CN114255074A

CN114255074A - Block chain based method and system for evaluating product value

Info

Publication number: CN114255074A
Application number: CN202111511944.1A
Authority: CN
Inventors: 程龙; 李浩然; 李艳鹏; 陆旭明
Original assignee: Ant Blockchain Technology Shanghai Co Ltd
Current assignee: Ant Blockchain Technology Shanghai Co Ltd
Priority date: 2021-12-06
Filing date: 2021-12-06
Publication date: 2022-03-29

Abstract

Embodiments of the present specification provide a method and a system for evaluating a product value based on a blockchain, which can be used for product evaluation under the condition of protecting user privacy. The method for evaluating the product value comprises the steps that a client-side responds to a query request of a user for a target product, and a target transaction for invoking a product valuation contract is submitted to a blockchain network, wherein the target product is attached with an indemnity agreement, and the target transaction comprises product information of the target product and user information of the user. The blockchain network executes a product valuation contract based on the target transaction. The product valuation contract determines a product valuation of the target product for the user based on the product information and the user information and provides the product valuation to the client. Optionally, the user information is encrypted user information, the product valuation contract includes a privacy contract portion, and the blockchain network may load the encrypted user information and the privacy contract portion into a TEE, where the encrypted user information is decrypted, and the privacy contract portion is executed.

Description

Block chain based method and system for evaluating product value

Technical Field

One or more embodiments of the present disclosure relate to the field of blockchain technology, and more particularly, to a method and system for evaluating product value based on blockchain.

Background

For a target product (e.g., an insurance product) with a reimbursement agreement, in order to guarantee the vital interests of both suppliers and suppliers, it is usually necessary to evaluate the value of the product based on various factors (e.g., product information, company operating condition information, etc.).

In the conventional art, the value of a target product is generally evaluated using a fixed formula. Therefore, there is a need to provide a more flexible solution for assessing the value of a product.

Disclosure of Invention

One or more embodiments of the present specification describe a method and a system for evaluating a product value based on a block chain, which can realize flexible evaluation of thousands of people and thousands of faces, and can realize transparency, openness and auditability of a product evaluation process.

In a first aspect, a method for assessing product value based on blockchain is provided, including:

the method comprises the steps that a client-side responds to a query request of a user for a target product, and submits a target transaction for invoking a product valuation contract to a blockchain network, wherein the target product is attached with an indemnity agreement; the target transaction comprises product information of the target product and user information of the user; the product information includes agreement information of the indemnity agreement;

the blockchain network executing 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 user information;

the blockchain network provides the product valuation to the client.

In a second aspect, an apparatus for assessing product value based on blockchain is provided, including: a client and a blockchain network;

the client is used for responding to a query request of a user for a target product, and submitting a target transaction for invoking a product valuation contract to the blockchain network, wherein the target product is attached with a compensation agreement; the target transaction comprises product information of the target product and user information of the user; the product information includes agreement information of the indemnity agreement;

the blockchain network is used for executing the product valuation contract based on the target transaction, wherein the product valuation contract determines the product valuation of the target product for the user based on the product information and the user information;

the blockchain network is further configured to provide the product valuation to the client.

In a third aspect, there is provided a computer storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of the first aspect.

In a fourth aspect, there is provided a computing device comprising a memory having stored therein executable code and a processor that, when executing the executable code, implements the method of the first aspect.

The method and system for evaluating the value of a product based on a block chain, provided by one or more embodiments of the present specification, can evaluate the value of a target product by executing a product evaluation contract pre-deployed in a block chain network, and can realize transparency, openness and auditability of a product evaluation process. In addition, the product valuation contract determines the product valuation of the target product for the current user based on the product information and the user information, and can realize flexible valuation of thousands of people.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art to obtain other drawings based on the drawings without creative efforts.

FIG. 1 is a schematic diagram of creating an intelligent contract and invoking an intelligent contract as provided herein;

FIG. 2 is a schematic diagram of an implementation scenario provided by an embodiment of the present disclosure;

FIG. 3 illustrates a method interaction diagram for a first valuation contract deployment, according to one embodiment;

FIG. 4 illustrates a method interaction diagram for a second valuation contract deployment, according to one embodiment;

FIG. 5 illustrates a schematic diagram of an incremental training method according to one embodiment;

FIG. 6 illustrates a method interaction diagram for a second valuation contract deployment, according to another embodiment;

FIG. 7 shows a schematic diagram of an incremental training method according to another embodiment;

FIG. 8 illustrates an interaction diagram for a method of assessing product value based on blockchains, according to one embodiment;

FIG. 9 illustrates a schematic diagram of a method of performing a product valuation contract, according to one embodiment;

FIG. 10 shows a block chain based system for assessing product value, according to one embodiment.

Detailed Description

The scheme provided by the specification is described below with reference to the accompanying drawings.

As described above, in the conventional art, the value of a target product (e.g., insurance product) with a reimbursement agreement is generally evaluated by using a fixed formula. The product value evaluated by the mode is obviously homogeneous and cannot be different from person to person. However, since the probability that the reimbursement agreement is satisfied differs for different purchasing users, the value of the target product should also vary accordingly. To this end, the inventors of the present application propose to evaluate the value of a target product by executing a product valuation contract that is pre-deployed in a blockchain network. The product valuation contract herein is an intelligent contract for evaluating the value of a product.

Before describing the solutions provided by the embodiments of the present disclosure, concepts such as blockchains and intelligent contracts are briefly described.

It should be noted that the blockchain described herein may specifically refer to a P2P network system having a distributed data storage structure, where each node achieves data sharing via a consensus mechanism, and the data in the blockchain is distributed in temporally consecutive "blocks", and the latter block may include a data digest of the former block, and achieves full data backup for all or part of the nodes according to different specific consensus mechanisms (e.g., POW, POS, DPOS, or PBFT).

The real data generated by the physical world can be constructed into a standard transaction (transaction) format supported by a block chain, then is issued to the block chain, the received transaction is identified and verified by each node in the block chain, and after the verification is passed, the transaction is packaged into a block by the node serving as an accounting node in the block chain, and the persistent evidence is stored in the block chain.

The consensus algorithm supported in the blockchain may include: consensus algorithms such as Proof of Work (POW), Proof of stock (POS), Proof of commission rights (DPOS), and Practical Byzantine Fault Tolerance (PBFT), etc.

Regardless of which consensus algorithm is adopted by the block chain, the accounting node of the current round can pack the received transaction to generate the latest block and send the generated latest block or the block header of the latest block to other nodes for consensus verification. If no problem is verified after other nodes receive the latest block or the block header of the latest block, the latest block can be added to the tail of the original block chain, so that the accounting process of the block chain is completed. The transaction contained in the block may also be performed by other nodes in verifying the new block or block header sent by the accounting node.

As is well known to those skilled in the art, since the blockchain operates under a corresponding consensus mechanism, data included in the blockchain is difficult to be tampered by any node, for example, a whitehead blockchain is adopted, and it is possible to tamper existing data only by an attack that requires at least 51% of effort on the whole network, so the blockchain has a characteristic of ensuring data security and anti-attack tampering that cannot be achieved by other centralized database systems. Therefore, the data recorded in the distributed database of the blockchain cannot be attacked or tampered, and the authenticity and reliability of the data information of the distributed database of the blockchain are guaranteed.

Example types of blockchains may include public blockchains, private blockchains, and federation blockchains. Although the term blockchain is typically associated with bitcoin cryptocurrency networks, blockchains as used herein may refer to DLS (distributed ledger system) that do not reference any particular use case.

In a public blockchain, the consensus process is controlled by nodes of the consensus network. For example, hundreds, thousands, or even millions of entities may cooperate in a public blockchain, each entity operating at least one node in the public blockchain. Thus, a public blockchain may be considered a public network with respect to participating entities. An example public blockchain includes a bitcoin network that is a peer-to-peer payment network. Bitcoin networks utilize a distributed ledger, called blockchains. However, as noted above, the term blockchain is generally used to refer to distributed ledgers that do not specifically refer to bitcoin networks.

Typically, public blockchains support public transactions. The public transaction is shared with all nodes within the public blockchain and stored in the global blockchain. A global blockchain is a chain of blocks that is replicated across all nodes. That is, for a global blockchain, all nodes are in a completely consistent state. To achieve consensus (e.g., agree to add blocks to a blockchain), a consensus protocol is implemented within the public blockchain. Example consensus protocols include, but are not limited to, proof of work (POW) implemented in bitcoin networks.

Typically, private blockchains are provided to specific entities that collectively control read and write permissions. The entity controls which nodes can participate in the blockchain. Thus, private blockchains are often referred to as licensed networks, which impose restrictions on who is allowed to participate in the network and its level of participation (e.g., only in certain transactions). Various types of access control mechanisms may be used (e.g., existing participants vote to add a new entity, and regulatory authorities may control admission).

Typically, federation blockchains are private among participating entities. In a federation blockchain, the consensus process is controlled by an authorized set of nodes (federation member nodes), one or more of which are operated by respective entities (e.g., enterprises). For example, a federation consisting of ten (10) entities (e.g., enterprises) can operate a blockchain of federations in which each entity operates at least one node. Thus, a federated blockchain may be considered a private network with respect to participating entities. In some examples, each entity (node) must sign each block to validate the block and add the validated 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 to validate the block and add the validated block to the blockchain.

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

In practical applications, whether public block chains, private block chains, or alliance block chains, may provide the functionality of a Smart contract (Smart contract). An intelligent contract on a blockchain is a contract on a blockchain that can be executed triggered by a transaction. An intelligent contract may be defined in the form of code.

Taking an Etherhouse as an example, a user is supported to create and call some complex logic in the Etherhouse network. The ethernet workshop is used as a programmable block chain, and the core of the ethernet workshop is an ethernet workshop virtual machine (EVM), and each ethernet workshop node can run the EVM. The EVM is a well-behaved virtual machine through which various complex logic can be implemented. The user issuing and invoking smart contracts in the etherhouse is running on the EVM. In fact, the EVM directly runs virtual machine code (virtual machine bytecode, hereinafter referred to as "bytecode"), so the intelligent contract deployed on the blockchain may be bytecode.

The process of issuing the smart contract will be described first.

For example, after a user sends a Transaction (Transaction) containing the creation of a smart contract to the ethernet network, each node may execute the Transaction in the EVM. The From field of the transaction is used To record the address of the account initiating the creation of the intelligent contract, the contract code stored in the field value of the Data field of the transaction may be byte code, and the field value of the To field of the transaction is a null account. After the nodes reach the agreement through the consensus mechanism, the intelligent contract is successfully created, and the follow-up user can call the intelligent contract.

After the intelligent contract is created, a contract account corresponding to the intelligent contract appears on the blockchain and has a specific address. The contract Code (Code) and account store (Storage) will be maintained in the account store for that contract account. The behavior of the intelligent contract is controlled by the contract code, while the account storage of the intelligent contract preserves the state of the contract. In other words, the intelligent contract causes a virtual account to be generated on the blockchain that contains the contract code and account storage.

As mentioned above, the Data field containing the transaction that created the intelligent contract may hold the byte code of the intelligent contract. A bytecode consists of a series of bytes, each of which can identify an operation. Based on the multiple considerations of development efficiency, readability and the like, a developer can select a high-level language to write intelligent contract codes instead of directly writing byte codes. For example, a high level language may employ a language such as Solidity, Serpent, C + +, or the like. For intelligent contract code written in a high-level language, the intelligent contract code can be compiled by a compiler to generate byte codes which can be deployed on a blockchain.

Taking the Solidity language as an example, the contract code written by it is very similar to a Class (Class) in the object-oriented programming language, and various members including state variables, functions, function modifiers, events, etc. can be declared in one contract. A state variable is a value permanently stored in an account Storage (Storage) field of an intelligent contract to save the state of the contract.

The following describes the calling process of the intelligent contract.

Still taking the ethernet network as an example, after the user sends a transaction containing the information of the intelligent contract to the ethernet network, each node can execute the transaction in the EVM. The From field of the transaction is used for recording the address of the account initiating the calling of the intelligent contract, the To field is used for recording the address of the called intelligent contract, and the Data field of the transaction is used for recording the method and the parameter for calling the intelligent contract. After invoking the smart contract, the account status of the contract account may change.

Subsequently, the intelligent contract invoker can check the account state of the contract account through the accessed block chain nodes.

The intelligent contract can be independently executed at each node in the blockchain in a specified mode, and all execution records and data are stored on the blockchain, so that after the transaction is executed, transaction certificates which cannot be tampered and cannot be lost are stored on the blockchain.

A schematic diagram of creating an intelligent contract and invoking the intelligent contract is shown in fig. 1. An intelligent contract is created in an Ethernet workshop and needs to be subjected to the processes of compiling the intelligent contract, changing the intelligent contract into byte codes, deploying the intelligent contract to a block chain and the like. The intelligent contract is called in the Ethernet workshop, a transaction pointing to the intelligent contract address is initiated, the EVM of each node can respectively execute the transaction, and the intelligent contract code is distributed and operated in the virtual machine of each node in the Ethernet workshop network.

The following description will be given of the embodiments provided in the present specification as a whole.

Fig. 2 is a schematic view of an implementation scenario provided in an embodiment of the present specification. In fig. 2, a product valuation contract is deployed in the blockchain network, and the product valuation contract can be constructed based on a pre-trained valuation model, and is used for determining the product valuation of a target product for a user based on product information and user information of the target product. The target product is accompanied by a reimbursement agreement, which may be, for example, an insurance product.

In one specific example, the product valuation contracts include a first valuation contract and/or a second valuation contract, wherein first valuation logic in the first valuation contract is constructed based on a common valuation formula; a second valuation logic in a second valuation contract is constructed based on the trained risk assessment model.

Each client in fig. 2 may correspond to a different insurance company (abbreviated as a insurance department), which may provide services such as insurance application service, insurance withdrawal service, and claim settlement service to the user. For instance, in the case of an application service, any client may first receive a user query request for a target product, and then may submit a target transaction to the blockchain network that invokes a product valuation contract. The blockchain network may execute the first valuation contract and/or the second valuation contract and obtain one or both processing results based on the target transaction. Finally, a product valuation is determined based on one or both of the processing results and provided to the client so that the client can provide the user with an application service based on the product valuation.

The following describes the deployment process of the first evaluation contract described above.

FIG. 3 illustrates a method interaction diagram for a first valuation contract deployment, according to one embodiment. As shown in fig. 3, the method may include at least the following steps.

Step 302, the client obtains the general estimation formula and creates a corresponding UML model for the general estimation formula.

The general valuation formula herein may be for evaluating the value of the target product for the user as a whole. The general estimation formula is invariable and is a derivation of the general case.

Taking the above target product as an insurance product, and the insurance product is specifically a life insurance product as an example, the implementation principle of the corresponding general estimation formula may be: referring to the experience life table of the Chinese life insurance industry (2010-2013), the current value of the future loss of the insurance product is calculated (assuming simple profit recovery), then the mathematical expectation of the current value of the future loss of the insurance product is calculated, and then the corresponding insurance fee (namely the product estimation value) is determined based on the data expectation.

For example, suppose that user x purchases an insurance product, the premium is 1 unit, and the payment method is wholesale payment. According to insurance benefits, future lossesHas a present value of X ═ v^TWhere v ═ 1/(1+ i), i denotes the annual rate and T denotes the future life of the insured life. Therefore, the insurance fee paid by the wharf of the insurance product is as follows:

wherein ω is the limiting age, f_T(T) represents the probability density function of T, since f cannot be described by an analytic function_T(t), so consider discretizing the above equation. Specifically, assume that the present value of future loss of the insurance product is X ═ v^K+1Where K ═ T }, then the discretized representation of equation 1 can be:

it can thus be demonstrated that under the assumption of a uniformly distributed condition of death,

thereby calculating A_xThe wholesale payment premium of the insurance product can be obtained.

Further, in step 302, a UML model corresponding to the general estimation formula may be constructed using a UML modeling design tool.

In step 304, the client constructs a first valuation logic according to the UML model.

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

At step 306, the client submits a first transaction to deploy a first valuation contract to the blockchain network.

Wherein the first transaction includes first valuation logic. In one specific example, the first evaluation logic may be a bytecode obtained by compiling a corresponding high-level language code.

Specifically, the client may submit the first transaction to any first node in the blockchain network. After receiving the first transaction, the first node may determine whether the first transaction is valid, and if it is determined that the first transaction is valid, place the first transaction in the transaction storage pool and forward the first transaction to other nodes in the blockchain network for the other nodes to repeat the processing procedure of the first node. Thereafter, when the first transaction is packaged into blocks and issued to the chain, each node verifies the packaged blocks, stores the blocks locally when the verification is passed, and executes the first transaction to deploy the first evaluation contract into the blockchain network.

The above is a description of the deployment process for the first valuation contract, and the following is a description of the deployment process for the second valuation contract.

It should be noted that, because the EVM has a computation limit (random number is not supported), and the computation process of some machine learning algorithms includes randomness, the operation of such machine learning algorithms (neural network/Bagging, etc.) on the same data may result in slightly different models and also may result in similar but different prediction results, if the prediction results are written into the chain, values on the written chain may also have a certain probability of inconsistency, which may cause the reading and writing set and endorsement verification to fail, thereby causing the consensus to fail. There is a certain probability in the classification task that causes the transaction to fail, and the regression task has a larger possibility that causes the transaction to fail.

Regarding the above restriction, the second evaluation contract may be deployed in two ways, and one of the ways will be described below.

FIG. 4 illustrates a method interaction diagram for a second valuation contract deployment, according to one embodiment. As shown in fig. 4, the method may include at least the following steps.

And step 402, each data holder i of the n data holders digitally signs the corresponding training sample, encrypts the signature result and the training sample and provides the encrypted result to a trusted third party.

Each data holder i and trusted third party may each generate a corresponding public-private key pair prior to performing step 402. The public and private key pair generated by each data holder i can be called a first public and private key pair, wherein the first private key is stored by each data holder i, and is used for digitally signing the corresponding training sample, and the first public key is provided for a trusted third party and is used for verifying the signature result. The public and private key pair generated by the trusted third party can be called a second public and private key pair, wherein the second public key is provided for each data holder and used for encrypting the signature result and the training sample of each data holder, and the second private key is stored by the trusted third party and used for decrypting the received encrypted result.

Taking an arbitrary first data party of the n data holders as an example, step 402 may specifically include: the first data party digitally signs the corresponding training samples by using a first private key saved in advance, encrypts the corresponding signature result and the training samples by using a second public key of the trusted third party, and provides the encrypted result to the trusted third party.

It should be understood that through the above-mentioned methods of signature and encryption, the security of each data can be ensured, and the data is prevented from being tampered in the transmission process.

And step 404, the Trusted third party receives n encrypted results sent by the n data holders, loads the n encrypted results into a Trusted Execution Environment (TEE), decrypts the n encrypted results in the TEE, and verifies the n decrypted training samples.

Taking the first data party as an example, after receiving the encryption result provided by the first data party, the trusted third party may decrypt the encryption result sent by the first data party by using the second private key corresponding to the second public key, and check the training sample obtained by decryption by using the first public key corresponding to the first private key.

And 406, after the signature verification is passed, training a risk assessment model by the trusted third party based on the n training samples, and constructing a second evaluation logic corresponding to the trained risk assessment model.

Each training sample is herein understood to be a sample set comprising a plurality of training samples. The risk assessment model may be a classification model or a regression model for predicting the risk value.

It should be noted that in this embodiment, the training method of the risk assessment model may be understood as an under-chain training method. The risk assessment model can be realized by a machine learning algorithm without randomness, such as a Logistic Regression (LR) algorithm, a Generalized Linear Model (GLM), and the like; and can be realized as machine learning algorithms including randomness, such as neural networks, Bagging and the like.

Optionally, before performing the step of model training, the trusted third party may calculate sample hashes corresponding to the n training samples by using a predetermined hash algorithm, and record the sample hashes in the blockchain network for use in subsequent verification data.

In addition, after the model training step is performed, the trusted third party may further calculate a parameter hash of a model parameter of the trained risk assessment model by using a predetermined hash algorithm, and record the parameter hash in the blockchain network for use in a subsequent verification model.

In one example, the constructing of the second valuation logic corresponding to the trained risk assessment model described above can include:

and converting the operation contained in the trained risk assessment model into matrix operation, and constructing a second evaluation logic based on the matrix operation.

At step 408, the trusted third party submits a second transaction to deploy a second valuation contract to the blockchain network.

The second transaction includes second valuation logic. In one specific example, the second evaluation logic may be a bytecode.

Specifically, the trusted third party may submit the second transaction to any second node in the blockchain network. The second node, after receiving the second transaction, may determine whether the second transaction is valid, and if it is determined that the second transaction is valid, place the second transaction in the transaction storage pool and forward the second transaction to other nodes in the blockchain network for the other nodes to repeat the processing procedure of the second node. Then, when the second transaction is packed into blocks and issued to the chain, each node verifies the packed blocks, stores the blocks locally when the verification is passed, and executes the second transaction to deploy a second valuation contract into the blockchain network.

Optionally, the trusted third party may also perform an incremental training method as shown in fig. 5 for the trained risk assessment model.

In fig. 5, the trusted third party receives encrypted incremental data sent by any data holder i among n data holders. And then, the trusted third party can verify whether the risk assessment model maintained by the trusted third party is a previously trained risk assessment model or not based on the parameter hash recorded in the blockchain network, if so, the trusted third party is used as an initial global model, and the initial global model is subjected to incremental training based on the encrypted incremental data to obtain the currently trained risk assessment model. The currently trained risk model is the updated global model. And a trusted third party, based on the updated global model, reconstructing the second valuation logic and submitting a third transaction to update the second valuation contract to the blockchain network, the third transaction including the reconstructed second valuation logic.

First, the encrypted incremental data may be obtained by the data holder i digitally signing the corresponding incremental data by using a first private key stored in advance, and then encrypting the signature result and the incremental data by using a second public key of a trusted third party.

Then, the trusted third party can decrypt the encrypted incremental data by using the second private key corresponding to the second public key, and verify the signature of the decrypted plaintext incremental data by using the first public key corresponding to the first private key. After the signature verification is passed, data hash of the plaintext incremental data can be recorded into the blockchain network, and the initial global model is subjected to incremental training based on the plaintext incremental data. After training is finished, the parameter hash of the model parameter for updating the global model can be recorded into the blockchain network for verification in the next incremental training.

Finally, the blockchain network may replace the original second evaluation logic with the reconstructed second evaluation logic after receiving the third transaction, resulting in an updated second evaluation contract.

It should be appreciated that in practical applications, the above incremental training process is performed continuously, so that automatic real-time updating of the second valuation contract can be achieved.

Another deployment for the second valuation contract, which is suitable for a scenario with a high requirement on data security, is described below.

FIG. 6 illustrates a method interaction diagram for a second valuation contract deployment, according to another embodiment. As shown in fig. 6, the method may include at least the following steps.

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 encrypted training samples of the corresponding data holders.

The encrypted training sample may be obtained by performing digital signature on a training sample corresponding to the corresponding data holder, and then encrypting the signature result and the training sample. Alternatively, the corresponding training samples may be directly encrypted by the corresponding data holder.

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 the risk assessment model based on the plaintext training sample.

Specifically, in the TEE, the encrypted training sample may be decrypted first, and then the plaintext training sample obtained through decryption may be subjected to signature verification. And after the signature verification is passed, training a risk assessment model based on respective plaintext training samples of the n data holders. Alternatively, in TEE, the encrypted training samples may be decrypted and then the risk assessment model may be trained based on the decrypted clear training samples.

Optionally, the first node may further record the decrypted plaintext training sample in a blockchain network to implement data storage.

Further, the risk assessment model may be a classification model or a regression model for predicting the risk value.

It should be noted that in this embodiment, the training method of the risk assessment model may be understood as an on-chain training method. The method has the advantages that the prediction results of the method on the same data set are the same each time, the consistency of the data of the read-write set can be met, and the consensus of the nodes can be realized. This method suffers from a certain degradation in performance because of the consensus process required for each run, and it can only use algorithms without random processes. For example, the risk assessment model may be implemented as a Logistic Regression (LR) algorithm, a Generalized Linear Model (GLM), or other machine learning algorithms that do not include randomness.

And step 606, the first node constructs a second valuation logic based on the trained risk assessment model, takes the second valuation logic as contract content of a second valuation contract, and deploys the second valuation contract on the blockchain network.

The step of constructing the second evaluation logic can be described with reference to step 406 and will not be repeated herein.

In particular, the first node may create a trade for deploying the second valuation contract and place it into a trade storage pool. The first node forwards the transaction to other nodes in the blockchain network so that the other nodes can determine whether the transaction is valid and, if it is determined to be valid, place it in the transaction storage pool. Thereafter, when the transaction is packaged into blocks and issued onto the chain, each node verifies the packaged blocks and, when verified, stores the blocks locally and executes the transaction to deploy a second valuation contract into the blockchain network.

In addition, the first node may also publish the trained risk assessment model on the blockchain network. Namely, the model parameters of the trained risk assessment model are recorded into the blockchain network, so as to facilitate subsequent incremental training.

After issuing the trained risk assessment model, an incremental training method as shown in FIG. 7 may also be performed for the model.

In fig. 7, any second node in the blockchain network receives a fifth transaction submitted by any data holder i of the n data holders. This fifth transaction includes the encrypted delta data of the data holder i (either by digital signature followed by encryption or by direct encryption). The second node may decrypt the encrypted delta data and, after decryption, record the plaintext delta data into the blockchain network. And pulling the trained risk assessment model from the block chain network, and performing incremental training on the pulled model 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 a second valuation contract based thereon.

The second node may specifically update the second valuation contract by creating a trade for updating the second valuation contract. Updating the second valuation contract herein can refer to replacing the original second valuation logic with the reconstructed second valuation logic.

By this, deployment of the first valuation contract and the second valuation contract in the blockchain network is achieved.

The method for evaluating the value of a product provided in the present specification will be described in detail below.

FIG. 8 illustrates an interaction diagram for a method of assessing product value based on blockchains, according to one embodiment. As shown in fig. 8, the method may include at least the following steps.

In step 802, a client submits a target transaction invoking a product valuation contract to a blockchain network in response to a user query request for a target product.

The target product is accompanied by an indemnity agreement, which may be, for example, an insurance product.

In addition, the target transaction includes product information of the target product and user information of the user. Wherein the product information includes agreement information of the indemnity agreement. For example, the target product is an insurance product, and the agreement information may include an insurance condition. In addition, the product information may also include conditions for insuring, terms of insuring, insurance responsibility, and the like. The user information may include name, age, salary, and the like.

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

At step 804, the blockchain network executes a product valuation contract based on the target transaction.

The product valuation contract determines the product valuation of the target product for the user based on the product information and the user information. Wherein contract logic in the product valuation contract can be constructed based on a pre-trained valuation model.

In one example, the product valuation contract described above can include a first valuation contract in which first valuation logic is based on being constructed by a valuation formula, which in particular can be deployed into a blockchain network through the method steps shown in fig. 3.

In this example, the blockchain network executing the product valuation contract based on the target transaction may specifically include: and performing first processing corresponding to the first evaluation logic on the product information and the user information, and determining the product evaluation according to the first processing result. Wherein the first processing result indicates the target product to be aimed at the evaluation condition of the user as a whole.

In another example, the product valuation contract described above can include a second valuation contract in which second valuation logic is built based on a pre-trained risk assessment model, which can be deployed into the blockchain network through the method steps shown in fig. 4 or fig. 6.

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

and performing second processing corresponding to second valuation logic on the product information and the user information to obtain a risk value of the user for the target product, and determining product valuation according to the risk value, wherein the risk value indicates the probability that the indemnity agreement is met after the user purchases the target product.

For example, the target product is an insurance product, the product valuation may refer to an insurance fee, and the risk value may refer to an insurance probability. That is, in the scheme, the value of the insurance product can be evaluated by combining the risk probability.

In yet another example, the product valuation contract can include both the first valuation contract and the second valuation contract.

In this example, the blockchain network executing the product valuation contract based on the target transaction may specifically include: and performing first processing corresponding to the first estimation logic on the product information and the user information to obtain an initial estimation aiming at the target product. The initial estimate indicates an estimate of the target product for the user as a whole. And performing second processing corresponding to the second valuation logic on the product information and the user information to obtain a risk value aiming at the target product, wherein the risk value indicates the probability that the indemnity agreement is met after the user purchases the target product. And determining a product estimate in combination with the initial estimate and the risk value.

In one particular example, the initial estimate and the risk value can be weighted and summed, and based on the weighted sum, a product estimate can be determined.

In yet another example, the user information is encrypted user information, and the product valuation contract includes a privacy contract portion that is dependent on the user information. In addition, a clear contract portion may be included that depends on product information. In this example, the execution method of the product valuation contract can be as shown in FIG. 9.

In fig. 9, any node in the blockchain network loads the target transaction into the trusted execution environment TEE where the encrypted user information is decrypted and the privacy contract portion is executed. And executing the plaintext contract portion based on the product information in a normal environment. And finally, fusing contract state parameters corresponding to the privacy contract part with contract state parameters corresponding to the plaintext contract part to obtain product evaluation values.

Of course, in practical applications, the blockchain network may also store encrypted contract state parameters associated with executing the privacy contract portion.

The blockchain network provides the product estimate to the client, step 806.

The client may present the product valuation to the user for the user to decide whether to purchase the target product.

In summary, the method for evaluating a product value based on a block chain provided in the embodiments of the present specification evaluates a value of a target product by executing a product evaluation contract pre-deployed in a block chain network, and can implement transparency, openness, and auditability of a product evaluation process. In addition, the product valuation contract determines the product valuation of the target product for the current user based on the product information and the user information, and can realize flexible valuation of thousands of people.

In correspondence with the method for evaluating a product value based on a blockchain, an embodiment of the present specification further provides a system for evaluating a product value based on a blockchain, as shown in fig. 10, where the system may include: a client 1002 and a blockchain network 1004.

The client 1002 is configured to submit a target transaction invoking a product valuation contract to the blockchain network in response to a user query request for a target product, where the target product is accompanied by a reimbursement agreement. The target transaction includes product information of the target product and user information of the user, the product information including agreement information of the indemnity agreement.

A blockchain network 1004 for executing a 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.

Contract logic in the product valuation contract is constructed based on a pre-trained valuation model.

In one example, the product valuation contracts include a first valuation contract in which first valuation logic is constructed based on a common valuation formula;

the blockchain network 1004 is specifically configured to:

and performing first processing corresponding to the first evaluation logic on the product information and the user information, and determining the product evaluation according to the first processing result. Wherein the first processing result indicates the target product to be aimed at the evaluation condition of the user as a whole.

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

the blockchain network 1004 is further specifically configured to:

In yet another example, the product valuation contracts include a first valuation contract in which first valuation logic is constructed based on a common valuation formula and a second valuation contract in which second valuation logic is constructed based on a pre-trained risk assessment model;

the blockchain network 1004 is further specifically configured to:

performing first processing corresponding to first evaluation logic on the product information and the user information to obtain an initial evaluation value aiming at a target product; the initial estimation indicates the estimation condition of the target product aiming at the user as a whole;

performing second processing corresponding to second evaluation logic on the product information and the user information to obtain a risk value for the target product; the risk value indicating a probability that a reimbursement agreement was satisfied after the user purchased the target product;

and determining a product estimate in combination with the initial estimate and the risk value.

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

the blockchain network 1004 is further specifically configured to:

the target transaction is loaded into the trusted execution environment TEE where the encrypted user information is decrypted and the privacy contract portion is executed. In addition, contract state parameters associated with executing the privacy contract part may also be stored encrypted.

The blockchain network 1004 is also used to provide product valuations to the client 1002.

Optionally, the client 1002 is further configured to obtain a general estimation formula, and create a corresponding UML model for the general estimation formula;

the client 1002 is further configured to construct a first estimation logic according to the UML model;

the client 1002 is further configured to submit a first transaction to deploy a first valuation contract to the blockchain network 1004, the first transaction including the first valuation logic.

Optionally, the system may also include n data holders 1006 and trusted third parties 1008.

Each of the n data holders 1006 is configured to digitally sign a corresponding training sample, encrypt the signature result and the training sample, and provide the encrypted result to the trusted third party 1008.

Taking a first data party 1006 of any of the n data holders 1006 as an example, the first data party 1006 digitally signs a corresponding training sample using a first private key saved in advance, encrypts a corresponding signature result and the training sample using a second public key of the trusted third party 1008, and provides the encrypted result to the trusted third party 1008.

And the trusted third party 1008 is configured to receive the n encrypted results sent by the n data holders 1006, load the n encrypted results into a trusted execution environment TEE, decrypt the n encrypted results in the TEE, and check the n training samples obtained by decryption.

In the foregoing example, the trusted third party 1008 is specifically configured to: and decrypting the encrypted result sent by the first data party by using a second private key corresponding to the second public key, and verifying the signature of the decrypted training sample by using a first public key corresponding to the first private key.

And the trusted third party 1008 is further used for training the risk assessment model based on the n training samples after the signature verification passes, and constructing a second evaluation logic corresponding to the trained risk assessment model.

The trusted third party 1008 is also specifically configured to: converting the operation contained in the trained risk assessment model into matrix operation; based on the matrix operation, a second evaluation logic is constructed.

The trusted third party 1008 is also configured to submit a second transaction to deploy a second valuation contract to the blockchain network 1004, the second transaction including second valuation logic.

Optionally, trusted third party 1008 is further configured to receive encrypted delta data sent by any of n data holders 1006.

The trusted third party 1008 is further configured to perform 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 1008 is also used to reconstruct the second valuation logic based on the currently trained risk assessment model.

The trusted third party 1008 is also configured to submit a third transaction to update the second valuation contract to the blockchain network 1004, the third transaction including the reconstructed second valuation logic.

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

The first node is further configured to load the fourth transaction into a trusted execution environment TEE, where the encrypted training samples are decrypted and the risk assessment model is trained based on the plaintext training samples.

The first node is further configured to construct a second valuation logic based on the trained risk assessment model and deploy the second valuation contract on the blockchain network 1004 as contract content of the second valuation contract.

In addition, the first node is also configured to publish the trained risk assessment model on the blockchain network 1004.

Optionally, any second node in blockchain network 1004 is configured to receive a fifth transaction submitted by any data holder 1006 of the n data holders 1006, where the fifth transaction includes at least encrypted delta data of the data holder 1006.

The second node is further configured to pull the trained risk assessment model from the blockchain network 1004, and perform incremental training on the trained risk assessment model based on the encrypted incremental data to obtain a currently trained risk assessment model.

The second node is further configured to publish the currently trained risk assessment model on the blockchain network 1004 and update the second valuation contract based thereon.

The functions of each functional module of the system in the above embodiments of the present description may be implemented through each step of the above method embodiments, and therefore, a specific working process of the system provided in one embodiment of the present description is not repeated herein.

The system for evaluating the product value based on the block chain provided by one embodiment of the specification can improve the flexibility of target product value evaluation.

According to an embodiment of another aspect, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method described in connection with any of fig. 3 to 9.

According to an embodiment of yet another aspect, there is also provided a computing device comprising a memory and a processor, the memory having stored therein executable code, the processor implementing the method described in conjunction with any one of fig. 3-9 when executing the executable code.

The embodiments in the present specification are described in a progressive manner, and the same and similar parts among the embodiments are referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.

The steps of a method or algorithm described in connection with the disclosure herein may be embodied in hardware or may be embodied in software instructions executed by a processor. The software instructions may consist of corresponding software modules that may be stored in RAM memory, flash memory, ROM memory, EPROM memory, EEPROM memory, registers, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to the processor such the processor can read information from, and write information to, the storage medium. Of course, the storage medium may also be integral to the processor. The processor and the storage medium may reside in an ASIC. Additionally, the ASIC may reside in a server. Of course, the processor and the storage medium may reside as discrete components in a server.

Those skilled in the art will recognize that, in one or more of the examples described above, the functions described in this invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, the functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium. Computer-readable media includes both computer storage media and communication media including any medium that facilitates transfer of a computer program from one place to another. A storage media may be any available media that can be accessed by a general purpose or special purpose computer.

The foregoing description has been directed to specific embodiments of this disclosure. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.

The above-mentioned embodiments, objects, technical solutions and advantages of the present specification are further described in detail, it should be understood that the above-mentioned embodiments are only specific embodiments of the present specification, and are not intended to limit the scope of the present specification, and any modifications, equivalent substitutions, improvements and the like made on the basis of the technical solutions of the present specification should be included in the scope of the present specification.

Claims

1. A blockchain-based method of assessing product value, comprising:

the blockchain network provides the product valuation to the client.

2. The method of claim 1, wherein the contract logic in the product valuation contract is constructed based on a pre-trained valuation model.

3. The method of claim 1, wherein the product valuation contract comprises a first valuation contract in which first valuation logic is constructed based on a common valuation formula;

the blockchain network executing the product valuation contract based on the target transaction, including:

performing first processing corresponding to the first evaluation logic on the product information and the user information, and determining the product evaluation according to a first processing result; wherein the first processing result indicates an evaluation situation of the target product for the user as a whole.

4. The method of claim 1, wherein the product valuation contract comprises a second valuation contract in which second valuation logic is constructed based on a pre-trained risk assessment model;

and performing second processing corresponding to the second valuation logic on the product information and the user information to obtain a risk value of the user for the target product, and determining the product valuation according to the risk value, wherein the risk value indicates the probability that the indemnity agreement is met after the user purchases the target product.

5. The method of claim 1, wherein the product valuation contracts include a first valuation contract in which first valuation logic is constructed based on a common valuation formula and a second valuation contract in which second valuation logic is constructed based on a pre-trained risk assessment model;

performing first processing corresponding to the first estimation logic on the product information and the user information to obtain an initial estimation of the target product; the initial valuation indicates an valuation situation of the target product for the user as a whole;

performing second processing corresponding to the second evaluation logic on the product information and the user information to obtain a risk value for the target product; the risk value indicates a probability that the reimbursement agreement was satisfied after the user purchased the target product;

determining the product estimate in conjunction with the initial estimate and the risk value.

6. The method of claim 3 or 5, wherein the first valuation contract is deployed into the blockchain network by:

the client acquires the general valuation formula and creates a corresponding UML model aiming at the general valuation formula;

the client side constructs the first estimation logic according to the UML model;

the client submits a first transaction to the blockchain network that deploys the first valuation contract, the first transaction including the first valuation logic.

7. The method of claim 4 or 5, wherein the second valuation contract is deployed into the blockchain network by:

each data holder i of the n data holders digitally signs the corresponding training sample, encrypts the signing result and the training sample and provides the encrypted result to a trusted third party;

the trusted third party receives n encrypted results sent by n data holders, loads the n encrypted results into a Trusted Execution Environment (TEE), decrypts the n encrypted results in the TEE, and verifies the n decrypted training samples;

after the signature verification passes, 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 submitting a second transaction to the blockchain network deploying the second valuation contract, the second transaction including the second valuation logic.

8. The method of claim 7, said n data holders comprising a first data holder;

the digitally signing the corresponding training sample, encrypting the signing result and the training sample and providing the encrypted result and the encrypted training sample to a trusted third party includes:

the first data party carries out digital signature on the corresponding training sample by using a first private key saved in advance, encrypts the corresponding signature result and the training sample by using a second public key of the trusted third party, and provides the encrypted result to the trusted third party;

the decrypting the n encrypted results and the verifying the n training samples obtained by decryption comprise:

and the trusted third party decrypts the encrypted result sent by the first data party by using a second private key corresponding to the second public key, and verifies the decrypted training sample by using a first public key corresponding to the first private key.

9. The method of claim 7, wherein said constructing second valuation logic corresponding to a trained risk assessment model comprises:

converting the operation contained in the trained risk assessment model into matrix operation;

based on the matrix operation, the second evaluation logic is constructed.

10. The method of claim 7, further comprising:

the trusted third party receives encrypted incremental data sent by any data holder i in 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 a second evaluation logic based on the currently trained risk assessment model;

the trusted third party submitting a third transaction to the blockchain network that updates the second valuation contract, the third transaction including reconstructed second valuation logic.

11. The method of claim 4 or 5, wherein the second valuation contract is deployed into the blockchain network by:

any first node in the block chain network receives fourth transactions submitted by n data holders respectively; the fourth transaction includes at least encrypted training samples of the corresponding data holder;

the first node loads the fourth transaction into a Trusted Execution Environment (TEE), decrypts an encrypted training sample in the TEE, and trains a risk assessment model based on a plaintext training sample;

and the first node constructs a second evaluation logic based on the trained risk assessment model, and uses the second evaluation logic as contract content of the second evaluation contract, and deploys the second evaluation contract on the blockchain network.

12. The method of claim 11, further comprising:

and the first node issues the trained risk assessment model on the blockchain network.

13. The method of claim 12, further comprising:

any second node in the block chain network receives a fifth transaction submitted by any data holder i in the n data holders; the fifth transaction comprises at least encrypted delta data of the data holder i;

the second node pulls the trained risk assessment model from the block chain network, and performs incremental training on the trained risk assessment 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 thereon.

14. The method of claim 1, wherein the user information is encrypted user information; the product valuation contract includes a privacy contract portion that depends on the user information;

and loading the target transaction into a Trusted Execution Environment (TEE), decrypting the encrypted user information in the TEE, and executing the privacy contract part.

15. The method of claim 14, further comprising:

and encrypting and storing contract state parameters related to executing the privacy contract part.

16. A system for assessing product value based on a blockchain comprises a client and a blockchain network;

17. The system of claim 16, wherein the product valuation contract comprises a first valuation contract in which first valuation logic is constructed based on a common valuation formula;

the blockchain network is specifically configured to:

18. The system of claim 16, wherein the product valuation contract comprises a second valuation contract in which second valuation logic is constructed based on a pre-trained risk assessment model;

the block chain network is further specifically configured to:

19. The system of claim 16, wherein the product valuation contracts include a first valuation contract in which first valuation logic is constructed based on a common valuation formula and a second valuation contract in which second valuation logic is constructed based on a pre-trained risk assessment model;

the block chain network is further specifically configured to:

20. The system according to claim 17 or 19,

the client is further used for obtaining the general valuation formula and establishing a corresponding UML model aiming at the general valuation formula;

the client is further used for constructing the first evaluation logic according to the UML model;

the client is further configured to submit a first transaction to the blockchain network that deploys the first valuation contract, the first transaction including the first valuation logic.

21. The system of claim 18 or 19, further comprising n data-holders and trusted third parties;

each data holder i of the n data holders is used for carrying out digital signature on the corresponding training sample, and encrypting the signature result and the training sample and then providing the encrypted result to the trusted third party;

the trusted third party is used for receiving n encrypted results sent by n data holders, loading the n encrypted results into a trusted execution environment TEE, decrypting the n encrypted results in the TEE, and verifying and signing the n training samples obtained through decryption;

the trusted third party is further used for training a risk assessment model based on the n training samples after the signature passes, and constructing 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 deploying the second valuation contract, the second transaction including the second valuation logic.

22. The system of claim 18 or 19, further comprising n data holders;

any first node in the block chain network is used for receiving fourth transactions submitted by the n data holders respectively; the fourth transaction includes at least encrypted training samples of the corresponding data holder;

the first node is further configured to load the fourth transaction into a Trusted Execution Environment (TEE), decrypt, in the TEE, an encrypted training sample, and train a risk assessment model based on a 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 contract content of the second valuation contract, and deploy the second valuation contract on the blockchain network.

23. The system of claim 16, wherein the user information is encrypted user information; the product valuation contract includes a privacy contract portion that depends on the user information;

the block chain network is further specifically configured to:

24. A computer-readable storage medium, on which a computer program is stored, wherein the computer program causes a computer to carry out the method of any one of claims 1-15, when the computer program is carried out in the computer.

25. A computing device comprising a memory and a processor, wherein the memory has stored therein executable code that when executed by the processor implements the method of any of claims 1-15.