Method and system for evaluating product value based on blockchain

Abstract

The embodiments of this specification provide a blockchain-based method and system for assessing product value, which can be used to perform product valuation while protecting user privacy. This method includes: a client submitting a target transaction to a blockchain network, in response to a user's query request for a target product, to invoke a product valuation contract. The target product is accompanied by a compensation agreement, and the target transaction includes the target product's product information and the user's user information. The blockchain network then executes the product valuation contract based on the target transaction. Based on the product and user information, the product valuation contract determines the user's valuation of the target product and provides it to the client. Optionally, the user information is encrypted, and the product valuation contract includes a private contract portion. The blockchain network can load the encrypted user information and the private contract portion into a TEE, decrypt the encrypted user information within the TEE, and execute the private contract portion.

Description

Technical Field

[0001] One or more embodiments of this specification relate to the field of blockchain technology, and more particularly, to a method and system for evaluating product value based on blockchain. Background Art

[0002] For target products with indemnity agreements (e.g., insurance products), in order to protect the vital interests of both supply and demand sides, it is usually necessary to evaluate the value of the product based on multiple factors (e.g., product information and company operating information).

[0003] Traditionally, fixed formulas are used to evaluate the value of a target product. Therefore, a more flexible solution for evaluating product value is needed. Summary of the Invention

[0004] One or more embodiments of this specification describe a blockchain-based method and system for evaluating product value, which can achieve flexible valuation based on different needs of different people, and can achieve transparency, openness, and auditability of the product valuation process.

[0005] First, a blockchain-based method for evaluating product value is provided, including:

[0006] In response to a user's query request for a target product, the client submits a target transaction to the blockchain network that invokes a product valuation contract, wherein the target product is accompanied by a compensation agreement; the target transaction includes product information of the target product and user information of the user; and the product information includes agreement information of the compensation agreement.

[0007] The blockchain network executes the product valuation contract based on the target transaction, wherein the product valuation contract determines a product valuation of the target product for the user based on the product information and the user information;

[0008] The blockchain network provides the product valuation to the client.

[0009] In a second aspect, a device for evaluating product value based on blockchain is provided, comprising: a client and a blockchain network;

[0010] The client is configured to submit a target transaction for invoking a product valuation contract to the blockchain network in response to a user's query request for a target product, wherein the target product is accompanied by a compensation agreement; the target transaction includes product information of the target product and user information of the user; and the product information includes agreement information of the compensation agreement;

[0011] The blockchain network is configured to execute the product valuation contract based on the target transaction, wherein the product valuation contract determines a product valuation of the target product for the user based on the product information and the user information;

[0012] The blockchain network is also used to provide the product valuation to the client.

[0013] According to a third aspect, a computer storage medium is provided, on which a computer program is stored. When the computer program is executed in a computer, the computer is caused to execute the method according to the first aspect.

[0014] In a fourth aspect, a computing device is provided, comprising a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the method of the first aspect is implemented.

[0015] One or more embodiments of this specification provide a blockchain-based product valuation method and system. This method evaluates the value of a target product by executing a pre-deployed product valuation contract within the blockchain network, ensuring transparency, openness, and auditability in the product valuation process. Furthermore, the product valuation contract determines the target product's valuation for the current user based on product and user information, enabling flexible, personalized valuation. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions of the embodiments of this specification, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0017] Figure 1 Schematic diagrams for creating and calling smart contracts provided in this manual;

[0018] Figure 2 A schematic diagram of an implementation scenario provided for one embodiment of this specification;

[0019] Figure 3 A method interaction diagram illustrating a first valuation contract deployment according to one embodiment;

[0020] Figure 4 An interaction diagram illustrating a method for deploying a second valuation contract according to one embodiment;

[0021] Figure 5 A schematic diagram of an incremental training method according to one embodiment is shown;

[0022] Figure 6An interaction diagram illustrating a method for deploying a second valuation contract according to another embodiment;

[0023] Figure 7 A schematic diagram of an incremental training method according to another embodiment is shown;

[0024] Figure 8 An interactive diagram illustrating a method for evaluating product value based on blockchain according to one embodiment;

[0025] Figure 9 A schematic diagram illustrating a method for executing a product valuation contract according to one embodiment is shown;

[0026] Figure 10 A schematic diagram of a system for evaluating product value based on blockchain according to one embodiment is shown. DETAILED DESCRIPTION

[0027] The solution provided in this specification is described below in conjunction with the accompanying drawings.

[0028] As previously mentioned, traditional technologies typically use fixed formulas to assess the value of target products with accompanying compensation agreements (e.g., insurance products). The product values ​​assessed using this approach are highly homogeneous and cannot be customized for individual users. However, since the probability of the compensation agreement being satisfied varies for different purchasing users, the value of the target product should also vary accordingly. To address this issue, the inventors of this application propose evaluating the value of the target product by executing a product valuation contract pre-deployed on a blockchain network. The product valuation contract here is a smart contract used to assess product value.

[0029] Before describing the solutions provided by the embodiments of this specification, a brief explanation of concepts such as blockchain and smart contracts is given.

[0030] It should be noted that the blockchain described in this specification may specifically refer to a P2P network system with a distributed data storage structure in which each node reaches a consensus mechanism. The data in the blockchain is distributed in "blocks" that are connected in time. The latter block may contain a data summary of the previous block, and depending on the specific consensus mechanism (such as POW, POS, DPOS or PBFT), a full backup of the data of all or part of the nodes is achieved.

[0031] Real data generated in the physical world can be constructed into a standard transaction format supported by the blockchain, and then published to the blockchain. Each node in the blockchain will conduct consensus verification on the received transactions. After the verification is passed, the node serving as the accounting node in the blockchain will package the transaction into a block and store it persistently in the blockchain.

[0032] Among them, the consensus algorithms supported in the blockchain may include: Proof of Work (POW), Proof of Stake (POS), Delegated Proof of Stake (DPOS), and Practical Byzantine Fault Tolerance (PBFT) and other consensus algorithms.

[0033] Regardless of the consensus algorithm used by the blockchain, the accounting nodes in this round can package the received transactions to generate a new block and send the generated new block or its header to other nodes for consensus verification. If other nodes receive the new block or its header and verify that it is correct, they can append it to the end of the existing blockchain, thus completing the blockchain's accounting process. While other nodes are verifying the new block or header sent by the accounting node, they can also execute the transactions contained in that block.

[0034] Those skilled in the art are well aware that, because blockchains operate under a consensus mechanism, data stored in the blockchain is difficult to tamper with by any node. For example, in a blockchain using Proof-of-Work consensus, an attack requiring at least 51% of the network's computing power is required to tamper with the data. Therefore, blockchains offer unparalleled data security and anti-tampering features that other centralized database systems cannot match. Therefore, data stored in a distributed database on the blockchain cannot be attacked or tampered with, thus ensuring the authenticity and reliability of the data stored in the distributed database on the blockchain.

[0035] Example types of blockchains may include public blockchains, private blockchains, and consortium blockchains.

[0036] In a public blockchain, the consensus process is controlled by the nodes of the consensus network. For example, hundreds, thousands, or even millions of entities can collaborate on a public blockchain, each operating at least one node. Therefore, a public blockchain can be thought of as a public network relative to the participating entities.

[0037] Typically, public blockchains support public transactions. Public transactions are shared with all nodes within the public blockchain and stored in a global blockchain. The global blockchain is a blockchain that is replicated across all nodes. This means that all nodes are in a completely consistent state with respect to the global blockchain. To achieve consensus (e.g., agreeing to add a block to the blockchain), a consensus protocol is implemented within the public blockchain.

[0038] Typically, a private blockchain is provided to a specific entity, which centrally controls read and write permissions. This entity controls which nodes can participate in the blockchain. For this reason, private blockchains are often referred to as permissioned networks, which impose restrictions on who is allowed to participate and their level of participation (e.g., only in certain transactions). Various types of access control mechanisms can be used (e.g., existing participants vote to add new entities, and regulators can control admission).

[0039] Typically, consortium blockchains are private among participating entities. In a consortium blockchain, the consensus process is controlled by an authorized set of nodes (consortium member nodes), one or more of which are operated by the corresponding entity (e.g., an enterprise). For example, a consortium consisting of ten (10) entities (e.g., enterprises) can operate a consortium blockchain, with each entity operating at least one node in the consortium blockchain. Therefore, a consortium blockchain can be considered a private network with respect to the participating entities. In some examples, each entity (node) must sign each block in order for the block to be valid and to add the valid block to the blockchain. In some examples, at least a subset of the entities (nodes) (e.g., at least 7 entities) must sign each block in order for the block to be valid and to add the valid block to the blockchain.

[0040] It is contemplated that the embodiments provided herein can be implemented in any suitable type of blockchain.

[0041] In practical applications, public, private, and consortium blockchains all offer smart contract functionality. Smart contracts on a blockchain are contracts that can be triggered and executed by transactions on the blockchain. Smart contracts can be defined in code.

[0042] Taking Ethereum as an example, users can create and invoke complex logic within the Ethereum network. As a programmable blockchain, Ethereum's core is the Ethereum Virtual Machine (EVM), which runs on every Ethereum node. The EVM is a Turing-complete virtual machine that enables the implementation of complex logic. When users publish and invoke smart contracts within Ethereum, they execute them on the EVM. In reality, the EVM directly runs virtual machine code (virtual machine bytecode, hereinafter referred to as "bytecode"), so smart contracts deployed on the blockchain can be bytecode.

[0043] The following first explains the publishing process of the smart contract.

[0044] For example, when a user sends a transaction to the Ethereum network containing the creation of a smart contract, each node can execute the transaction in the EVM. The From field of the transaction records the address of the account that initiated the creation of the smart contract, the Data field of the transaction stores the contract code, which can be bytecode, and the To field of the transaction contains a null account. Once the nodes reach consensus through the consensus mechanism, the smart contract is successfully created and can be subsequently invoked by users.

[0045] After a smart contract is created, a contract account corresponding to the smart contract appears on the blockchain with a specific address. The contract code and account storage are stored in the contract account's account storage. The smart contract's behavior is controlled by the contract code, while the smart contract's account storage stores the contract's state. In other words, a smart contract creates a virtual account on the blockchain that contains the contract code and account storage.

[0046] As mentioned above, the Data field of a transaction that creates a smart contract may contain the bytecode for that smart contract. Bytecode consists of a series of bytes, each of which identifies an operation. For reasons of development efficiency and readability, developers can choose to write smart contract code in a high-level language rather than directly writing bytecode. Examples of high-level languages ​​include Solidity, Serpent, and C++. Smart contract code written in a high-level language can be compiled using a compiler to generate bytecode that can be deployed on the blockchain.

[0047] Taking the Solidity language as an example, contract code written in it is very similar to classes in object-oriented programming languages. A contract can declare a variety of members, including state variables, functions, function modifiers, events, etc. State variables are values ​​permanently stored in the smart contract's account storage field to preserve the contract's state.

[0048] The following describes the calling process of the smart contract.

[0049] Taking the Ethereum network as an example, once a user sends a transaction containing information about calling a smart contract, each node can execute the transaction in the EVM. The From field of the transaction records the address of the account initiating the smart contract call, the To field records the address of the called smart contract, and the Data field records the method and parameters used to call the smart contract. After calling a smart contract, the account status of the contract account may change.

[0050] Subsequently, the smart contract caller can view the account status of the contract account through the connected blockchain node.

[0051] Smart contracts can be executed independently on each node in the blockchain in a prescribed manner, and all execution records and data are stored on the blockchain. Therefore, when such a transaction is executed, the blockchain will store transaction credentials that cannot be tampered with or lost.

[0052] The schematic diagram of creating and calling smart contracts is as follows Figure 1 As shown in Figure 2. Creating a smart contract in Ethereum requires writing the smart contract, converting it into bytecode, and deploying it to the blockchain. Calling a smart contract in Ethereum involves initiating a transaction directed to the smart contract address. The EVMs of each node can execute this transaction separately, distributing the smart contract code across the virtual machines of every node in the Ethereum network.

[0053] The following first describes the solutions provided in the embodiments of this specification in general.

[0054] Figure 2 A schematic diagram of an implementation scenario provided for one embodiment of this specification. Figure 2 In this example, a product valuation contract is deployed in the blockchain network. This contract can be built based on a pre-trained valuation model and is used to determine the user-specific valuation of a target product based on the target product's product information and user information. The target product here comes with an indemnity agreement, which can be, for example, an insurance product.

[0055] In a specific example, the above-mentioned product valuation contract includes a first valuation contract and / or a second valuation contract, wherein the first valuation logic in the first valuation contract is constructed based on a general valuation formula; and the second valuation logic in the second valuation contract is constructed based on a trained risk assessment model.

[0056] Figure 2 Each client in the system can correspond to a different insurance company (hereinafter referred to as an insurance company), which can provide users with services such as insurance application, policy cancellation, and claims settlement. Taking insurance application services as an example, any client can first receive a user's query request for a target product and then submit a target transaction to the blockchain network to invoke the product valuation contract. The blockchain network can execute the first valuation contract and / or the second valuation contract based on the target transaction and obtain one or two processing results. Finally, based on one or two processing results, the product valuation is determined and provided to the client, which can then provide insurance services to the user based on the product valuation.

[0057] The following describes the deployment process of the first valuation contract.

[0058] Figure 3 A diagram illustrating a method interaction of deploying a first valuation contract according to one embodiment is shown. Figure 3 As shown, the method may include at least the following steps.

[0059] Step 302: The client obtains the general valuation formula and creates a corresponding UML model for it.

[0060] The general valuation formula here can be used to evaluate the value of the target product to users in an overall manner. This general valuation formula is unchanging and is derived from general situations.

[0061] Taking the above-mentioned target product as an insurance product, and the insurance product specifically as a life insurance product as an example, the implementation principle of the corresponding general valuation formula can be: referring to the empirical life table of China's life insurance industry (2010-2013), first calculate the present value of the future losses of the insurance product (assuming simple compound interest), then calculate the mathematical expectation of the present value of the future losses of the insurance product, and then determine the corresponding insurance premium (i.e. product valuation) based on the data expectation.

[0062] For example, suppose user x purchases an insurance product with a coverage of 1 unit and a lump sum payment method. Based on the insurance interest, the present value of future losses is X = v T , where v = 1 / (1+i), i represents the annual interest rate, and T represents the future life expectancy of the insured. Therefore, the lump sum premium for this insurance product is:

[0063]

[0064] Where ω is the limit age, f T (t) represents the probability density function of T, because f cannot be described by an analytical function T (t), so consider discretizing the above formula. Specifically, assuming that the present value of the future loss of the insurance product is X = v K+1 , where K = [T], then the discretization of formula 1 can be:

[0065]

[0066] This shows that under the assumption of uniform death distribution, Thus, we can calculate A x , you can get the lump sum premium of this insurance product.

[0067] Furthermore, in step 302 , a UML modeling design tool may be used to construct a UML model corresponding to the general valuation formula.

[0068] Step 304: The client constructs a first valuation logic according to the UML model.

[0069] Specifically, the UML model may be converted into high-level language code, such as C++ code, and then the first valuation logic may be constructed based on the high-level language code.

[0070] In step 306 , the client submits a first transaction to the blockchain network to deploy a first valuation contract.

[0071] The first transaction includes a first valuation logic. In a specific example, the first valuation logic may be a bytecode obtained by compiling a corresponding high-level language code.

[0072] Specifically, the client can submit the first transaction to any first node in the blockchain network. After receiving the first transaction, the first node can determine whether the first transaction is valid. If so, it will place the transaction in a transaction storage pool and forward it to other nodes in the blockchain network, allowing them to repeat the processing of the first node. Afterwards, when the first transaction is packaged into a block and published on the chain, each node will verify the packaged block. If the verification passes, the block will be stored locally and the first transaction will be executed to deploy the first valuation contract to the blockchain network.

[0073] The above is an explanation of the deployment process of the first valuation contract. The following is an explanation of the deployment process of the second valuation contract.

[0074] It should be noted that due to computational limitations of the EVM (such as lack of support for random numbers) and the randomness inherent in the computational processes of some machine learning algorithms (neural networks / bagging, etc.), running these algorithms on the same data can produce slightly different models and similar but different predictions. If the predictions are written to the chain, there is a chance that the values ​​written to the chain will be inconsistent, causing read-write set and endorsement verification to fail, leading to consensus failure. There is a certain probability of transaction failure in classification tasks, and a higher probability of transaction failure in regression tasks.

[0075] In response to the above limitations, the second valuation contract can be deployed in two ways. The following describes one of the deployment methods.

[0076] Figure 4 A diagram illustrating a method interaction of deploying a second valuation contract according to one embodiment is shown. Figure 4 As shown, the method may include at least the following steps.

[0077] In step 402, each data holder i among the n data holders digitally signs the corresponding training sample, and encrypts the signature result and the training sample and provides them to a trusted third party.

[0078] Before executing step 402, each data holder i and the trusted third party may each generate a corresponding public-private key pair. The public-private key pair generated by each data holder i may be referred to as a first public-private key pair, wherein the first private key is stored by each data holder i and is used to digitally sign the corresponding training sample. The first public key is provided to the trusted third party for signature verification. The public-private key pair generated by the trusted third party may be referred to as a second public-private key pair, wherein the second public key is provided to each data holder and is used to encrypt each data holder's signature and training sample. The second private key is stored by the trusted third party and is used to decrypt the received encrypted result.

[0079] Taking any first data party among the n data holders as an example, step 402 may specifically include: the first data party uses a pre-saved first private key to digitally sign the corresponding training sample, and uses the second public key of a trusted third party to encrypt the corresponding signature result and training sample, and provides the encrypted result to the trusted third party.

[0080] It should be understood that the above-mentioned signing and encryption methods can ensure the security of data of all parties and avoid data tampering during transmission.

[0081] In step 404, the trusted third party receives the n encryption results sent by the n data holders and loads them into the Trusted Execution Environment (TEE). In the TEE, the n encryption results are decrypted and the signatures of the n training samples obtained by decryption are verified.

[0082] Taking the first data party as an example, after receiving the encryption result provided by the first data party, the trusted third party can use the second private key corresponding to the second public key to decrypt the encryption result sent by the first data party, and use the first public key corresponding to the first private key to verify the signature of the decrypted training sample.

[0083] Step 406: After the signature verification is passed, the trusted third party trains the risk assessment model based on the n training samples and constructs a second valuation logic corresponding to the trained risk assessment model.

[0084] Each training sample here can be understood as a sample set, which includes multiple training samples. The above risk assessment model can be a classification model or a regression model, which is used to predict the risk value.

[0085] It should be noted that in this embodiment, the training method of the risk assessment model can be understood as an off-chain training method. The risk assessment model can be implemented as a machine learning algorithm that does not contain randomness, such as the Logistic Regression (LR) algorithm and the Generalized Linear Model (GLM); it can also be implemented as a machine learning algorithm that contains randomness, such as neural networks and bagging.

[0086] Optionally, before executing the above-mentioned model training step, the trusted third party may use a predetermined hash algorithm to calculate the sample hash corresponding to each of the n training samples, and record each sample hash in the blockchain network for subsequent verification data use.

[0087] In addition, after executing the above-mentioned model training steps, the trusted third party can also use a predetermined hash algorithm to calculate the parameter hash of the model parameters of the trained risk assessment model, and record the parameter hash in the blockchain network for subsequent verification of the model.

[0088] In one example, constructing the second valuation logic corresponding to the trained risk assessment model may include:

[0089] The operations contained in the trained risk assessment model are converted into matrix operations, and the second valuation logic is constructed based on the matrix operations.

[0090] In step 408, the trusted third party submits a second transaction to the blockchain network to deploy a second valuation contract.

[0091] The second transaction includes a second evaluation logic. In a specific example, the second evaluation logic may be a bytecode.

[0092] Specifically, the trusted third party can submit the second transaction to any second node in the blockchain network. After receiving the second transaction, the second node can determine whether it is valid. If so, it will place the transaction in a transaction storage pool and forward it to other nodes in the blockchain network, allowing them to repeat the second node's processing. Afterwards, when the second transaction is packaged into a block and published on the chain, each node will verify the packaged block. If verification is successful, it will store the block locally and execute the second transaction to deploy the second valuation contract to the blockchain network.

[0093] Optionally, the trusted third party can also perform the following operations on the trained risk assessment model: Figure 5 The incremental training method shown.

[0094] Figure 5In this example, a trusted third party receives encrypted incremental data from any data holder i among n data holders. The trusted third party can then verify, based on the parameter hash recorded in the blockchain network, whether the risk assessment model it maintains is the previously trained risk assessment model. If so, it uses this model as the initial global model and incrementally trains the initial global model based on the encrypted incremental data to obtain the currently trained risk assessment model. This currently trained risk assessment model is referred to as the updated global model. Based on the updated global model, the trusted third party reconstructs the second valuation logic and submits a third transaction to the blockchain network to update the second valuation contract. The third transaction includes the reconstructed second valuation logic.

[0095] First, the encrypted incremental data can be obtained by the data holder i using a pre-saved first private key to digitally sign the corresponding incremental data, and then using a second public key of a trusted third party to encrypt the signature result and the incremental data.

[0096] The trusted third party can then decrypt the encrypted incremental data using the second private key corresponding to the second public key and verify the decrypted plaintext incremental data using the first public key corresponding to the first private key. After the signature verification is successful, the data hash of the plaintext incremental data can be recorded in the blockchain network, and the initial global model can be incrementally trained based on the plaintext incremental data. After training is completed, the parameter hash of the updated model parameters of the global model can be recorded in the blockchain network for verification during the next incremental training.

[0097] Finally, after receiving the third transaction, the blockchain network can replace the original second valuation logic with the reconstructed second valuation logic to obtain an updated second valuation contract.

[0098] It should be understood that in actual applications, the above incremental training process is continuously executed, thereby achieving automatic real-time updating of the second valuation contract.

[0099] The following describes another deployment method for the second valuation contract, which is suitable for scenarios with higher data security requirements.

[0100] Figure 6 FIG. 1 shows an interaction diagram of a method for deploying a second valuation contract according to another embodiment. Figure 6 As shown, the method may include at least the following steps.

[0101] In step 602, any first node in the blockchain network receives a fourth transaction submitted by each of n data holders, where the fourth transaction includes at least an encrypted training sample of the corresponding data holder.

[0102] The encrypted training samples here can be obtained by first digitally signing the corresponding training samples by the corresponding data holder, and then encrypting the signature result and the training samples. Alternatively, the corresponding data holder can directly encrypt the corresponding training samples.

[0103] In step 604 , the first node loads the fourth transaction into the trusted execution environment (TEE), decrypts the encrypted training sample in the TEE, and trains a risk assessment model based on the plaintext training sample.

[0104] Specifically, within the TEE, the encrypted training samples can be decrypted first, and then the decrypted plaintext training samples can be signature-verified. After the signature verification is successful, the risk assessment model is trained based on the plaintext training samples of each of the n data holders. Alternatively, within the TEE, the encrypted training samples can be decrypted, and then the risk assessment model can be trained based on the decrypted plaintext training samples.

[0105] Optionally, the first node may also record the decrypted plaintext training sample into the blockchain network to achieve data storage.

[0106] In addition, the above-mentioned risk assessment model can be a classification model or a regression model, which is used to predict the risk value.

[0107] It should be noted that in this embodiment, the training method of the risk assessment model can be understood as an on-chain training method. This method produces the same prediction results each time on the same dataset, can meet the consistency of the read and write set data, and can pass the consensus of the nodes. Because each run must go through the consensus process, this method will have a certain degree of performance degradation, and this method can only use algorithms without random processes. For example, the risk assessment model can be implemented as a machine learning algorithm that does not contain randomness, such as the Logistic Regression (LR) algorithm and the Generalized Linear Model (GLM).

[0108] In step 606, the first node constructs a second valuation logic based on the trained risk assessment model, uses it as the contract content of the second valuation contract, and deploys the second valuation contract on the blockchain network.

[0109] The steps of constructing the second evaluation logic here can refer to step 406 and will not be repeated here.

[0110] Specifically, the first node can create a transaction for deploying the second valuation contract and place it in the transaction storage pool. The first node forwards this transaction to other nodes in the blockchain network so that they can determine whether the transaction is valid. If so, the first node places it in the transaction storage pool. Later, when the transaction is packaged into a block and published on the chain, each node will verify the packaged block. If verification is successful, the node will store the block locally and execute the transaction to deploy the second valuation contract on the blockchain network.

[0111] In addition, the first node can also publish the trained risk assessment model on the blockchain network. That is, the model parameters of the trained risk assessment model are recorded in the blockchain network to facilitate subsequent incremental training.

[0112] After publishing the trained risk assessment model, you can also perform the following operations on the model: Figure 7 The incremental training method shown.

[0113] Figure 7 In the example, any second node in the blockchain network receives a fifth transaction submitted by any data holder i among n data holders. The fifth transaction includes the encrypted incremental data of data holder i (obtained by first digitally signing and then encrypting, or by direct encryption). The second node can decrypt the encrypted incremental data and, after decryption, record the plaintext incremental data in the blockchain network. The trained risk assessment model is pulled from the blockchain network, and the pulled model is incrementally trained based on the plaintext incremental data to obtain the currently trained risk assessment model. The second node publishes the currently trained risk assessment model on the blockchain network and updates the second valuation contract based on it.

[0114] Specifically, the second node may update the second valuation contract by creating a transaction for updating the second valuation contract. Updating the second valuation contract here may mean replacing the original second valuation logic with the reconstructed second valuation logic.

[0115] It should be understood that in actual applications, the above incremental training process is continuously executed, thereby achieving automatic real-time updating of the second valuation contract.

[0116] At this point, the deployment of the first valuation contract and the second valuation contract in the blockchain network has been realized.

[0117] The following is a detailed description of the method for evaluating product value provided in this manual.

[0118] Figure 8 An interactive diagram of a method for evaluating product value based on blockchain according to one embodiment is shown. Figure 8As shown, the method may include at least the following steps.

[0119] In step 802, the client submits a target transaction to the blockchain network to invoke the product valuation contract in response to the user's query request for the target product.

[0120] The target product is accompanied by a compensation agreement, which may be an insurance product, for example.

[0121] Furthermore, the target transaction includes product information of the target product and user information. Product information includes information about the compensation agreement. For example, if the target product is an insurance product, the agreement information may include the conditions for claiming the loss. Furthermore, product information may include insurance conditions, the insurance period, and insurance coverage. User information may include name, age, and salary.

[0122] The above target transaction may also include information such as the address of the product valuation contract, the name of the calling function, and parameters.

[0123] In step 804, the blockchain network executes the product valuation contract based on the target transaction.

[0124] The aforementioned product valuation contract determines the target product's valuation for each user based on product and user information. The contract logic within the product valuation contract can be built based on a pre-trained valuation model.

[0125] In one example, the product valuation contract may include a first valuation contract, wherein the first valuation logic in the first valuation contract is constructed based on a valuation formula, which may be specifically constructed by Figure 3 The method steps shown are deployed in a blockchain network.

[0126] In this example, executing the product valuation contract based on the target transaction on the blockchain network may specifically include: performing a first processing on the product information and user information according to a first valuation logic, and determining the product valuation based on the first processing result. The first processing result indicates the overall valuation of the target product for the user.

[0127] In another example, the product valuation contract may include a second valuation contract, in which the second valuation logic in the second valuation contract is constructed based on a pre-trained risk assessment model, which may be specifically constructed by Figure 4 or Figure 6 The method steps shown are deployed in a blockchain network.

[0128] In this example, the blockchain network executing the product valuation contract based on the target transaction may specifically include:

[0129] The product information and user information are subjected to a second processing corresponding to the second valuation logic to obtain a risk value of the user for the target product, and the product valuation is determined based on the risk value, wherein the risk value indicates the probability that the compensation agreement will be satisfied after the user purchases the target product.

[0130] For example, if the target product is an insurance product, the product valuation can refer to the insurance premium, and the risk value can refer to the probability of risk. In other words, in this solution, the value of the insurance product can be evaluated in combination with the probability of risk.

[0131] In yet another example, the product valuation contract may include both the first valuation contract and the second valuation contract.

[0132] In this example, executing a product valuation contract based on a target transaction on a blockchain network may specifically include: performing a first process on product and user information according to a first valuation logic to obtain an initial valuation for the target product. This initial valuation indicates the overall valuation of the target product for the user. Performing a second process on the product and user information according to a second valuation logic to obtain a risk value for the target product, indicating the probability that the compensation agreement will be satisfied after the user purchases the target product. Combining the initial valuation and the risk value determines the product valuation.

[0133] In a specific example, the initial valuation and the risk value may be weighted and summed, and the product valuation may be determined based on the weighted summation result.

[0134] In another example, the user information is encrypted user information, and the product valuation contract includes a privacy contract part that depends on the user information. In addition, it may also include a plain text contract part that depends on the product information. In this example, the execution method of the product valuation contract can be as follows: Figure 9 shown.

[0135] Figure 9 In this process, any node in the blockchain network loads the target transaction into a trusted execution environment (TEE). Within the TEE, the encrypted user information is decrypted and the private contract portion is executed. Furthermore, in a standard environment, the plaintext contract portion is executed based on the product information. Finally, the contract state parameters corresponding to the private contract portion are combined with the contract state parameters corresponding to the plaintext contract portion to obtain the product valuation.

[0136] Of course, in actual applications, the blockchain network can also encrypt and store the contract state parameters related to the execution of the privacy contract.

[0137] In step 806, the blockchain network provides the product valuation to the client.

[0138] The client can display the product valuation to the user so that the user can decide whether to purchase the target product.

[0139] In summary, the blockchain-based product valuation method provided in the embodiments of this specification evaluates the value of a target product by executing a pre-deployed product valuation contract within the blockchain network. This ensures transparency, openness, and auditability in the product valuation process. Furthermore, the product valuation contract determines the target product's valuation for the current user based on product and user information, enabling flexible and personalized valuation.

[0140] Corresponding to the above-mentioned method for evaluating product value based on blockchain, one embodiment of this specification also provides a system for evaluating product value based on blockchain, such as Figure 10 As shown, the system may include: a client 1002 and a blockchain network 1004.

[0141] Client 1002 is configured to submit a target transaction to the blockchain network to invoke the product valuation contract in response to a user's query request for a target product, where the target product is accompanied by a compensation agreement. The target transaction includes product information of the target product and user information of the user, and the product information includes agreement information of the compensation agreement.

[0142] The blockchain network 1004 is configured to execute a product valuation contract based on a target transaction, wherein the product valuation contract determines a product valuation of the target product for the user based on product information and user information.

[0143] The contract logic in the above product valuation contract is built based on a pre-trained valuation model.

[0144] In one example, the product valuation contract includes a first valuation contract, wherein a first valuation logic in the first valuation contract is constructed based on a general valuation formula;

[0145] Blockchain network 1004 is specifically used for:

[0146] A first process is performed on the product information and the user information according to a first valuation logic, and a product valuation is determined based on the first process result, wherein the first process result indicates the overall valuation of the target product for the user.

[0147] In another example, the product valuation contract includes a second valuation contract, and the second valuation logic in the second valuation contract is constructed based on a pre-trained risk assessment model;

[0148] The blockchain network 1004 is further specifically used for:

[0149] The product information and user information are subjected to a second processing corresponding to the second valuation logic to obtain a risk value of the user for the target product, and the product valuation is determined based on the risk value, wherein the risk value indicates the probability that the compensation agreement will be satisfied after the user purchases the target product.

[0150] In another example, the product valuation contract includes a first valuation contract and a second valuation contract, wherein the first valuation logic in the first valuation contract is constructed based on a general valuation formula, and the second valuation logic in the second valuation contract is constructed based on a pre-trained risk assessment model;

[0151] The blockchain network 1004 is further specifically used for:

[0152] Performing a first process corresponding to a first valuation logic on the product information and the user information to obtain an initial valuation for the target product; the initial valuation indicates an overall valuation of the target product for the user;

[0153] Performing a second process corresponding to the second valuation logic on the product information and the user information to obtain a risk value for the target product; the risk value indicates the probability that the compensation agreement will be satisfied after the user purchases the target product;

[0154] Determine product valuation by combining initial valuation and risk value.

[0155] In yet another example, the user information is encrypted user information, and the product valuation contract includes a privacy contract portion that relies on the user information;

[0156] The blockchain network 1004 is further specifically used for:

[0157] The target transaction is loaded into the Trusted Execution Environment (TEE). Within the TEE, the encrypted user information is decrypted and the privacy contract is executed. Furthermore, the contract state parameters related to the privacy contract execution can be encrypted and stored.

[0158] The blockchain network 1004 is also used to provide product valuation to the client 1002.

[0159] Optionally, the client 1002 is further configured to obtain a general valuation formula and create a corresponding UML model therefor;

[0160] The client 1002 is further configured to construct a first valuation logic according to the UML model;

[0161] The client 1002 is further configured to submit a first transaction for deploying a first valuation contract to the blockchain network 1004 , where the first transaction includes a first valuation logic.

[0162] Optionally, the system may further include n data holders 1006 and a trusted third party 1008 .

[0163] Each data holder 1006 among the n data holders 1006 is used to digitally sign the corresponding training sample, and encrypt the signature result and the training sample and provide them to the trusted third party 1008.

[0164] Taking any first data party 1006 among the n data holders 1006 as an example, the first data party 1006 uses a pre-saved first private key to digitally sign the corresponding training sample, and uses the second public key of the trusted third party 1008 to encrypt the corresponding signature result and training sample, and provides the encrypted result to the trusted third party 1008.

[0165] The trusted third party 1008 is used to receive n encryption results sent by n data holders 1006 and load them into the trusted execution environment TEE. In the TEE, the n encryption results are decrypted and the n training samples obtained by decryption are signed.

[0166] In the aforementioned example, the trusted third party 1008 is specifically used to: use the second private key corresponding to the second public key to decrypt the encryption result sent by the first data party, and use the first public key corresponding to the first private key to verify the signature of the decrypted training sample.

[0167] The trusted third party 1008 is further configured to train a risk assessment model based on n training samples after the signature verification is passed, and to construct a second valuation logic corresponding to the trained risk assessment model.

[0168] The trusted third party 1008 is further specifically used to: convert the operations included in the trained risk assessment model into matrix operations; and construct a second valuation logic based on the matrix operations.

[0169] The trusted third party 1008 is further configured to submit a second transaction for deploying a second valuation contract to the blockchain network 1004 , where the second transaction includes a second valuation logic.

[0170] Optionally, the trusted third party 1008 is further configured to receive encrypted incremental data sent by any data holder 1006 among the n data holders 1006 .

[0171] The trusted third party 1008 is also used to perform incremental training on the trained risk assessment model based on the encrypted incremental data to obtain a currently trained risk assessment model.

[0172] The trusted third party 1008 is also used to reconstruct the second valuation logic based on the currently trained risk assessment model.

[0173] The trusted third party 1008 is further configured to submit a third transaction to the blockchain network 1004 for updating the second valuation contract, where the third transaction includes the reconstructed second valuation logic.

[0174] Optionally, any first node in the blockchain network 1004 is used to receive a fourth transaction submitted by each of n data holders 1006 , where the fourth transaction at least includes an encrypted training sample corresponding to the data holder 1006 .

[0175] The first node is further configured to load the fourth transaction into a trusted execution environment (TEE), decrypt the encrypted training sample in the TEE, and train a risk assessment model based on the plaintext training sample.

[0176] The first node is further used to construct a second valuation logic based on the trained risk assessment model, and use it as the contract content of the second valuation contract, and deploy the second valuation contract on the blockchain network 1004.

[0177] In addition, the first node is also used to publish the trained risk assessment model on the blockchain network 1004.

[0178] Optionally, any second node in the blockchain network 1004 is used to receive a fifth transaction submitted by any data holder 1006 among the n data holders 1006, where the fifth transaction includes at least the encrypted incremental data of the data holder 1006.

[0179] The second node is also used to pull the trained risk assessment model from the blockchain network 1004, and perform incremental training on it based on the encrypted incremental data to obtain the currently trained risk assessment model.

[0180] The second node is also used to publish the currently trained risk assessment model on the blockchain network 1004 and update the second valuation contract based on it.

[0181] The functions of the various functional modules of the system in the above embodiment of this specification can be implemented through the various steps of the above method embodiment. Therefore, the specific working process of the system provided by one embodiment of this specification will not be repeated here.

[0182] An embodiment of this specification provides a blockchain-based system for evaluating product value, which can improve the flexibility of target product value evaluation.

[0183] According to another embodiment, there is also provided a computer readable storage medium having a computer program stored thereon, which, when executed in a computer, causes the computer to execute a combination of Figures 3 to 9 The method described in any one of .

[0184] According to another embodiment, a computing device is provided, including a memory and a processor, wherein the memory stores executable code, and when the processor executes the executable code, the system realizes the combination of Figures 3 to 9 The method of any one of the above.

[0185] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0186] The steps of the method or algorithm described in conjunction with the disclosure of this specification can be implemented in hardware or by a processor executing software instructions. The software instructions can be composed of corresponding software modules, which can be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, hard disk, mobile hard disk, CD-ROM or any other form of storage medium well known in the art. An exemplary storage medium is coupled to the processor so that the processor can read information from the storage medium and write information to the storage medium. Of course, the storage medium can also be an integral part of the processor. The processor and storage medium can be located in an ASIC. In addition, the ASIC can be located in a server. Of course, the processor and storage medium can also exist in the server as discrete components.

[0187] Those skilled in the art will appreciate that in one or more of the above examples, the functions described herein can be implemented using hardware, software, firmware, or any combination thereof. When implemented using software, these functions can be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of computer programs from one place to another. The storage medium can be any available medium that can be accessed by a general-purpose or special-purpose computer.

[0188] The foregoing description of this specification describes specific embodiments. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims can be performed in an order different from that described in the embodiments and still achieve the desired results. Furthermore, the processes depicted in the accompanying drawings do not necessarily require the specific order shown or the sequential order to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0189] The specific implementation methods described above further illustrate the purpose, technical solutions and beneficial effects of this specification. It should be understood that the above description is only the specific implementation method of this specification and is not intended to limit the scope of protection of this specification. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solutions of this specification should be included in the scope of protection of this specification.

Claims

1. A method for evaluating product value based on blockchain, comprising: In response to a user's query request for a target product, the client submits a target transaction to the blockchain network that invokes a product valuation contract, wherein the target product is accompanied by a compensation agreement; the target transaction includes product information of the target product and user information of the user; and the product information includes agreement information of the compensation agreement. The blockchain network executes the product valuation contract based on the target transaction to obtain a product valuation of the target product for the user; the product valuation contract includes a second valuation contract, and a second valuation logic in the second valuation contract is constructed based on a pre-trained risk assessment model; The blockchain network provides the product valuation to the client; The blockchain network executes the product valuation contract based on the target transaction, including: The product information and user information are subjected to a second processing corresponding to the second valuation logic to obtain a risk value of the user for the target product, and the product valuation is determined based on the risk value, wherein the risk value indicates the probability that the compensation agreement will be satisfied after the user purchases the target product.

2. The method according to claim 1, wherein The product valuation contract further includes a first valuation contract, wherein the first valuation logic in the first valuation contract is constructed based on a general valuation formula; The blockchain network executes the product valuation contract based on the target transaction, further comprising: Performing a first process corresponding to the first valuation logic on the product information and the user information to obtain an initial valuation for the target product; the initial valuation indicates an overall valuation of the target product for the user; Determining the product valuation according to the risk value includes: The product valuation is determined by combining the initial valuation and the risk value.

3. The method according to claim 2, wherein: The first valuation contract is deployed to the blockchain network in the following manner: The client obtains the general valuation formula and creates a corresponding UML model for it; The client constructs the first valuation logic according to the UML model; The client submits a first transaction to the blockchain network for deploying the first valuation contract, where the first transaction includes the first valuation logic.

4. The method according to claim 1, wherein The second valuation contract is deployed to the blockchain network in the following manner: Each data holder i among the n data holders digitally signs the corresponding training sample, encrypts the signature result and the training sample, and provides it to a trusted third party; The trusted third party receives n encrypted results sent by n data holders and loads them into the trusted execution environment (TEE). In the TEE, the n encrypted results are decrypted and the signatures of the n decrypted training samples are verified. After the signature verification is passed, the trusted third party trains a risk assessment model based on the n training samples and constructs a second valuation logic corresponding to the trained risk assessment model; The trusted third party submits a second transaction to the blockchain network to deploy the second valuation contract, where the second transaction includes the second valuation logic.

5. The method according to claim 4, wherein the n data holders include a first data holder; The digitally signing the corresponding training sample and encrypting the signature result and the training sample and providing them to a trusted third party includes: The first data party digitally signs the corresponding training sample using a pre-stored first private key, encrypts the corresponding signature result and the training sample using a second public key of the trusted third party, and provides the encrypted result to the trusted third party; Decrypting the n encrypted results and verifying the signatures of the n decrypted training samples includes: The trusted third party decrypts the encryption result sent by the first data party using the second private key corresponding to the second public key, and verifies the signature of the decrypted training sample using the first public key corresponding to the first private key.

6. The method according to claim 4, wherein: The constructing of the second valuation logic corresponding to the trained risk assessment model includes: Converting operations included in the trained risk assessment model into matrix operations; Based on the matrix operation, the second evaluation logic is constructed.

7. The method according to claim 4, further comprising: The trusted third party receives the encrypted incremental data sent by any data holder i among the n data holders; The trusted third party performs incremental training on the trained risk assessment model based on the encrypted incremental data to obtain a currently trained risk assessment model; The trusted third party reconstructs the second valuation logic based on the currently trained risk assessment model; The trusted third party submits a third transaction to the blockchain network to update the second valuation contract, where the third transaction includes the reconstructed second valuation logic.

8. The method according to claim 1, wherein The second valuation contract is deployed to the blockchain network in the following manner: Any first node in the blockchain network receives a fourth transaction submitted by each of n data holders; the fourth transaction includes at least an encrypted training sample of the corresponding data holder; The first node loads the fourth transaction into a trusted execution environment (TEE), decrypts the encrypted training sample in the TEE, and trains a risk assessment model based on the plaintext training sample; The first node constructs a second valuation logic based on the trained risk assessment model, uses it as the contract content of the second valuation contract, and deploys the second valuation contract on the blockchain network.

9. The method according to claim 8, further comprising: The first node publishes the trained risk assessment model on the blockchain network.

10. The method according to claim 9, further comprising: Any second node in the blockchain network receives a fifth transaction submitted by any data holder i among the n data holders; The fifth transaction includes at least the encrypted incremental data of the data holder i; The second node pulls the trained risk assessment model from the blockchain network and performs incremental training on the model based on the encrypted incremental data to obtain a currently trained risk assessment model; The second node publishes the currently trained risk assessment model on the blockchain network and updates the second valuation contract based on the model.

11. The method according to claim 1, wherein The user information is encrypted user information; The product valuation contract includes a privacy contract portion that relies on the user information; The blockchain network executes the product valuation contract based on the target transaction, including: The target transaction is loaded into a trusted execution environment (TEE), where the encrypted user information is decrypted and the privacy contract portion is executed.

12. The method according to claim 11, further comprising: The contract status parameters related to the execution of the privacy contract are encrypted and stored.

13. A blockchain-based system for evaluating product value, comprising a client and a blockchain network; The client is used to submit a target transaction for invoking a product valuation contract to the blockchain network in response to a user's query request for a target product, wherein: The target product is accompanied by a compensation agreement; the target transaction includes product information of the target product and user information of the user; The product information includes agreement information of the compensation agreement; The blockchain network is configured to execute the product valuation contract based on the target transaction to obtain a product valuation of the target product for the user; the product valuation contract includes a second valuation contract, wherein a second valuation logic in the second valuation contract is constructed based on a pre-trained risk assessment model; The blockchain network is further used to provide the product valuation to the client; The blockchain network is specifically used for: The product information and user information are subjected to a second processing corresponding to the second valuation logic to obtain a risk value of the user for the target product, and the product valuation is determined based on the risk value, wherein the risk value indicates the probability that the compensation agreement will be satisfied after the user purchases the target product.

14. The system according to claim 13, wherein: The product valuation contract further includes a first valuation contract, wherein the first valuation logic in the first valuation contract is constructed based on a general valuation formula; The blockchain network is also specifically used for: Performing a first process corresponding to the first valuation logic on the product information and the user information to obtain an initial valuation for the target product; the initial valuation indicates an overall valuation of the target product for the user; The product valuation is determined by combining the initial valuation and the risk value.

15. The system according to claim 14, The client is further used to obtain the general valuation formula and create a corresponding UML model for it; The client is further configured to construct the first valuation logic according to the UML model; The client is further configured to submit a first transaction for deploying the first valuation contract to the blockchain network, where the first transaction includes the first valuation logic.

16. The system according to claim 13, further comprising n data holders and a trusted third party; Each data holder i among the n data holders is configured to digitally sign the corresponding training sample, and encrypt the signature result and the training sample and provide them to the trusted third party; The trusted third party is used to receive n encrypted results sent by n data holders and load them into the trusted execution environment TEE. In the TEE, the n encrypted results are decrypted and the signatures of the n training samples obtained by decryption are verified. The trusted third party is further configured to, after the signature verification is passed, train a risk assessment model based on the n training samples and construct a second valuation logic corresponding to the trained risk assessment model; The trusted third party is further configured to submit a second transaction to the blockchain network for deploying the second valuation contract, where the second transaction includes the second valuation logic.

17. The system according to claim 13, further comprising n data holders; Any first node in the blockchain network is configured to receive a fourth transaction submitted by each of the n data holders; the fourth transaction at least includes an encrypted training sample corresponding to the data holder; The first node is further configured to load the fourth transaction into a trusted execution environment (TEE), decrypt the encrypted training sample in the TEE, and train a risk assessment model based on the plaintext training sample; The first node is further configured to construct a second valuation logic based on the trained risk assessment model, use the second valuation logic as the contract content of the second valuation contract, and deploy the second valuation contract on the blockchain network.

18. The system of claim 13, wherein: The user information is encrypted user information; the product valuation contract includes a privacy contract portion that depends on the user information; The blockchain network is also specifically used for: The target transaction is loaded into a trusted execution environment (TEE), where the encrypted user information is decrypted and the privacy contract portion is executed.

19. A computer-readable storage medium having a computer program stored thereon, wherein: When the computer program is executed in a computer, the computer is caused to execute the method according to any one of claims 1 to 12.

20. A computing device comprising a memory and a processor, wherein: The memory stores executable code, and when the processor executes the executable code, the method according to any one of claims 1 to 12 is implemented.

Images