribution analysis while protecting their own commercial data. It aims to address issues of distrust among all parties involved in the attribution process, data leakage, and falsification of attribution results. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0052] Figure 1 This is a schematic diagram of the principle of the blockchain-based privacy-preserving advertising attribution method according to Example 1 of the present invention.

[0053] Figure 2 This is a flowchart of privacy intersection according to embodiment 1 of the present invention.

[0054] Figure 3 This is a flowchart of advertising attribution according to Example 1 of the present invention.

[0055] Figure 4 This is a schematic diagram of the HLF member architecture of Example 1 of the present invention.

[0056] Figure 5 This is a schematic diagram of the architecture of the privacy-preserving advertising attribution system based on blockchain according to Example 1 of the present invention.

[0057] Figure 6 This is a structural block diagram of a privacy-preserving advertising attribution device based on blockchain according to Example 2 of the present invention.

[0058] Figure 7 This is a structural block diagram of a computer device according to embodiment 3 of the present invention. DETAILED DESCRIPTION

[0059] To make the purpose, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention. It should be understood that the specific embodiments described are only used to explain this application and are not used to limit this application.

[0060] Example 1:

[0061] like Figure 1 As shown, this embodiment provides a privacy-preserving advertising attribution method based on blockchain, including privacy intersection and advertising attribution, wherein privacy intersection utilizes the tamper-proof and privacy intersection characteristics of blockchain to allow the participants of this attribution to obtain the intersection data between them and any party without leaking any data outside the intersection; the participants include multiple traffic parties and advertisers; advertising attribution utilizes the decentralization, immutability, consensus mechanism and trusted execution environment of blockchain to associate the intersection data with the advertiser data, and perform attribution operations according to a specific time window and attribution logic, so that each advertising platform, each advertiser and each traffic party can obtain attribution details.

[0062] (1) Private communication.

[0063] Further, such as Figure 2 As shown, step (1) specifically includes the following steps:

[0064] (1-1) After an advertiser places an ad on an advertising platform, the data storage machines of each traffic party associated with the advertiser are added to the channel after passing the identity authentication service and call the real-time evidence service when the user generates data. Once the advertiser configures the attribution touchpoints on the front end, the traffic party's storage machine combines the advertiser's identity with the attribution touchpoints to select a specific range of data as the attribution data. This can reduce communication volume and protect its own data to a certain extent.

[0065] (1-2) Each traffic provider and advertiser hashes the relevant data using the user ID, activates channel monitoring and the Idemix service in HLF, and sends the hash value to the channel in the form of a transaction. Because the Idemix service is composed of zero-knowledge proof and blind signature technology based on bilinear mapping, it has anonymity and unlinkability. Anonymity ensures that the identity of the trader is not disclosed, and unlinkability ensures that when a single identity sends multiple transactions, the system will not reveal that the transactions were sent by the same identity;

[0066] In (1-3), the parties within the channel can obtain all the transaction hash values within the channel through the listening service. After removing their own transaction hash values, they can obtain the transaction hash values sent by other parties. Based on the hash values sent by other parties, they can obtain their transaction contents, and each party can perform the intersection calculation locally, but they cannot know which party a certain data belongs to;

[0067] In (1-4), after local blurring of the intersection data, the parties upload the data to IPFS through an off-chain storage service. After threshold encryption of the hash value returned by IPFS, double encryption is performed using the public key publicly provided by the advertising platform. Then, the doubly encrypted hash value and the IDs registered by each party on the advertising platform are sent to the advertising platform through the shared service within the channel. Only the advertising platform can decrypt the doubly encrypted hash value, and at the same time, the threshold ciphertext decrypted by the advertising platform can correspond one by one with the corresponding registered IDs; in addition, the threshold ciphertext needs to be jointly decrypted by N attribution machines, and this process can ensure that the hash value of IPFS will not be obtained by unauthorized personnel.

[0068] (2) Advertising attribution.

[0069] To ensure the security of the attribution calculation process, the advertising attribution process is carried out by dedicated attribution machines in the TEE.

[0070] Furthermore, as Figure 3 shown, step (2) specifically includes the following steps:

[0071] (2-1) After obtaining the doubly encrypted hash value, the advertising platform decrypts it with its own private key to obtain the threshold ciphertext, and then sends the threshold ciphertext to be shared within the channel through the shared service within the channel. The attribution machines obtain the threshold ciphertexts of all parties;

[0072] (2-2) The attribution machines perform threshold decryption in the TEE trusted execution environment. The private key used for decryption is divided into M pieces and stored on M machines participating in this attribution respectively. Only N machines can jointly recover this private key for decryption. Let P be the attribution machine provided by the advertising platform, then it needs to satisfy P < N < M. This restriction can prevent the platform side from recovering the private key alone. The attribution machines obtain the IPFS hash value after threshold decryption, call the off-chain storage service to obtain the corresponding blurred data, and align the data according to the hash value of the user ID;

[0073] (2-3) Determine whether the aligned data overlaps with the advertiser's conversion data. If not, discard the relevant data. If overlaps with the advertiser's data, use the data closest to the conversion time as the attribution contributor for this user (assuming the attribution uses the LTA model), and discard the remaining data. The attribution machine uses [user ID hash value, threshold ciphertext] as the attribution result. All corresponding relationships for this attribution are uploaded to IPFS. After reaching an attribution consensus, the attribution result is transmitted to the advertising platform.

[0074] (2-4) Because the advertising platform has a correspondence between threshold ciphertext and registration IDs, it can easily parse the attribution results. The advertising platform obtains the result of [user ID hash value, contributing traffic source]. For threshold ciphertexts that do not have a corresponding relationship, they are considered to be traffic sources on other platforms and are discarded. The advertising platform then returns the results one by one: all results are encrypted with the advertiser's public key and sent to the channel. For the attribution results of a specific traffic source, the advertising platform only summarizes the user ID hash value related to it, encrypts it with the traffic source's public key, and sends it to the channel. Only the party with the private key can access the attribution results returned by the advertising platform.

[0075] Through the above-mentioned advertising attribution, each advertising platform, advertiser and traffic provider can obtain attribution details, that is: the advertising platform can know which traffic provider brings each user, the advertiser can know which traffic provider the users who generate their conversion behaviors come from, and the traffic provider can only know whether its own users have contributed to this attribution.

[0076] This embodiment also provides a privacy-preserving advertising attribution system based on blockchain, which includes an underlying architecture and a system architecture.

[0077] (1) Underlying architecture.

[0078] like Figure 4 As shown, this embodiment uses Hyperledger Fabric (HLF) in the consortium chain as the underlying architecture. In HLF, organizations and departments are abstractions at the upper level, and actual operations require coordination by nodes at the lower level. Organizations in HLF are composed of different advertising platforms, and each organization has two departments: the traffic department and the advertiser department. They are respectively composed of traffic parties and advertisers under the advertising platform as actual operating nodes. Generally, an advertising platform includes multiple traffic parties and multiple advertisers, but in attribution operations, data alignment is based on the conversion data of each advertiser.

[0079] (2)System architecture.

[0080] like Figure 5As shown in Figure 1, the system architecture includes seven services: identity authentication service, real-time evidence storage service, user dimension intersection service, off-chain storage service, channel sharing service, attribution service, and scalable service, among which:

[0081] (2-1) Identity authentication service.

[0082] The identity authentication service is initiated when an applicant applies to join the alliance chain. The identity of the joining node needs to be strictly reviewed to ensure that the applicant is one of the three parties: traffic provider, advertiser and advertising platform.

[0083] (2-2) Real-time evidence storage service.

[0084] Traffic providers, advertisers, and advertising platforms join the consortium chain after completing identity authentication. To ensure the security and reliability of the data used for attribution, traffic providers and advertisers must not only store their data locally but also perform a hash calculation. The hash value is then uploaded to the chain through a real-time evidence storage service. The blockchain's immutable nature greatly facilitates future audits.

[0085] (2-3) User dimension intersection service.

[0086] After traffic providers and advertisers store their data on-chain, they join the same channel and perform a private intersection operation on the user dimension. The non-time data in the intersection result is hashed, and the time data is obfuscated using a unified shift cipher. This process protects the private data of traffic providers and advertisers.

[0087] (2-4) Off-chain storage services.

[0088] In order to reduce data storage and transmission costs, each traffic party and advertiser will send the obfuscated intersection data to the distributed storage system IPFS through the Go-IPFS-API for off-chain storage. IPFS will return a unique hash value of the traffic party and advertiser based on the data content for the next retrieval.

[0089] (2-5) Sharing services within the channel.

[0090] This time, the traffic party establishes a channel with the advertising platform and shares their respective hash values ​​and agreed-upon attribution rules with the advertising platform. The advertising platform must ensure that the attribution rules uploaded by each traffic party and advertiser are consistent.

[0091] (2-6) Attribution services.

[0092] The advertising platform, along with the attribution servers provided by traffic providers and advertisers, joins the same channel. Using the in-channel sharing service, the advertising platform shares attribution tasks, rules, and hash values ​​on-chain with all traffic providers and advertisers. The participating attribution servers then retrieve the obfuscated intersection data via the Go-IPFS API and perform attribution according to a specific consensus mechanism. Once attribution is complete, the results are transmitted back to the advertising platform, which then communicates them back to the relevant traffic providers and advertisers via the in-channel sharing service.

[0093] (2-7) Scalable services.

[0094] This service can be dynamically configured based on the privacy protection needs of users (generally traffic providers, advertisers, and advertising platforms). It includes zero-knowledge proofs, blind signatures, and time obfuscation mechanisms in user-dimensional intersection operations, as well as incentive and penalty mechanisms in attribution operations. The functions implemented include:

[0095] (a) Protect the identity of the data owner.

[0096] When each party sends the hash result into the channel, they use zero-knowledge proof and blind signature technology to achieve anonymous transactions. All users' hash values ​​are then shared on the blockchain, and each party can simply compare these hash values ​​to determine the intersection data with any other party without revealing who actually owns the data.

[0097] (b) Protect the privacy information of “user click / conversion time”.

[0098] The system uses an event obfuscation mechanism. The input is a series of time, and the output is the sequence of each time. Outsiders cannot know the specific time through the sequence.

[0099] (c) Whether there is any dishonest behavior on the part of the traffic provider or the server provided by the advertiser.

[0100] For example, if malicious actors attempt to sabotage the attribution process and produce incorrect attribution results, they can use the incentive and penalty service. Each party is required to stake a certain amount of tokens when joining the consortium chain, and this staked tokens are associated with credibility. If dishonest behavior occurs, the staked tokens will be lost and credibility will be reduced.

[0101] This embodiment utilizes a consensus mechanism based on trust-based dynamic incentives within the system architecture and introduces a node reputation mechanism. Nodes are categorized into four levels: untrustworthy, general, trusted, and prioritized. Node reputations are dynamically adjusted. If a node engages in dishonest behavior, its reputation is lowered and its staked tokens are confiscated. This incentive mechanism can regulate node behavior to a certain extent and improve the robustness of the system.

[0102] The system architecture in this embodiment can implement the above-mentioned privacy-preserving advertising attribution method.

[0103] Those skilled in the art will appreciate that all or part of the steps in the method for implementing the above embodiments may be completed by instructing related hardware through a program, and the corresponding program may be stored in a computer-readable storage medium.

[0104] It should be noted that although the method operations of the above embodiments are described in a particular order in the accompanying drawings, this does not require or imply that the operations must be performed in this particular order, or that all of the illustrated operations must be performed to achieve the desired results. Rather, the depicted steps may be performed in a different order. Additionally or alternatively, certain steps may be omitted, multiple steps may be combined into a single step, and / or a single step may be broken down into multiple steps.

[0105] Example 2:

[0106] like Figure 6 As shown, this embodiment provides a privacy-preserving advertising attribution device based on blockchain, which includes a privacy intersection module 601 and an advertising attribution module 602, wherein:

[0107] The private intersection module 601 is used to utilize the immutability and private intersection characteristics of the blockchain to allow participants in this attribution to obtain the intersection data with any other party without leaking any data outside the intersection; the participants include multiple traffic providers and advertisers;

[0108] The advertising attribution module 602 is used to utilize the decentralization, immutability, consensus mechanism and trusted execution environment of the blockchain to associate the intersection data with the advertiser data, and perform attribution operations according to a specific time window and attribution logic, so that each advertising platform, each advertiser and each traffic party can obtain attribution details.

[0109] The specific implementation of each module in this embodiment can be found in the above-mentioned embodiment 1, and will not be described one by one here; it should be noted that the device provided in this embodiment is only illustrated by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure can be divided into different functional modules to complete all or part of the functions described above.

[0110] Example 3:

[0111] This embodiment provides a computer device, which can be a computer, such as Figure 7As shown, a processor 702, a memory, an input device 703, a display 704, and a network interface 705 are connected via a system bus 701. The processor is used to provide computing and control capabilities. The memory includes a non-volatile storage medium 706 and an internal memory 707. The non-volatile storage medium 706 stores an operating system, a computer program, and a database. The internal memory 707 provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. When the processor 702 executes the computer program stored in the memory, the privacy-preserving advertising attribution method of the above-mentioned embodiment 1 is implemented as follows:

[0112] Leveraging the blockchain's immutability and privacy-preserving intersection features, participants in this attribution process can obtain the intersection data with any other party without leaking any data outside of the intersection. The participants include multiple traffic providers and advertisers.

[0113] By leveraging the decentralization, immutability, consensus mechanism, and trusted execution environment of blockchain, the intersection data is associated with the advertiser's data, and attribution operations are performed according to a specific time window and attribution logic, so that each advertising platform, each advertiser, and each traffic party can obtain attribution details.

[0114] Example 4:

[0115] This embodiment provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the privacy-preserving advertising attribution method of the above-mentioned embodiment 1 is implemented as follows:

[0116] Leveraging the blockchain's immutability and privacy-preserving intersection features, participants in this attribution process can obtain the intersection data with any other party without leaking any data outside of the intersection. The participants include multiple traffic providers and advertisers.

[0117] By leveraging the decentralization, immutability, consensus mechanism, and trusted execution environment of blockchain, the intersection data is associated with the advertiser's data, and attribution operations are performed according to a specific time window and attribution logic, so that each advertising platform, each advertiser, and each traffic party can obtain attribution details.

[0118] It should be noted that the computer-readable storage medium of the present embodiment may be a computer-readable signal medium or a computer-readable storage medium or any combination thereof. The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof.

[0119] In summary, the method provided by the present invention combines blockchain with advertising attribution, allowing traffic providers and advertisers to store data in real time on the blockchain network. The blockchain's decentralization, immutability, and corresponding consensus mechanism ensure the credibility of the attribution results. Privacy protection methods such as privacy intersection and zero-knowledge proofs can also ensure data privacy. The present invention also provides a blockchain-based privacy-preserving advertising attribution system. Unlike traditional attribution methods, this system allows multiple advertising platforms to participate and completes advertising attribution operations without collecting traffic provider data. Furthermore, traffic providers, advertisers, and advertising platforms all receive their own attribution details. This architecture is designed for all types of traffic providers and advertisers, enabling them to implement attribution analysis while protecting their own business data. It aims to address issues such as distrust among all parties involved in the attribution process, data leakage, and falsification of attribution results.

[0120] The above is only a preferred embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes based on the technical solution and inventive concept of the present invention within the scope disclosed by the present invention, which falls within the scope of protection of the present invention.

Claims

1. A privacy-preserving advertising attribution method based on blockchain, characterized in that: The method comprises: Leveraging the blockchain's immutability and privacy-preserving intersection features, participants in this attribution process can obtain the intersection data with any other party without leaking any data outside of the intersection. The participants include multiple traffic providers and advertisers. Leveraging the decentralization, immutability, consensus mechanism, and trusted execution environment of blockchain, the intersection data is associated with advertiser data, and attribution operations are performed according to specific time windows and attribution logic, so that each advertising platform, each advertiser, and each traffic source can obtain attribution details; The aforementioned use of the blockchain's immutable and private intersection characteristics allows the participants in this attribution to obtain the intersection data with any other party, including: After the advertising platform receives the ads from each advertiser, the data storage machines of each traffic party related to the advertiser are added to the channel after identity authentication service. When the user generates data, the real-time evidence service is called. When the advertiser configures the attribution touchpoints on the front end, the storage machines of each traffic party combine the advertiser's identity with the attribution touchpoints to select a specific range of data as the attribution data. Each party hashes the user ID of the attribution data to obtain a hash value of the user ID. Channel monitoring and the Idemix service in Hyperledger Fabric are activated, and each party sends the hash value of the user ID to the channel in the form of a transaction. The parties are the traffic providers and advertisers. Each party obtains all transaction hash values ​​in the channel through the channel monitoring service and obtains the transaction content. Based on the transaction content, each party performs intersection calculation locally to obtain the intersection data. After each party locally obfuscates the intersection data, it uploads the obfuscated data to the distributed storage system IPFS through the off-chain storage service; each party obtains the hash value returned by the distributed storage system IPFS and performs threshold encryption, and then uses the public key disclosed by the advertising platform to perform double encryption to obtain a double-encrypted hash value; each party uses the shared service within the channel to send the double-encrypted hash value and the ID registered on the advertising platform to the advertising platform.

2. The privacy protection advertising attribution method according to claim 1, characterized in that: The parties obtain all transaction hash values ​​in the channel through the channel monitoring service and obtain the transaction content, including: Each party obtains all transaction hash values ​​in the channel through the channel monitoring service, removes its own transaction hash value and obtains the transaction hash value sent by other participants; Each party obtains the transaction content based on the transaction hash value sent by other participants.

3. The privacy-preserving advertising attribution method according to claim 1, characterized in that: The double-encrypted hash value can only be decrypted by the advertising platform, and the threshold ciphertext decrypted by the advertising platform can correspond one-to-one with the corresponding registration ID.

4. The privacy-preserving advertising attribution method according to any one of claims 1 to 3, wherein: The blockchain utilizes decentralization, immutability, consensus mechanism, and trusted execution environment to associate the intersection data with advertiser data, and performs attribution operations according to specific time windows and attribution logic, so that each advertising platform, each advertiser, and each traffic source can obtain attribution details, including: Based on the double-encrypted hash values ​​of each advertiser and traffic source, the advertising platform uses the private key to decrypt the threshold ciphertext and sends the threshold ciphertext to the channel for sharing. The attribution machine then obtains the threshold ciphertext of all participants. The attribution machine decrypts the threshold ciphertext in the TEE trusted execution environment, and after decryption, obtains the IPFS hash value of the distributed storage system; according to the IPFS hash value of the distributed storage system, it calls the off-chain storage service to obtain the corresponding obfuscated data; the obfuscated data is aligned according to the hash value of the user ID. If there is an intersection between the aligned data and the advertiser conversion data, the data party closest to the conversion time is taken as the attribution contributor of this user, and the remaining data is discarded, where the attribution uses the LTA model; the attribution machine takes [user ID hash value, threshold ciphertext] as the attribution result, and uploads all the corresponding relationships of this attribution to the IPFS of the distributed storage system. After reaching the attribution consensus, the attribution result is transmitted to the advertising platform. According to the corresponding relationship between the threshold ciphertext and the registration ID, the advertising platform analyzes the attribution result to obtain the result of the user ID hash value and the contributing traffic party, and sends the result to the traffic party and the advertiser. Only the traffic party / advertiser with the private key can know the attribution result sent by the advertising platform.

5. The privacy-preserving advertising attribution method according to claim 4, characterized in that: The attribution machine decrypts the threshold ciphertext in the TEE trusted execution environment. The private key used for decryption is divided into M pieces and stored on M machines participating in this attribution respectively. Only when N machines are combined can this private key be restored for decryption. Let P be the attribution machine provided by the advertising platform, then P < N < M, where N is a positive integer greater than or equal to 3.

6. A privacy-preserving advertising attribution system based on blockchain, characterized in that: The system includes a bottom-layer architecture and a system architecture. The bottom-layer architecture uses Hyperledger Fabric in the consortium chain, and uses the traffic parties and advertisers under the advertising platform as running nodes in the Hyperledger Fabric; the system architecture implements the privacy-protected advertising attribution method described in any one of claims 1 to 5.

7. The privacy-preserving advertising attribution system according to claim 6, wherein: The system architecture includes an identity authentication service, a real-time evidence storage service, a user dimension intersection service, an off-chain storage service, an in-channel sharing service, an attribution service, and an extensible service, where: The real-time evidence storage service is used for traffic parties, advertisers, and the advertising platform to join the consortium chain after passing the system's identity authentication. The traffic parties and advertisers locally store their respective data and perform hash calculations, and then upload the hash values to the chain through the real-time evidence storage service. The user dimension intersection service is used for when the traffic parties and advertisers store and upload the data they own, and then join the same channel to perform the intersection operation of the user dimension using private intersection. Hash the non-time data in the intersection result, and scramble the time data with a unified shift cipher. The attribution service is used for adding the attribution servers provided by the advertising platform, traffic parties, and advertisers to the same channel. The advertising platform uses the in-channel sharing service to share the attribution tasks, rules, and hash values on the chain with the traffic parties and advertisers. Then, the participating attribution servers obtain the scrambled intersection data through the Go-IPFS-API, perform attribution operations according to a specific consensus mechanism. After completing the attribution operation, the attribution result is sent back to the advertising platform, and the advertising platform uses the in-channel sharing service to send the attribution result to the corresponding traffic party or advertiser. The scalable service is used to dynamically configure according to the privacy protection requirements of traffic providers, advertisers or advertising platforms, including zero-knowledge proof, blind signature, time obfuscation mechanism in user-dimensional intersection operations, and incentive and penalty mechanism in attribution operations.

8. The privacy-preserving advertising attribution system according to any one of claims 6 to 7, characterized in that: In the Hyperledger Fabric, multiple advertising platforms constitute an organization in the Hyperledger Fabric. Each organization includes a traffic department and an advertiser department. The traffic department includes multiple traffic parties under the advertising platform, and the advertiser department includes multiple advertisers under the advertising platform.

9. A privacy-preserving advertising attribution device based on blockchain, characterized in that: The device comprises: The private intersection module is used to leverage the immutability and private intersection properties of the blockchain to allow participants in this attribution to obtain the intersection data with any other party without leaking any data outside the intersection; the participants include multiple traffic providers and advertisers; An advertising attribution module, which leverages the decentralization, immutability, consensus mechanism, and trusted execution environment of blockchain to associate the intersection data with advertiser data and perform attribution operations according to a specific time window and attribution logic, so that each advertising platform, each advertiser, and each traffic source can obtain attribution details; The aforementioned use of the blockchain's immutable and private intersection characteristics allows the participants in this attribution to obtain the intersection data with any other party, including: After the advertising platform receives the ads from each advertiser, the data storage machines of each traffic party related to the advertiser are added to the channel after identity authentication service. When the user generates data, the real-time evidence service is called. When the advertiser configures the attribution touchpoints on the front end, the storage machines of each traffic party combine the advertiser's identity with the attribution touchpoints to select a specific range of data as the attribution data. Each party hashes the user ID of the attribution data to obtain a hash value of the user ID. Channel monitoring and the Idemix service in Hyperledger Fabric are activated, and each party sends the hash value of the user ID to the channel in the form of a transaction. The parties are the traffic providers and advertisers. Each party obtains all transaction hash values ​​in the channel through the channel monitoring service and obtains the transaction content. Based on the transaction content, each party performs intersection calculation locally to obtain the intersection data. After each party locally obfuscates the intersection data, it uploads the obfuscated data to the distributed storage system IPFS through the off-chain storage service; each party obtains the hash value returned by the distributed storage system IPFS and performs threshold encryption, and then uses the public key disclosed by the advertising platform to perform double encryption to obtain a double-encrypted hash value; each party uses the shared service within the channel to send the double-encrypted hash value and the ID registered on the advertising platform to the advertising platform.

Images