CN114579857A

CN114579857A - Object recommendation method, device and system based on block chain

Info

Publication number: CN114579857A
Application number: CN202210208616.2A
Authority: CN
Inventors: 陈聪明
Original assignee: Alipay Labs Singapore Pte Ltd
Current assignee: Advanced Nova Technology Singapore Holdings Ltd
Priority date: 2022-03-03
Filing date: 2022-03-03
Publication date: 2022-06-03

Abstract

An embodiment of the present specification provides an object recommendation method, an object recommendation device, and an object recommendation system based on a blockchain, where the object recommendation method based on a blockchain is applied to a node device in a blockchain network, and includes: receiving a recommendation request aiming at a target object sent by a client; responding to the recommendation request, calling an intelligent contract, and performing privacy data processing on user privacy data submitted by each data platform to obtain a user feature set; and sending the user feature set to the client so that the client screens out the target user according to the user feature set and recommends the target object to the target user. By the method, the user characteristic set can be generated more accurately while the safety of the user privacy data is ensured, so that the client can recommend the target object to the target user more pertinently.

Description

Object recommendation method, device and system based on block chain

Technical Field

The embodiment of the specification relates to the technical field of computers, in particular to an object recommendation method based on a block chain.

Background

With the development of internet technology, each network platform can send various recommendation information to users according to the requirements of the users so as to meet the personalized requirements of different users.

At present, each network platform sends personalized recommendation information to a user based on user data of each platform, and the platform with deficient user data volume cannot send accurate recommendation information to the user; and the user data of each platform relates to user privacy and business confidentiality, and the user data cannot be directly shared among a plurality of platforms to accurately send personalized recommendation information to the user.

Therefore, how to accurately send personalized recommendation information to a user is a problem which needs to be solved urgently at present.

Disclosure of Invention

In view of this, the embodiments of the present specification provide an object recommendation method based on a block chain. One or more embodiments of the present disclosure also relate to an object recommendation apparatus based on a blockchain, an object recommendation system based on a blockchain, a computing device, a computer-readable storage medium, and a computer program, so as to solve technical deficiencies in the prior art.

According to a first aspect of the embodiments of the present specification, an object recommendation method based on a blockchain is provided, which is applied to a node device in a blockchain network, where the node device stores user privacy data submitted by each data platform, and an intelligent contract for user privacy data management is deployed on the blockchain network; the method comprises the following steps:

receiving a recommendation request aiming at a target object sent by a client;

responding to the recommendation request, calling the intelligent contract, and performing privacy data processing on the user privacy data submitted by each data platform to obtain a user feature set;

and sending the user feature set to the client, so that the client screens out a target user according to the user feature set and recommends the target object to the target user.

According to a second aspect of the embodiments of the present specification, there is provided a blockchain-based object recommendation method, applied to a client, the method including:

sending a recommendation request aiming at a target object to node equipment in a block chain network;

receiving a user feature set fed back by the node equipment, wherein the user feature set is obtained by calling an intelligent contract to perform privacy data processing on user privacy data of each data platform by the node equipment in response to the recommendation request, and the intelligent contract is deployed on the block chain network and used for user privacy data management;

and screening out target users according to the user feature set, and recommending the target objects to the target users.

According to a third aspect of the embodiments of the present specification, there is provided an object recommendation apparatus based on a blockchain, which is applied to a node device in a blockchain network, where the node device stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the blockchain network; the device comprises:

the first receiving module is configured to receive a recommendation request for a target object sent by a client;

the privacy processing module is configured to respond to the recommendation request, call the intelligent contract, and perform privacy data processing on the user privacy data submitted by each data platform to obtain a user feature set;

the first sending module is configured to send the user feature set to the client, so that the client screens out a target user according to the user feature set and recommends the target object to the target user.

According to a fourth aspect of embodiments of the present specification, there is provided an object recommendation apparatus based on a blockchain, applied to a client, the apparatus including:

a second sending module configured to send a recommendation request for the target object to a node device in the blockchain network;

a second receiving module, configured to receive a user feature set fed back by the node device, where the user feature set is obtained by the node device responding to the recommendation request and invoking an intelligent contract to perform privacy data processing on user privacy data of each data platform, and the intelligent contract is deployed on the block chain network and used for user privacy data management;

and the recommending module is configured to screen out target users according to the user feature set and recommend the target objects to the target users.

According to a fifth aspect of embodiments of the present specification, there is provided a blockchain-based object recommendation system, including at least one data platform, a blockchain network and a client, where the blockchain network includes a plurality of node devices, and an intelligent contract for user privacy data management is deployed on the blockchain network;

each data platform submits the user privacy data to the node equipment in the block chain network for storage;

the client sends a recommendation request aiming at a target object to node equipment in the block chain network;

the node equipment in the block chain responds to the recommendation request, calls the intelligent contract, and carries out privacy data processing on the user privacy data of each data platform to obtain a user feature set; sending the user feature set to the client;

and the client screens out a target user according to the user feature set and recommends the target object to the target user.

According to a sixth aspect of embodiments herein, there is provided a computing device comprising:

a memory and a processor;

the memory is used for storing computer-executable instructions, and the processor is used for executing the computer-executable instructions, and the computer-executable instructions when executed by the processor realize the steps of the object recommendation method based on the block chain.

According to a seventh aspect of the embodiments of the present specification, there is provided a computer-readable storage medium storing computer-executable instructions, which when executed by a processor, implement the steps of the above object recommendation method based on block chains.

According to an eighth aspect of embodiments of the present specification, there is provided a computer program, wherein when the computer program is executed in a computer, the computer program is used for executing the steps of the object recommendation method based on the block chain.

The object recommendation method based on the blockchain is applied to node equipment in a blockchain network, wherein the node equipment stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the blockchain network; the method comprises the steps of receiving a recommendation request aiming at a target object sent by a client, responding to the recommendation request, calling an intelligent contract, and carrying out privacy data processing on user privacy data submitted by each data platform to obtain a user feature set; and then sending the user feature set to the client so that the client screens out the target user according to the user feature set and recommends the target object to the target user. By the method, the intelligent contract is called based on the recommendation request aiming at the target object sent by the client, and the privacy data of the user submitted by each data platform are processed, so that the security of the privacy data of the user can be ensured, and the risk of leakage of the privacy data of the user is avoided; meanwhile, a credible information sharing environment is established between each data platform and the client through the blockchain network, node equipment in the blockchain network responds to a recommendation request aiming at a target object sent by the client, calls an intelligent contract and carries out privacy data processing on user privacy data submitted by each data platform, so that a more accurate user feature set is obtained, the client can screen out the target user according to the user feature set, and the accuracy of recommending the target object to the target user is improved.

Drawings

FIG. 1 is a flow chart illustrating a method for blockchain-based object recommendation provided in accordance with one embodiment of the present specification;

FIG. 2 is a flow diagram illustrating another blockchain-based object recommendation method provided in accordance with one embodiment of the present specification;

FIG. 3 is a process diagram illustrating a blockchain-based object recommendation method according to an embodiment of the present disclosure;

fig. 4 is a flowchart illustrating an information sharing method in a blockchain-based object recommendation method according to an embodiment of the present specification;

FIG. 5 is a flowchart illustrating a marketing recommendation method in a blockchain-based object recommendation method according to an embodiment of the present disclosure;

FIG. 6 is a block diagram illustrating an architecture of an object recommendation apparatus based on a blockchain according to an embodiment of the present disclosure;

FIG. 7 is a block diagram illustrating an architecture of another blockchain-based object recommendation apparatus according to an embodiment of the present disclosure;

FIG. 8 is a block diagram illustrating an architecture of a blockchain-based object recommendation system according to an embodiment of the present disclosure;

FIG. 9 illustrates a block diagram of a computing device, according to one embodiment of the present description.

Detailed Description

In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present description. This description may be embodied in many different forms and should not be construed as limited to the embodiments set forth herein, as those skilled in the art will be able to make and use the present disclosure without departing from the spirit and scope of the present disclosure.

The terminology used in the description of the one or more embodiments is for the purpose of describing the particular embodiments only and is not intended to be limiting of the description of the one or more embodiments. As used in one or more embodiments of the present specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used in one or more embodiments of the present specification refers to and encompasses any and all possible combinations of one or more of the associated listed items.

It will be understood that, although the terms first, second, etc. may be used herein in one or more embodiments to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, a first can also be referred to as a second and, similarly, a second can also be referred to as a first without departing from the scope of one or more embodiments of the present description. The word "if" as used herein may be interpreted as "at … …" or "when … …" or "in response to a determination", depending on the context.

First, the noun terms referred to in one or more embodiments of the present specification are explained.

Block chains: the block chain is a special distributed database technology, is suitable for storing simple data which have precedence relationship and can be verified in a system, and guarantees that the data cannot be tampered and counterfeited by using cryptography and a consensus algorithm. From a technological level, the blockchain involves many scientific and technical problems such as mathematics, cryptography, internet and computer programming. From the application perspective, the blockchain is a distributed shared account book and a database, and has the characteristics of decentralization, no tampering, trace leaving in the whole process, traceability, collective maintenance, public transparency and the like. The characteristics ensure the honesty and the transparency of the block chain and lay a foundation for creating trust for the block chain. And the rich application scenes of the block chains basically solve the problem of information asymmetry based on the block chains, and realize the cooperative trust and consistent action among a plurality of main bodies.

Smart Contract (Smart Contract): is a computer protocol intended to propagate, validate or execute contracts in an informational manner. Smart contracts allow trusted transactions to be conducted without third parties, which transactions are traceable and irreversible. The goal of smart contracts is to provide a secure method over traditional contracts and to reduce other transaction costs associated with the contracts.

And (3) privacy calculation: the method is a computing theory and a method for protecting privacy information in a full life cycle, and particularly relates to a method for describing, measuring, evaluating, fusing and the like the related privacy information when processing information such as video, audio, images, graphics, characters, numerical values, network behavior information streams and the like, so that a set of symbolized and formulaized privacy computing theory, algorithm and application technology with quantitative evaluation standards are formed, and the protection of the privacy information with multi-system fusion is supported.

Multi Party secure computing (MPC): the algorithm is a type of algorithm for privacy calculation, and the core is to solve the problem of cooperative calculation for protecting privacy among a group of mutually untrusted participants. MPC is required to ensure the characteristics of independence of inputs, correctness of calculation, decentralization, etc., and not to leak each input value to other members participating in calculation. The method mainly aims at the problem of how to safely calculate an agreed function under the condition of no trusted third party, and simultaneously requires that each participating subject cannot obtain any input information of other entities except the calculation result. Secure multiparty computing plays an important role in electronic elections, electronic voting, electronic auctions, secret sharing, threshold signatures, and other scenarios. Secure multi-party computing is usually implemented in combination with technical schemes such as homomorphic encryption, zero-knowledge proof, garbled circuit, and secret sharing.

User portrait: the user portrait is also called a user role and is used as an effective tool for drawing target users and connecting user appeal and design direction, and the user portrait is widely applied to various fields. In the practical operation process, the attributes and behaviors of the user are often combined with expected data conversion by the utterances with the most shallow and close to life. As a virtual representation of an actual user, the user roles formed by user portrayal are not constructed outside products and markets, and the formed user roles need to represent the main audience and target groups of the products. For example, a user representation may typically include the user's purchasing habits, historical orders, hobbies, and the like.

With the development of internet technology, each network platform can send various recommendation information to users according to the requirements of the users so as to meet the personalized requirements of different users. At present, each network platform sends personalized recommendation information to a user based on user data of each platform, and accurate recommendation information cannot be sent to the user for the platform with insufficient user data; user privacy and business secrets are designed according to the user data of each platform, and the user data cannot be directly shared among a plurality of platforms to accurately send personalized recommendation information to the user.

In view of the foregoing, in order to better and more accurately recommend a target object to a target user, the present specification provides an object recommendation method based on a block chain, and one or more embodiments of the present specification relate to an object recommendation apparatus based on a block chain, an object recommendation system based on a block chain, a computing device, a computer-readable storage medium, and a computer program, which are described in detail in the following embodiments one by one.

The blockchain network described in one or more embodiments of the present specification may specifically refer to a P2P network system having a distributed data storage structure and achieved by a consensus mechanism, where the P2P network system is suitable for storing simple data that has a precedence relationship and can be verified in the system, and the cryptology and the consensus algorithm are used to ensure that the data is not falsifiable or falsifiable.

In one or more embodiments of the present specification, node devices in a blockchain network store user privacy data submitted by each data platform. From the perspective of each data platform, the block chain network is a distributed shared account book and database, and has the characteristics of decentralization, no tampering, trace remaining in the whole process, traceability, collective maintenance, public transparency and the like. The characteristics ensure the honesty and transparency of the blockchain network and lay a foundation for creating trust for the blockchain network. Therefore, each data platform can safely submit the user privacy data to the node equipment in the blockchain network for storage, and a credible information sharing environment is built among the data platforms through the blockchain network, so that the risk of leakage of the user privacy data is not needed to be worried about.

Meanwhile, a Smart Contract (Smart Contract) for managing user private data is also deployed on the blockchain network, wherein the Smart Contract is a computer protocol which can be defined by a code form and aims to propagate, verify or execute the Contract in an informatization manner. In this embodiment, the purpose of the smart contract is to manage user privacy data.

In this specification, each data platform may be various online shopping platforms or online video platforms, and each data platform may submit its own user privacy data to a node device in the blockchain network for storage, and then the node device in the blockchain network calls an intelligent contract to manage the user privacy data.

Referring to fig. 1, fig. 1 is a flowchart illustrating a method for recommending an object based on a blockchain according to an embodiment of the present disclosure. The method is applied to node equipment in a block chain network, and specifically comprises the following steps:

s102, receiving a recommendation request aiming at a target object sent by a client.

The client in this embodiment is configured to recommend a target object to a user, where the target object is target object information recommended to the user, and may recommend a target product, a target website, a target video, or the like to the user, for example.

In particular practical applications, the client for recommending the target object to the user may select a client with a huge number of users, such as an electronic wallet client, a social client in common use, and the like. In an actual application scene, users can select different data platforms to shop or watch online videos and the like according to own preferences, but for the data platforms with the deficient number of users, the data platforms can only recommend the users, and the recommendation range cannot be expanded. Therefore, each data platform with a deficient number of users can be combined with one or more clients with a huge number of users, and target objects of each data platform are recommended to the users of the clients based on the huge user groups of the clients, so that each data platform can send recommendation information of the platform to more users.

In this embodiment, a recommendation request for a target object sent by a client needs to be received first, where the recommendation request carries a query condition, and the query condition is used to query user privacy data stored in a node device by each data platform.

Specifically, the recommendation request for the target object may be obtained as follows:

first, each data platform needs to synchronize its own object information to the client, where the object information refers to information recommended to the user by each data platform, and may be, for example, commodity type information (for example, commodity name, commodity type, etc.) of the data platform that is heavily promoted, promotion information (for example, details of value of commodities participating in promotion, promotion width, promotion time, etc.), and the like.

And then, the client generates a recommendation request based on the synchronous object information of each data platform, wherein the recommendation request carries query conditions, and the query conditions are used for querying user privacy data stored in the node equipment by each data platform.

For example, each data platform synchronizes respective object information (digital product mobile phone a, original price 5000 yuan, promotion price 4500 yuan, promotion amplitude 90%, promotion time 2 months) to the client; the client generates a query condition of which users visit the product related information of at least 5 times at 20-22 points in the weekday and have average page stay time longer than 1 minute based on the synchronous object information of each data platform, then queries the user privacy data stored in the node equipment based on the query condition, and finally generates a recommendation request.

In a possible implementation manner of the embodiment of this specification, before receiving a recommendation request for a target object sent by a client, the method further includes:

and receiving and storing user privacy data submitted by each data platform, wherein the user privacy data are submitted after each data platform is encrypted based on a preset format.

In this embodiment, the user privacy data refers to data related to user privacy recorded by each data platform, for example, the user privacy data may include user identification data and user behavior data. The user identification data refers to data capable of identifying the identity of the user, and may be, for example, the name, the phone number, the place of residence, the occupation, the education level, and the like of the user. The user behavior data refers to behavior information of the user in the data platform, and may be login time, login market, types of accessed commodities, dwell time of pages, whether an order is paid successfully, or the like.

Through the user privacy data, the identity, the operation habit, the interest and the like of the user in the data platform can be accurately grasped, and personalized recommendation information can be generated in a targeted manner based on the user behavior information and recommended to the user.

It should be noted that, before receiving and storing the user privacy data submitted by each data platform, the method further includes:

receiving registration requests sent by each data platform;

and distributing a key pair to each data platform based on the registration request, so that each data platform encrypts the user privacy data based on the key pair and a preset format by using a preset encryption algorithm.

In this embodiment, before receiving and storing user privacy data submitted by each data platform, a registration request sent by each data platform needs to be accepted, where the registration request refers to a request for registering each data platform on a blockchain network, and after receiving the registration request sent by each data platform, one or more node devices are allocated to each data platform, so that each data platform can implement association between data platforms based on the blockchain network, and further form a data platform association.

It should be noted that there are multiple node devices in the blockchain network, and the multiple node devices are used for storing the user privacy data submitted by each data platform. Each data platform can decide whether to hold the node device and how many node devices to hold based on the actual needs of the data platform. When the data platform does not hold the node device, it means that the node device in the blockchain network can be handed to other participants for hosting, and the other participants perform subsequent operations.

And while receiving a registration request sent by each data platform and distributing one or more node devices to each data platform, distributing a key pair to each data platform based on the registration request, wherein the key pair comprises a public key and a private key, so that each data platform encrypts user privacy data based on the key pair and a preset format by using a preset encryption algorithm.

In particular, the key pair is assigned to each data platform because each data platform needs to encrypt user private data based on the key pair. In practical applications, key encryption techniques are classified into symmetric key encryption techniques and asymmetric key encryption techniques. The symmetric key encryption technology is also called as private key encryption or session key encryption algorithm, namely, a sender and a receiver of information use the same key to encrypt and decrypt data, the greatest advantage is that the encryption/decryption speed is high, but key management is difficult, and once the key is leaked, the leakage of encrypted data is easily caused.

Asymmetric key cryptography, also known as public key cryptography, requires the use of separate keys, one of which is published publicly (i.e., a public key) and the other of which is kept secret by the user himself (i.e., a private key), to perform the encryption and decryption operations, respectively. The sender of the data is decrypted using the public key and the recipient of the data is decrypted using the private key.

In this embodiment, an asymmetric encryption technology is used to encrypt the user privacy data of each data platform. That is, in the asymmetric encryption technology, two kinds of keys are included in a key pair, which are divided into a private key and a public key. The private key can only be held by a user privacy data receiver and cannot be published; the public key is held by each data platform. Specifically, the public key is used to encrypt the user privacy data, and accordingly, the user privacy data encrypted with the public key can only be decrypted using the private key. That is, in the key pair, what is known to the public is the public key; private keys are known only to themselves and are not published to the public. The public key and the private key in one key pair are uniquely corresponding, and the public key and the private key can be mutually encrypted or decrypted (data encrypted by one key in the key pair must be decrypted by using the other key).

The public key is known to the public, so that even if the public key is acquired by a third party, the user privacy data is not leaked, and therefore, the encrypted user privacy data can be decrypted only by the private key corresponding to the public key; the private key is known only to the user privacy data recipient. Namely, after each data platform encrypts the user privacy data by using the public key, only the user privacy data receiver can decrypt the user behavior information by using the private key only known by the user, so that the user behavior information of each data platform can be ensured not to be leaked, and the encrypted transmission of the user behavior information is realized.

In the process that each data platform encrypts user privacy data based on a secret key, a preset encryption algorithm is required to encrypt the user privacy data, and the preset encryption algorithm is various, such as a homomorphic encryption algorithm, a federal learning algorithm and the like; and each preset encryption algorithm corresponds to the preset format, wherein the preset format is an information format specified by the preset encryption algorithm. That is to say, the preset format is a form in which the user privacy data is encrypted by using a preset encryption algorithm to form a ciphertext, and is generally a character string form with a certain length, but after different encryptions (for example, encryption algorithms such as federal learning) are calculated, ciphertext with character string forms with different lengths can be obtained, and characters contained in the ciphertext may also be different. For example, "SUybL 94tDIQX3 uufusts 7wwOYJN + viGsfzg3 hcbirx ═ is a ciphertext after encrypting certain data.

In this embodiment, each data platform may use a homomorphic encryption algorithm to encrypt the user privacy data of each data platform respectively. The homomorphic encryption algorithm can calculate the encrypted data without decrypting the data, the content of any original data cannot be leaked in the calculation process, and the encrypted data can be decrypted after the encrypted data is calculated to obtain the calculated data result.

In the above embodiment, before receiving and storing the user privacy data submitted by each data platform, it is further required to receive a registration request sent by each data platform, and distribute a key pair to each data platform based on the registration request, so that each data platform encrypts the user privacy data based on the key pair and based on a preset format by using a preset encryption algorithm. According to the method, each data platform encrypts the user privacy data of the data platform by using the preset encryption algorithm to obtain the encrypted user privacy data in the preset format, so that the user privacy data of each data platform is effectively prevented from being leaked, and the safety of the user privacy data of each data platform is improved.

After receiving a registration request sent by each data platform and distributing a key pair to each data platform based on the registration request, user privacy data submitted by each data platform needs to be received and stored, wherein the user privacy data are submitted after each data platform is encrypted based on a preset format.

That is, after the user privacy data is encrypted based on the key pair and the preset format by using the preset encryption algorithm in each data platform, the encrypted user privacy data needs to be submitted to each node device in the blockchain network for storage.

Specifically, in a possible implementation manner of the embodiment of the present specification, after receiving a registration request sent by each data platform and allocating a key pair to each data platform based on the registration request, each data platform encrypts user privacy data of the data platform by using a public key in the key pair. And then, signing the encrypted user privacy data by using a private key in the key pair, and submitting the signed encrypted user privacy data to each node device in the block chain network.

The signature of the encrypted user privacy data refers to the digital signature of the encrypted user privacy data, the digital signature is a section of digital string which can only be generated by a user privacy data sender (namely each data platform) and cannot be forged by others, and the section of digital string is also an effective proof of the authenticity of information sent by the user privacy data sender.

In order to ensure that the encrypted user privacy data is indeed sent by each data platform, each data platform needs to perform digital signature on the encrypted user privacy data by using a private key in a key pair, so that the user privacy data is protected, and the user privacy data is prevented from being leaked. The method can be specifically realized by the following steps:

and each data platform firstly encrypts the user privacy data of the data platform by using the public key in the key pair to obtain the encrypted user privacy data. The encrypted user private data is then signed based on a private key, and before signing, the encrypted user private data needs to be subjected to hash calculation by using a hash function to obtain a Message Digest (Message Digest) of the encrypted user private data, wherein the hash function is a "compression function", an input with an arbitrary length can be converted into an output with a fixed length by using the hash function through a hash function algorithm (for example, cryptographic hash functions such as SHA-1 and SHA-2), and a hash value of the output is a Message Digest and is also called a digital Digest.

After the message digest of the encrypted user privacy data is obtained, each data platform signs the message digest by using a private key of the data platform to form a unique digital signature of each data platform, and then the digital signature and the encrypted user privacy data are sent to the node equipment of the block chain network together for storage.

In the above embodiment, before receiving a recommendation request for a target object sent by a client, user privacy data submitted by each data platform needs to be received and stored, where the user privacy data is submitted after each data platform is encrypted based on a preset format. By the method, the user privacy data can be encrypted based on the preset format, and the safety of the user privacy data is improved. When the data platforms submit the user privacy data, the user privacy data are signed, and authenticity of the user privacy data submitted by the data platforms is guaranteed.

And S104, responding to the recommendation request, calling an intelligent contract, and carrying out privacy data processing on the user privacy data submitted by each data platform to obtain a user feature set.

In this embodiment, the smart contracts are used for private data management. Specifically, after a recommendation request for a target object sent by a client is received, an intelligent contract is called in response to the recommendation request, and privacy data processing is performed on user privacy data submitted by each data platform to obtain a user feature set.

The privacy data processing is carried out on the user privacy data submitted by each data platform, namely, based on the query condition in the recommendation request, the user privacy data meeting the query condition in the user privacy data submitted by each data platform are called by an intelligent contract to carry out privacy calculation, and then a user characteristic set is obtained, wherein the user characteristic set is a set reflecting the user behavior characteristics of each data platform. The user feature set is also called a user image set and is used for representing main audiences and target groups of various data platform products, and specifically can comprise purchasing habits, historical orders, interests and hobbies and the like of users.

The privacy computing technology refers to a computing theory and a method for protecting privacy information in a full life cycle, and particularly refers to operations such as description, measurement, evaluation, fusion and the like on related privacy information when processing information such as videos, audios, images, graphs, characters, numerical values, network behavior information streams and the like, so that a set of symbolized and formulaized privacy computing theory, algorithm and application technology with quantitative evaluation standards are formed, and multi-system fusion privacy information protection is supported. The essence of the method is to solve the problems of data services such as data circulation, data application and the like on the premise of protecting data privacy. Private computing technologies include a variety of technologies such as protocol-based secure Multi-Party computing (MPC), modern password-based federated learning, and hardware-based trusted execution environments, among others.

In practical application, after a recommendation request for a target object sent by a client is received, privacy calculation can be performed on user privacy data meeting the query condition in the user privacy data submitted by each data platform by adopting a safe multi-party calculation technology, a federal learning technology or a trusted execution environment based on the query condition in the recommendation request, so as to obtain a user feature set, wherein the user feature set is also called a user image set and reflects behavior features of users of each data platform, so that the user feature set is used for representing main audiences and target groups of products, and specifically can include purchasing habits, historical orders, interests and the like of the users.

Taking the private computing technology MPC as an example, since MPC is a computing problem for securely performing multi-party collaboration without a trusted third party, that is, in a distributed network of a blockchain, multiple participating entities each encrypt and input data, each party wants to complete computation of a certain function together, and each participating entity is required to obtain no input information of other participating entities except for a computation result.

Therefore, the intelligent contract is based on the query request, the MPC technology is adopted, privacy calculation can be carried out on the user privacy data meeting the query conditions in the encrypted user privacy data, the user privacy data in the encrypted state is directly calculated, all participants can not know the user privacy data of the other party, and the safety of the user privacy data of all data platforms is guaranteed.

It should be noted that the blockchain network is mainly used for verifying the result of MPC calculation and preventing data from being tampered, and the confidentiality problem of input data does not need to be considered in the process; the MPC emphasizes the confidentiality of the input data in the calculation process, and whether the calculation result is tampered or not does not need to be considered in the process; therefore, the privacy computing technology MPC is combined with the blockchain 104, so that the security of the user privacy data of each data platform is effectively ensured, and the user privacy data of each data platform is prevented from being leaked.

In a possible implementation manner of the embodiment of the present specification, in response to a recommendation request, an intelligent contract is invoked, and privacy data processing is performed on user privacy data submitted by each data platform to obtain a user feature set, which may specifically be implemented in the following manner:

and responding to the recommendation request, calling an intelligent contract, and performing privacy data processing on the user privacy data submitted by each data platform by using a privacy data processing mode corresponding to a preset format to obtain a user feature set.

In this embodiment, the privacy data processing method corresponding to the preset format is used to perform privacy data processing on the user privacy data submitted by each data platform, which means that privacy calculation is performed on the user privacy data submitted by each data platform by using a privacy calculation technology corresponding to the preset format. The preset format corresponds to a privacy calculation technology, that is, different privacy calculation technologies correspond to different preset formats.

In practical application, after receiving user privacy data which are submitted by each data platform and encrypted based on a preset format and receiving a recommendation request which is sent by a client and aims at a target object, responding to the recommendation request, calling an intelligent contract, and carrying out privacy calculation on the user privacy data submitted by each data platform by using a privacy calculation technology corresponding to the preset format.

Specifically, in order to ensure the authenticity of the received user privacy data submitted by each data platform and the recommendation request sent by the client, the data platforms and the client are required to sign the user privacy data and the recommendation request respectively, and then the signature is verified by an intelligent contract, so that the authenticity of the user privacy data and the recommendation request is ensured.

The data platforms and the clients firstly perform Hash calculation on the encrypted user privacy data and the recommendation request to obtain the encrypted user privacy data and the message digest of the recommendation request, and after the message digest is obtained, the message digest of the encrypted user privacy data and the message digest of the recommendation request are signed by respective private keys;

and then the intelligent contract decrypts the signature based on the public key in the key pair held by the intelligent contract, and respectively obtains the encrypted message digest of the user privacy data and the message digest of the recommendation request. And then calculating the digest value by using the same hash calculation method as each data platform and the client, comparing the digest value with the digest obtained by decryption, and if the two are completely the same, indicating that the encrypted user privacy data and the recommendation request are not tampered midway.

After the authenticity of the encrypted user privacy data and the recommendation request is verified, privacy calculation technology corresponding to a preset format is adopted to perform privacy calculation on the user privacy data meeting the query conditions in the user privacy data encrypted by each data platform, and a user feature set is obtained.

Specifically, taking an example that the privacy computing technology corresponding to the preset format is an MPC technology, matching the encrypted user privacy data of each data platform with the query conditions in the recommendation request sent by the client, for example, the encrypted user privacy data includes user identification data and user behavior data, where the user identification data includes residence and occupation; the user behavior data comprises the types of browsed commodities and the time of browsing pages; the query in the recommendation request includes "which professional male users browse at which times for digital type goods".

Then, matching is carried out based on the user identification data, the user behavior data and the query conditions, and finally, the user behavior characteristics which meet the query conditions in each data platform are obtained: a data platform A: "a male user whose job is the IT industry likes to browse digital type goods eight to ten hours in saturday evening", the data platform B: "a male user who carelessly is a student likes to browse a digital type commodity seven to ten hours at saturday night", and the like.

And then, adding the user behaviors by using an MPC (multimedia personal computer) technology to finally obtain a user feature set, namely a user image set, wherein the user feature set comprises user features corresponding to the data platforms.

In the embodiment, in response to the recommendation request, the intelligent contract is called, and the privacy data processing mode corresponding to the preset format is utilized to perform privacy data processing on the user privacy data submitted by each data platform, so as to obtain the user feature set. By the method, the private data of the user submitted by each data platform is processed, the private data of the user in an encrypted state can be directly calculated, each participant can not know the private data of the user of the other participant, and the safety of the private data of the user of each data platform is guaranteed. The user feature set is obtained based on the user privacy data and the query recommendation request, and the user can be recommended accurately and pertinently.

And S106, sending the user feature set to the client, so that the client screens out the target user according to the user feature set and recommends the target object to the target user.

In this embodiment, after the privacy data of the users submitted by each data platform is processed to obtain the user feature set, the user feature set needs to be sent to the client, so that the client screens out the target users in the user group according to the user feature set, and recommends the target object to the target users.

It should be noted that, since the user feature set is obtained by using a preset encryption algorithm and performing privacy calculation, the user feature set obtained by the client is still in an encrypted state, and therefore the client is required to decrypt the user feature set to obtain a decrypted user feature set. Then, according to the decrypted user feature set, a target user is screened from the user group of the client, and then a target object is recommended to the target user, wherein the target user is a user in the client, and the user accords with the user feature set.

For example, the user feature set is that a male user who is 18-30 years old and has a job in the IT industry likes to browse digital commodities eight to ten points at saturday night, then the male user who is 18-30 years old and has the job in the IT industry in the client user group is screened out as a target user according to the user feature set, and then a target object of the digital commodities is recommended for the target user.

There are various ways of recommending the target user based on the user feature set, for example, the target user can be recommended directly based on the specific content of the user feature set after the user feature set is generated; or a certain time period can be preset, and the target user is recommended within the preset time period.

The object recommendation method based on the blockchain is applied to node equipment in a blockchain network, wherein the node equipment stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the blockchain network; the method comprises the steps of receiving a recommendation request aiming at a target object sent by a client, responding to the recommendation request, calling an intelligent contract, and carrying out privacy data processing on user privacy data submitted by each data platform to obtain a user feature set; and then, the user characteristic set is sent to the client side, so that the client side screens out the target user according to the user characteristic set, and recommends the target object to the target user. By the method, the intelligent contract is called based on the recommendation request aiming at the target object sent by the client, and the privacy data of the user submitted by each data platform are processed, so that the security of the privacy data of the user can be ensured, and the risk of leakage of the privacy data of the user is avoided; meanwhile, a credible information sharing environment is established between each data platform and the client through the blockchain network, node equipment in the blockchain network responds to a recommendation request aiming at a target object sent by the client, calls an intelligent contract and carries out privacy data processing on user privacy data submitted by each data platform, so that a more accurate user feature set is obtained, the client can screen out the target user according to the user feature set, and the accuracy of recommending the target object to the target user is improved.

Fig. 2 is a flowchart illustrating another object recommendation method based on a blockchain according to an embodiment of the present disclosure. The method is applied to the client and specifically comprises the following steps:

s202, sending a recommendation request aiming at the target object to the node equipment in the block chain network.

In this embodiment, the recommendation request is a request for recommending a target object to a user.

In a possible implementation manner of the embodiment of the present specification, in order to ensure the authenticity of sending a recommendation request for a target object to a node device in a blockchain network, a signature operation needs to be performed on the recommendation request before sending the recommendation request.

Specifically, the hash calculation is performed on the recommendation request to obtain a message digest of the recommendation request, and after the message digest is obtained, a signature operation is performed on the message digest of the recommendation request by using a private key to ensure the authenticity of the recommendation request for the target object.

In a possible implementation manner of the embodiment of this specification, before sending a recommendation request for a target object to a node device in a blockchain network, the method includes:

receiving synchronous object information of each data platform;

and generating a recommendation request aiming at the target object according to the object information.

In this embodiment, first, it is necessary to receive object information synchronized with each data platform, where the object information refers to information recommended to a user by each data platform, and may be, for example, commodity type information (for example, commodity name, commodity type, and the like) of a key promotion of each data platform, promotion information (for example, details of value of a commodity participating in a promotion, promotion width, promotion time, and the like), and the like.

And then, generating a recommendation request aiming at the target object according to the object information, wherein the recommendation request carries query conditions, and the query conditions are used for querying user privacy data stored in the node equipment by each data platform.

For example, the object information synchronized by each data platform is: the digital product mobile phone A has the original price of 5000 yuan, the sale promotion price of 4500 yuan, the promotion amplitude of 90% and the promotion time of 2 months. After receiving the object information synchronized by each data platform, generating a query condition of which the users visit the product related information for at least 5 times at 20-22 sunday and have average page stay time longer than 1 minute according to the object information, and then generating a recommendation request aiming at the target object based on the query condition.

In the above embodiment, the recommendation request for the target object is generated by receiving the object information synchronized by each data platform and then according to the object information. By the method, the target objects meeting the query conditions in each data platform can be accurately queried based on the recommendation request, and then recommendation is performed on the target objects, so that the accuracy of information recommendation is improved.

And S204, receiving a user feature set fed back by the node equipment, wherein the user feature set is obtained by calling an intelligent contract to perform privacy data processing on user privacy data of each data platform in response to a recommendation request by the node equipment, and the intelligent contract is deployed on a block chain network and used for user privacy data management.

In this embodiment, after sending a recommendation request for a target object to a node device in a blockchain network, the node device in the blockchain network invokes an intelligent contract to perform privacy data processing on user privacy data of each data platform, so as to obtain a user feature set.

The user characteristic set is a set reflecting user behavior characteristics of each data platform. The user feature set is also called a user image set and is used for representing main audiences and target groups of various data platform products, and specifically can comprise purchasing habits, historical orders, interests and hobbies and the like of users.

Specifically, after a recommendation request for a target object is sent to node equipment in a blockchain network, the node equipment in the blockchain network responds to the recommendation request, invokes an intelligent contract, performs privacy data processing on user privacy data submitted by each data platform by using a privacy data processing mode corresponding to a preset format to obtain a user feature set, and sends the user feature set to a client.

For example, taking the privacy computing technology corresponding to the preset format as an MPC technology as an example, matching the user privacy data encrypted by each data platform with the query conditions in the recommendation request, where the user privacy data includes user identification data and user behavior data, and the user identification data includes a place of residence and a place of occupation; the user behavior data comprises the types of browsed commodities and the time of browsing pages; the query in the recommendation request includes "which professional male users browse at which times for digital type goods".

Then, matching is carried out based on the user identification data, the user behavior data and the query conditions, and finally, the user behavior characteristics which meet the query conditions in each data platform are obtained: a data platform A: "a male user whose job is in IT industry likes to browse digital type goods eight to ten hours in saturday evening", data platform B: "a male user who carelessly is a student likes to browse a digital type commodity seven to ten hours at saturday night", and the like. And finally, adding the user behaviors by using an MPC (media control protocol) technology to obtain a user feature set, namely a user image set, wherein the user feature set comprises user features corresponding to the data platforms.

And calling an intelligent contract at node equipment in the block chain network to perform privacy data processing on the user privacy data of each data platform, and then sending the user feature set to the client after obtaining the user feature set. Accordingly, the client receives the user feature set fed back by the node device.

S206, screening out the target users according to the user feature set, and recommending the target objects to the target users.

After the user feature set fed back by the node device is received, the target users in the user group of the node device need to be screened out according to the user feature set, and then the target objects are recommended to the users.

It should be noted that, since the user feature set is obtained by performing privacy calculation by using a preset encryption algorithm, the obtained user feature set is still in an encrypted state, and therefore, the user feature set needs to be decrypted to obtain a decrypted user feature set. And then screening target users from the user group according to the decrypted user feature set, and then recommending the target users.

For example, the user feature set is that a male user who is 18-30 years old and has a job of the IT industry likes to browse digital commodities eight to ten points at saturday night, then the male user who is 18-30 years old and has the job of the IT industry is screened out as a target user according to the user population portrait, and then recommendation is carried out on the target user.

In one possible implementation manner of the embodiment of the present specification, the recommendation request includes a target time period and a target object identifier; recommending a target object to a target user, comprising:

and recommending the target object corresponding to the target object identification to the target user in the target time period.

The target time period is carried in the query condition of the recommendation request and is used for recommending the user; the target object identification refers to identification information which is carried in a query condition of the recommendation request and can represent the type of a target object; the target object is object information which meets the user characteristic set in the object information of each data synchronization.

Specifically, for example, the query conditions in the recommendation request are: "which occupations of male users browse at which times for digital type goods", wherein the "digital type goods" carry the target object identification;

the user feature set is: "male users who are professional in the IT industry like to browse digital type goods eight to ten hours on saturday nights";

and then according to the user feature set, identifying 'digital type commodities' based on the target object in the recommendation request, and determining 'digital type commodities' in the object information synchronized by each data platform as the target object. And recommending recommendation information of digital commodities, such as commodity values, promotion amplitudes, promotion times and the like of mobile phones and cameras, to the male user at a target time period, namely eight to ten nights every six weeks.

In the above embodiment, the recommendation request includes a target time period and a target object identification; and recommending the target object corresponding to the target object identifier to the target user in the target time period.

In a possible implementation manner of the embodiment of the present specification, screening out a target user according to a user feature set may be specifically implemented in the following manner:

matching the user characteristic set with target user characteristic information in a preset user set;

and determining the target user corresponding to the target user characteristic information with the matching degree reaching the preset threshold value.

When the target user is screened according to the user feature set, the user feature set needs to be matched with the target user feature information in the preset user set, so that the target user corresponding to the target user feature information with the matching degree reaching the preset threshold value is determined.

The reason for matching the user feature set with the target user feature set in the preset user set is that the client usually selects a large number of clients, such as an electronic wallet client, a commonly used social software client, and the like. Based on a huge user set, the recommendation information of each data platform can be recommended to the users of the client, so that the recommendation range of each data platform is expanded, and the recommendation method is not limited to the number of the users per se.

In this embodiment, target user characteristic information is recorded in the preset user set, and the target user characteristic information includes purchasing habits, historical orders, occupation, hobbies and the like of the users in the preset user set.

After receiving the user feature set fed back by the node device, first matching the user feature set with target user feature information in a preset user set, where the user feature set is, for example: "Male users between 18-30 years of age and occupational in the IT industry like to browse digital type merchandise eight to ten hours on Saturday nights"; the target user characteristic information is as follows: "Male users between 18-40 years of age and occupational in the IT industry would like to view digital type merchandise six to nine hours on Saturday nights".

Then, respectively presetting a threshold value for the years and the time periods in the target user characteristic information, wherein the difference between the ages of the target user characteristic information and the user characteristic set is 5 for example; the time difference was 1 hour. According to the user feature set and the target user feature information, a male user who is 18-35 years old and has an IT industry as a job is determined as a target user based on preset threshold matching in the target user feature information, and then, seven to ten points of night per six weeks are browsed for digital type commodities.

Further, if the user feature set and the target user feature information are accurate enough, the recommendation information sent to the target user can be further refined, for example, it is known that a user who accesses a mobile phone end number 1234 in the user feature set purchases a digital product 1 on a data platform a based on a privacy computing technology, and it is known that the time when the user accesses each data platform is usually eight to ten times late on a weekend; based on the information, whether a user with the tail number of 1234 exists in the preset user set is searched, the user is determined as a target user, and the digital commodity 2 of the data platform B is sent to the target user at eight to ten hours in the evening on weekends.

In the above embodiment, the user feature set is matched with the target user feature information in the preset user set; and determining the target user corresponding to the target user characteristic information with the matching degree reaching the preset threshold value. By the method, each data platform can not only recommend information to the user of the data platform, but also send the recommended information to the target user of the preset user set, so that the recommendation range of each data platform is expanded, and the data platform is not limited to the number of the users of the data platform.

In a possible implementation manner of the embodiment of this specification, after recommending a target object to a target user, the method further includes:

and submitting recommendation information for recommending the target object to the target user to the node equipment in the blockchain network so that the node equipment in the blockchain network confirms that the recommendation for the target object is completed.

In this embodiment, after recommending the target object to the target user, recommendation information for recommending the target object to the target user needs to be submitted to the node device in the blockchain network, so as to ensure that the client completes recommendation for the target user.

Therefore, after recommending the target object to the target user, the recommendation information for recommending the target object to the target user needs to be signed to obtain the signed recommendation information, so as to ensure the authenticity of the information recommended to the target user.

And after signing the recommendation information to obtain the signed recommendation information, sending the signed recommendation information to the node equipment in the block chain. Each data platform can acquire the recommendation information from the node device of the block chain, and then each data platform verifies the signature of the recommendation information to ensure the authenticity of the information recommended to the target user by the client.

Specifically, after a target object is recommended to a target user, hash calculation is performed on the recommendation information to obtain a message digest of the recommendation information, and the message digest is signed after the message digest is obtained to obtain signed recommendation information.

And sending the signed recommendation information to node equipment in the block chain, decrypting the signature by each data platform to obtain the decrypted recommendation information, calculating an abstract value by using the same Hash calculation method, comparing the abstract value with the decrypted abstract value, and if the two are completely the same, indicating that the client finishes the recommendation aiming at the target user.

In the above embodiment, the recommendation information for recommending the target object to the target user is submitted to the node device in the blockchain network, so that the node device in the blockchain network confirms that the recommendation for the target object is completed, thereby protecting the benefits of each data platform.

The object recommendation method based on the block chain is applied to a client, and a recommendation request aiming at a target object is sent to node equipment in a block chain network; then receiving a user feature set fed back by the node equipment, wherein the user feature set is obtained by calling an intelligent contract to perform privacy data processing on user privacy data of each data platform in response to a recommendation request by the node equipment, and the intelligent contract is deployed on a block chain network and used for user privacy data management; and screening out the target users according to the user feature set, and recommending the target objects to the target users. According to the method, a credible information sharing environment is established between each data platform and the client through the blockchain network, the node equipment in the blockchain network responds to the recommendation request aiming at the target object sent by the client, calls the intelligent contract and carries out privacy data processing on the user privacy data submitted by each data platform, so that a more accurate user characteristic set is obtained, the client can screen out the target user according to the user characteristic set, and the accuracy of recommending the target object to the target user is improved.

The following describes an object recommendation method based on a blockchain by taking an application of the object recommendation method based on a blockchain provided in this specification to an e-commerce platform as an example with reference to fig. 3. Fig. 3 is a processing diagram illustrating an object recommendation method based on a blockchain according to an embodiment of the present disclosure.

In order to realize accurate marketing, the e-commerce platforms form a joint marketing platform alliance, and the e-wallet (namely the client) and node equipment based on a block chain network form an object recommendation system based on a block chain.

The joint marketing platform alliance (namely, the data platforms mentioned above) comprises various e-commerce platforms, specifically an e-commerce platform a, an e-commerce platform B, an e-commerce platform C and an e-commerce platform D; the node devices in the block chain correspond to a plurality of nodes, such as node 1, node 2, node 3, node 4, and node 5. Each e-commerce platform and e-wallet can decide whether to hold a node and hold several nodes according to its own needs.

After encrypting the user private data on each platform, each E-commerce platform submits the encrypted user private data to node equipment of a block chain network for storage; meanwhile, each e-commerce platform synchronizes the item information of the goods and the promotion information (i.e. the above-mentioned object information) which are mainly marketed to the e-wallet. The electronic wallet generates a recommendation request based on the commodity class information and the promotion information synchronized by each e-commerce platform, and then submits the recommendation request to the node equipment of the block chain network so as to realize the uplink and downlink interaction of the chain.

After the node equipment of the blockchain network acquires the recommendation request submitted by the electronic wallet, privacy calculation is performed on the encrypted user privacy data submitted to the node equipment of the blockchain network by each e-commerce platform by combining a privacy calculation technology, so that a privacy calculation result (namely the user feature set) is obtained.

The electronic wallet extracts and analyzes the privacy calculation result, screens target users from a user set preset by the electronic wallet, and starts marketing recommendation for the target users.

The e-wallet then feeds back information to the targeted user marketing recommendations to the federated marketing platform federation.

In a possible implementation manner of the embodiment of the present specification, the whole object recommendation method based on the blockchain is divided into an information sharing phase and a marketing recommendation phase. In the information sharing stage, the data platforms encrypt the user privacy data of the data platforms, and submit the encrypted user privacy data to the node device of the blockchain network for storage. "

Fig. 4 is a flowchart illustrating an information sharing method in a blockchain-based object recommendation method according to an embodiment of the present disclosure.

S402, each participant sends a registration request to the node equipment of the block chain network to obtain a key pair.

In this embodiment, a plurality of e-commerce platforms and e-wallets form a federation chain, and each participant may choose to hold 0, 1, or more blockchain nodes. Each party refers to each e-commerce platform as well as an e-wallet.

S404, submitting user privacy data to node equipment of the block chain network by each E-commerce platform, wherein the user privacy data comprise user identification data and user behavior data.

Specifically, in step S404, each e-commerce platform submits user identification data, which may include a mobile phone number, a place of residence, occupation, and an education level, and homomorphically encrypts the data (other encryption algorithms may be selected depending on which technical scheme is specifically used for subsequent privacy calculation), and submits the encrypted data to the chain after signing based on the private key. Each time the user identification data changes, the data needs to be updated again.

Each e-commerce platform submits user behavior data, which may include login time, login duration, types of goods accessed, page stay duration, whether an order is paid successfully or not, and the like, and homomorphically encrypts the data (other encryption algorithms may be selected depending on which technical scheme is specifically used for subsequent privacy calculation), and submits the encrypted data to a chain after signing based on a private key. Each time the user has new behavior data, the data needs to be submitted again.

Step S404 continues to be executed until all the e-commerce platforms submit the relevant data.

In this embodiment, the related data refers to user identification data and user behavior data of each e-commerce platform.

Fig. 5 is a flowchart illustrating a marketing recommendation method in a blockchain-based object recommendation method according to an embodiment of the present disclosure.

And S502, synchronizing the commodity promotion information to the electronic wallet by each E-commerce platform.

In this embodiment, the promotional information may include platform name, item name, promotional width, promotional age, and the like.

Each e-commerce platform synchronizes the goods promotion information to the e-wallet, i.e., "each data platform synchronizes the object information to the client" mentioned above.

And S504, the electronic wallet assembles a privacy calculation request according to the information of the promotion commodity.

In this embodiment, the assembly privacy calculation request may include information such as a time interval, an access time period, a stay time period, and the like.

The electronic wallet assembles a privacy calculation request according to the promotion information, namely, the client generates a recommendation request based on the object information synchronized by each data platform.

And S506, the electronic wallet signs the recommendation request and submits the recommendation request to the node equipment of the block chain network.

And S508, calling an intelligent contract by the node equipment of the block chain network, and combining the safety multi-party computing technology to combine and compute the encrypted data submitted by each E-commerce platform to obtain the user feature set based on the recommendation request.

In this embodiment, the user group representation includes the number of users, the time period for accessing the merchandise, the length of stay, whether to place an order, and the like.

S510, the node device of the block chain network informs the electronic wallet of the privacy calculation result in an asynchronous notification mode, the electronic wallet filters out user groups which accord with the query result from the user groups of the electronic wallet based on the result, specific sales promotion commodity information is pushed to the specific users at specific time based on a certain marketing strategy, and the pushed information contains the link of a target e-commerce platform, so that the recommendation and drainage purposes are achieved.

S512, the E-wallet signs the recommended information and submits the signed information to node equipment of the block chain network, and the E-commerce platform acquires the recommended information by reading the node equipment and confirms that the E-wallet really executes the recommendation.

By the method, the intelligent contract is called based on the recommendation request aiming at the target object sent by the client, and the privacy data of the user submitted by each data platform are processed, so that the security of the privacy data of the user can be ensured, and the risk of leakage of the privacy data of the user is avoided; meanwhile, a credible information sharing environment is established between each data platform and the client through the blockchain network, node equipment in the blockchain network responds to a recommendation request aiming at a target object sent by the client, calls an intelligent contract and carries out privacy data processing on user privacy data submitted by each data platform, so that a more accurate user feature set is obtained, the client can screen out the target user according to the user feature set, and the accuracy of recommending the target object to the target user is improved.

Fig. 6 is a block diagram illustrating a structure of an object recommendation apparatus based on a blockchain according to an embodiment of the present disclosure, where the apparatus is applied to a node device in a blockchain network, where the node device stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the blockchain network.

A first receiving module 602 configured to receive a recommendation request for a target object sent by a client;

the privacy processing module 604 is configured to respond to the recommendation request, invoke an intelligent contract, and perform privacy data processing on the user privacy data submitted by each data platform to obtain a user feature set;

the first sending module 606 is configured to send the user feature set to the client, so that the client screens out the target user according to the user feature set and recommends the target object to the target user.

Optionally, the first receiving module 602 is further configured to:

Optionally, the privacy processing module 604 is further configured to:

Optionally, the first receiving module 602 is further configured to:

receiving registration requests sent by each data platform;

Optionally, the user privacy data comprises user identification data and user behaviour data.

The object recommendation device based on the blockchain provided by the specification is applied to node equipment in a blockchain network, wherein the node equipment stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the blockchain network; the method comprises the steps of receiving a recommendation request aiming at a target object sent by a client, responding to the recommendation request, calling an intelligent contract, and carrying out privacy data processing on user privacy data submitted by each data platform to obtain a user feature set; and then, the user characteristic set is sent to the client side, so that the client side screens out the target user according to the user characteristic set, and recommends the target object to the target user. By the method, the intelligent contract is called based on the recommendation request aiming at the target object sent by the client, and the privacy data of the user submitted by each data platform are processed, so that the security of the privacy data of the user can be ensured, and the risk of leakage of the privacy data of the user is avoided; meanwhile, a credible information sharing environment is established between each data platform and the client through the blockchain network, node equipment in the blockchain network responds to a recommendation request aiming at a target object sent by the client, calls an intelligent contract and carries out privacy data processing on user privacy data submitted by each data platform, so that a more accurate user feature set is obtained, the client can screen out the target user according to the user feature set, and the accuracy of recommending the target object to the target user is improved.

The foregoing is a schematic solution of an object recommendation apparatus based on a blockchain, which is applied to a node device in a blockchain network according to this embodiment. It should be noted that the technical solution of the object recommendation apparatus based on a blockchain belongs to the same concept as the technical solution of the object recommendation method based on a blockchain applied to a node device in a blockchain network, and details of the technical solution of the apparatus, which are not described in detail, can be referred to the description of the technical solution of the object recommendation method based on a blockchain applied to a node device in a blockchain network.

Fig. 7 is a block diagram illustrating a structure of another object recommendation device based on a blockchain according to an embodiment of the present disclosure, which is applied to a client.

A second sending module 702 configured to send a recommendation request for a target object to a node device in the blockchain network;

a second receiving module 704, configured to receive a user feature set fed back by the node device, where the user feature set is obtained by the node device responding to the recommendation request and invoking an intelligent contract to perform privacy data processing on user privacy data of each data platform, and the intelligent contract is deployed on a block chain network and used for user privacy data management;

and the recommending module 706 is configured to screen out the target users according to the user feature set and recommend the target objects to the target users.

Optionally, the second sending module 702 is further configured to:

receiving synchronous object information of each data platform;

Optionally, the recommendation request includes a target time period and a target object identifier;

a recommendation module 706 further configured to:

Optionally, the recommending module 706 is further configured to:

The object recommendation device based on the blockchain provided by the specification is applied to a client and sends a recommendation request aiming at a target object to node equipment in a blockchain network; then receiving a user feature set fed back by the node equipment, wherein the user feature set is obtained by calling an intelligent contract to carry out privacy data processing on user privacy data of each data platform when the node equipment responds to a recommendation request, and the intelligent contract is deployed on a block chain network and used for user privacy data management; and screening out the target user according to the user characteristic set, and recommending the target object to the target user. According to the method, a credible information sharing environment is established between each data platform and the client through the blockchain network, the node equipment in the blockchain network responds to the recommendation request aiming at the target object sent by the client, calls the intelligent contract and carries out privacy data processing on the user privacy data submitted by each data platform, so that a more accurate user characteristic set is obtained, the client can screen out the target user according to the user characteristic set, and the accuracy of recommending the target object to the target user is improved.

The foregoing is a schematic solution of an object recommendation apparatus based on a blockchain applied to a client in this embodiment. It should be noted that the technical solution of the object recommendation apparatus based on a blockchain belongs to the same concept as the technical solution of the object recommendation method based on a blockchain applied to the client, and details of the technical solution of the apparatus, which are not described in detail, can be referred to the description of the technical solution of the object recommendation method based on a blockchain applied to the client.

Fig. 8 is a block diagram illustrating an architecture of a blockchain-based object recommendation system according to an embodiment of the present disclosure, the system including at least one data platform 802, a blockchain network 804 and a client 806, wherein the blockchain network 804 includes a plurality of node devices 8042, and an intelligent contract for user privacy data management is deployed on the blockchain network 804.

The data platform 802 submits the user privacy data to the node device 8042 in the blockchain network 804 for storage;

a client 806 that sends a recommendation request for a target object to a node device 8042 in the blockchain network 804;

the node device 8042, in response to the recommendation request, invokes an intelligent contract, and performs privacy data processing on the user privacy data of each data platform 802 to obtain a user feature set; sending the user feature set to the client 806;

and the client 806 screens out the target user according to the user feature set and recommends the target object to the target user.

The object recommendation system based on the blockchain comprises at least one data platform, a blockchain network and a client, wherein the blockchain network comprises a plurality of node devices, and intelligent contracts used for user privacy data management are deployed on the blockchain network. The system enables a credible information sharing environment to be established between each data platform and the client through the blockchain network, and the node equipment in the blockchain network responds to a recommendation request aiming at a target object sent by the client, calls an intelligent contract and carries out privacy data processing on user privacy data submitted by each data platform, so that a more accurate user characteristic set is obtained, the client can screen out the target user according to the user characteristic set, and the accuracy of recommending the target object to the target user is improved.

The above is an illustrative scheme of the object recommendation system based on the blockchain according to this embodiment. It should be noted that the technical solution of the object recommendation system based on the blockchain and the technical solution of the object recommendation method based on the blockchain belong to the same concept, and details of the technical solution of the system, which are not described in detail, can be referred to the description of the technical solution of the object recommendation method based on the blockchain.

FIG. 9 illustrates a block diagram of a computing device 900 provided in accordance with one embodiment of the present specification. Components of the computing device 900 include, but are not limited to, a memory 910 and a processor 920. The processor 920 is coupled to the memory 910 via a bus 930, and a database 950 is used to store data.

Computing device 900 also includes access device 940, access device 940 enabling computing device 900 to communicate via one or more networks 960. Examples of such networks include the Public Switched Telephone Network (PSTN), a Local Area Network (LAN), a Wide Area Network (WAN), a Personal Area Network (PAN), or a combination of communication networks such as the internet. Access device 940 may include one or more of any type of network interface (e.g., a Network Interface Card (NIC)) whether wired or wireless, such as an IEEE802.11 Wireless Local Area Network (WLAN) wireless interface, a worldwide interoperability for microwave access (Wi-MAX) interface, an ethernet interface, a Universal Serial Bus (USB) interface, a cellular network interface, a bluetooth interface, a Near Field Communication (NFC) interface, and so forth.

In one embodiment of the present description, the above-described components of computing device 900, as well as other components not shown in FIG. 9, may also be connected to each other, such as by a bus. It should be understood that the block diagram of the computing device architecture shown in FIG. 9 is for purposes of example only and is not limiting as to the scope of the description. Those skilled in the art may add or replace other components as desired.

Computing device 900 may be any type of stationary or mobile computing device, including a mobile computer or mobile computing device (e.g., tablet, personal digital assistant, laptop, notebook, netbook, etc.), a mobile phone (e.g., smartphone), a wearable computing device (e.g., smartwatch, smartglasses, etc.), or other type of mobile device, or a stationary computing device such as a desktop computer or PC. Computing device 900 may also be a mobile or stationary server.

The processor 920 is configured to execute computer-executable instructions, and the computer-executable instructions, when executed by the processor, implement the steps of the object recommendation method based on the blockchain.

The above is an illustrative scheme of a computing device of the present embodiment. It should be noted that the technical solution of the computing device and the technical solution of the object recommendation method based on the blockchain belong to the same concept, and details that are not described in detail in the technical solution of the computing device can be referred to the description of the technical solution of the object recommendation method based on the blockchain.

An embodiment of the present specification further provides a computer-readable storage medium, which stores computer-executable instructions, and when the computer-executable instructions are executed by a processor, the steps of the object recommendation method based on the block chain are implemented.

The above is an illustrative scheme of a computer-readable storage medium of the present embodiment. It should be noted that the technical solution of the storage medium and the technical solution of the object recommendation method based on the blockchain belong to the same concept, and details that are not described in detail in the technical solution of the storage medium can be referred to the description of the technical solution of the object recommendation method based on the blockchain.

An embodiment of the present specification further provides a computer program, wherein when the computer program is executed in a computer, the computer program causes the computer to perform the steps of the above object recommendation method based on a blockchain.

The above is an illustrative scheme of a computer program of the present embodiment. It should be noted that the technical solution of the computer program and the technical solution of the object recommendation method based on the blockchain belong to the same concept, and details that are not described in detail in the technical solution of the computer program can be referred to the description of the technical solution of the object recommendation method based on the blockchain.

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 computer instructions comprise computer program code which may be in source code form, object code form, an executable file or some intermediate form, or the like. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, etc.

It should be noted that, for the sake of simplicity, the foregoing method embodiments are described as a series of acts, but those skilled in the art should understand that the present embodiment is not limited by the described acts, because some steps may be performed in other sequences or simultaneously according to the present embodiment. Further, those skilled in the art should also appreciate that the embodiments described in this specification are preferred embodiments and that acts and modules referred to are not necessarily required for an embodiment of the specification.

In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.

The preferred embodiments of the present specification disclosed above are intended only to aid in the description of the specification. Alternative embodiments are not exhaustive and do not limit the invention to the precise embodiments described. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the embodiments and the practical application, and to thereby enable others skilled in the art to best understand the specification and utilize the specification. The specification is limited only by the claims and their full scope and equivalents.

Claims

1. An object recommendation method based on a block chain is applied to node equipment in a block chain network, wherein the node equipment stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the block chain network; the method comprises the following steps:

receiving a recommendation request aiming at a target object sent by a client;

2. The method of claim 1, prior to receiving a recommendation request sent by a client for a target object, the method further comprising:

and receiving and storing the user privacy data submitted by each data platform, wherein the user privacy data are submitted by each data platform after being encrypted based on a preset format.

3. The method according to claim 2, wherein the invoking of the intelligent contract in response to the recommendation request performs privacy data processing on the user privacy data submitted by the data platforms to obtain a user feature set, and comprises:

and responding to the recommendation request, calling the intelligent contract, and performing privacy data processing on the user privacy data submitted by each data platform by using a privacy data processing mode corresponding to the preset format to obtain a user feature set.

4. The method of claim 2, prior to said receiving and storing user privacy data submitted by said data platforms, further comprising:

receiving registration requests sent by the data platforms;

5. The method of any of claims 1-4, the user privacy data comprising user identification data and user behavior data.

6. An object recommendation method based on a blockchain is applied to a client, and the method comprises the following steps:

receiving a user feature set fed back by the node equipment, wherein the user feature set is obtained by calling an intelligent contract to perform privacy data processing on user privacy data of each data platform in response to the recommendation request by the node equipment, and the intelligent contract is deployed on the block chain network and used for user privacy data management;

7. The method of claim 6, prior to said sending a recommendation request for a target object to a node device in a blockchain network, comprising:

receiving the synchronous object information of each data platform;

8. The method of claim 6 or 7, the recommendation request comprising a target time period and a target object identification; the recommending the target object to the target user comprises:

9. The method of claim 6, the screening out target users according to the user feature set, comprising:

10. The method of claim 6, further comprising, after said recommending the target object to the target user:

and submitting recommendation information for recommending the target object to the target user to node equipment in the blockchain network so as to ensure that the node equipment in the blockchain network confirms that the recommendation for the target object is completed.

11. An object recommendation device based on a block chain is applied to node equipment in a block chain network, wherein the node equipment stores user privacy data submitted by each data platform, and an intelligent contract for managing the user privacy data is deployed on the block chain network; the device comprises:

the privacy processing module is configured to respond to the recommendation request, call the intelligent contract and perform privacy data processing on the user privacy data submitted by each data platform to obtain a user feature set;

12. An object recommendation device based on a blockchain, which is applied to a client, the device comprising:

13. An object recommendation system based on a blockchain comprises at least one data platform, a blockchain network and a client, wherein the blockchain network comprises a plurality of node devices, and intelligent contracts used for user privacy data management are deployed on the blockchain network;

and the client screens out a target user according to the user characteristic set and recommends the target object to the target user.

14. A computing device, comprising:

a memory and a processor;

the memory is configured to store computer-executable instructions, and the processor is configured to execute the computer-executable instructions, which when executed by the processor implement the steps of the blockchain based object recommendation method of any one of claims 1 to 5 or the steps of the blockchain based object recommendation method of any one of claims 6 to 10.

15. A computer readable storage medium storing computer executable instructions which, when executed by a processor, implement the steps of the blockchain based object recommendation method of any one of claims 1 to 5 or the steps of the blockchain based object recommendation method of any one of claims 6 to 10.