Abstract: One or more embodiments of the present specification relate to a data processing method for binding server accounts. An example method includes, in response to obtaining a binding request, determining a first account, and sending binding request feedback data to a terminal device. In response to obtaining binding object selection data that indicates a selection of candidate binding objects presented by the terminal device, a respective target binding object is determined for each selected candidate binding object, and a respective target server is determined for each target binding object. For each target server, the first account is bound to a second account of the target server.

Abstract: An event processing request including an event processing parameter is received from an event initiator. When verification performed on the event processing parameter based on a first smart contract is passed, parsing the event processing parameter based on the first smart contract, determining an event participant, invoking a second smart contract, and determining a current remaining resource of the event participant. When the current remaining resource of the event participant satisfies an event processing condition, invoking the second smart contract based on the first smart contract, and freezing an event resource needed for processing the event processing request in the current remaining resource of the event participant. When a confirmation instruction of the event participant for the event processing parameter of the event processing request is received, invoking the second smart contract based on the first smart contract, deducting the event resource, and completing the event processing request.

Abstract: Implementations of the present specification provide techniques for transacting a stored value card for payment in a separate transaction between a user and a merchant. A stored value card of a card issuer applicable to the transaction between a user and a merchant is determined. An SVC graphics interface for transacting the stored value card is presented to the user, which corresponds to a merchant graphics interface for the transaction between the user and the merchant. The SVC graphics interface enables a transaction on the stored value card using an account of the user with a payment system. An identification information of the stored value card transacted through the SVC graphics interface is inserted onto the merchant graphics interface so that the SVC card is used in the payment for the transaction between the user and the merchant.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for document registration. One of the methods includes: at a service platform, receiving first information related to an order, wherein the first information is provided, or to be provided, to a service authority for clearance of the order; at the service platform, encrypting at least a portion of the first information to generate encrypted first data; and sending the encrypted first data to a blockchain network to store the encrypted first data on a blockchain managed by the blockchain network, wherein the encrypted first data are stored on the blockchain through consensus of blockchain nodes of the blockchain network.

Abstract: Methods, systems, and apparatuses, including computer programs encoded on computer storage media, for federal learning are disclosed. One exemplary method may include receiving, by a client device from a server device, model parameters of a global machine learning model being collaboratively trained by the client device and the server device; constructing, by the client device, a local machine learning model based on the model parameters of the global machine learning model, wherein the local machine learning model comprises two branches corresponding to two loss functions; training, by the client device, the local machine learning model based on local training data, wherein the training comprises updating the model parameters to minimize a first loss function of the two loss functions and maximize a second loss function of the two loss functions; and sending, by the client device, the updated model parameters back to the server device.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for managing user authorizations for blockchain-based services. One of the methods includes: at a service platform, receiving, from a computing device associated with a user, an encryption key and data for storage on a blockchain, wherein the data includes public data and private data, and the encryption key encrypts the private data; storing the encryption key and an identifier (ID) of the data in a cache storage dedicated to storing smart contract data for executing a smart contract; and invoking an application programming interface (API) to enable a blockchain node to initiate a consensus algorithm to record the data and the ID of the data on a blockchain.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing user management associated with blockchain-based services. One of the methods includes receiving: at a service platform, receiving a first request to authorize a first member to access information related to a first order; invoking a smart contract executing on a blockchain to request that the first member be added to a list of authorized members who are authorized to access the information related to the first order, in which the smart contract is configured to maintain a data structure that stores information about the authorized members; receiving a confirmation from the smart contract that the first member has been added to the list of authorized members; and sending a confirmation to the administrator that the first member has been added to the list of authorized members.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for managing transactions in blockchain networks.

Abstract: Implementations of the present specification provide a method and an apparatus for transferring a resource in batches, applied to the following scenario: a resource transferor holds a first resource, a receiving target of a resource transferee is a second resource, and the first resource of the resource transferor cannot be transferred once in a resource transfer process. In the resource transfer process, a client corresponding to the resource transferor sends a resource transfer request to a conversion serving end. The conversion serving end feeds back a to-be-transferred share and a service identifier to the client. The client transfers a first share of the first resource by using an associated transfer platform based on the to-be-transferred share and the service identifier that are fed back. The associated transfer platform can send a transfer record of the first resource to the conversion serving end based on the service identifier.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for identity document face image quality recognition. One computer-implemented method includes pairing, for each user of a plurality of users and to form a pair of face images, an identity document (ID) face image and a live face image. For each pair of face images and based on a face similarity between the ID face image and the live face image, a similarity score for the ID face image is generated. Based on ID face images and similarity scores corresponding to the ID face images, a model for ID face image quality recognition is trained.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for performing user management associated with blockchain-based services. One of the methods includes receiving: at a service platform, receiving a first request to authorize a first member to access information related to a first order; invoking a smart contract executing on a blockchain to request that the first member be added to a list of authorized members who are authorized to access the information related to the first order, in which the smart contract is configured to maintain a data structure that stores information about the authorized members; receiving a confirmation from the smart contract that the first member has been added to the list of authorized members; and sending a confirmation to the administrator that the first member has been added to the list of authorized members.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for processing data. One of the systems include: a service platform comprising a plurality of service modules and an application programming interface layer comprising a plurality of application programming interfaces (APIs) to enable users to invoke the service modules to process information related to an order associated with importation of a merchandise, wherein the information is provided, or to be provided, to a service authority for requesting clearance for the order, wherein a first application programming interface of the plurality of application programming interfaces enables a user of the service platform to invoke a smart contract on a blockchain managed by a blockchain network, in which the smart contract performs at least one of processing of the information or processing of information related to another user of the service platform.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for managing transactions in multiple blockchain networks.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for face anti-spoofing. One computer-implemented method includes receiving, by a server and from a user device, a plurality of images of a user face, each of the plurality of images corresponding to a facial expression performed by a user in response to each interaction challenge of a plurality of interaction challenges. The plurality of images are concatenated into a concatenated image. A convolutional neural network (CNN) classifier is used to obtain a confidence score for the concatenated image. A liveness of the user face is determined based on a comparison of the confidence score and a threshold value.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for managing transactions in multiple blockchain networks. One computer-implemented method includes identifying a first transaction in a first blockchain network that is a first Hash Time Locked Contract (HTLC) transaction in the first blockchain network, identifying a second transaction in a second blockchain network that is a second HTLC transaction in the second blockchain network different from the first blockchain network, determining that a first transaction commit time of the first HTLC transaction is earlier than a second transaction commit time of the second HTLC transaction and a first secret hash of the first HTLC transaction has a same value as a second secret hash of the second HTLC transaction, and in response, determining that the first HTLC transaction and the second HTLC transaction are associated with each other and related to a cross-chain transaction.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for smart contract and blockchain data storage. One of the methods includes determining that data stored in a cache storage satisfies a predetermined condition; adding a blockchain address of a second smart contract to a configuration file, wherein the configuration file includes a plurality of addresses corresponding to a plurality of smart contracts stored on a blockchain; and invoking a virtual machine to execute the configuration file, wherein execution of the configuration file initiates a consensus algorithm to generate the second smart contract at the blockchain address and a corresponding smart contract pool for storing at least a portion of the data on the blockchain, and wherein the smart contract pool is a data structure to be stored on the blockchain.

Abstract: Implementations of the present specification provide a service processing method. The method is performed by a service platform, the service platform including multiple area sites corresponding to multiple service areas, and each area site including a corresponding buyer service site and seller service site.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for data storage. One of the methods includes: receiving data for storage from a service platform, wherein the data includes mutable data, immutable data, and index data identified by the service platform; storing the mutable data in a cache storage, wherein the mutable data is to be executed by a smart contract; initiating, a consensus algorithm to record the immutable data on a blockchain; in response to successfully performing the consensus algorithm, recording, based on invoking the smart contract, the immutable data on the blockchain, wherein the blockchain is stored in a database that has lower storage cost than the cache storage; and linking, based on invoking the smart contract, the mutable data and the immutable data based on the index data.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for document identification. One computer-implemented method includes extracting a sequence of image frames from a video clip capturing an impact of an object against a surface. A stream of audio signals is extracted from the video clip. Using a trained document identification model, a first score and a second score is generated based on the sequence of image frames and the stream of audio signals, respectively. The trained document identification model is trained with a plurality of historical video clips, where each video clip captures an impact of a document against a surface. An identification score is generated based on the first score and the second score. Whether the object in the video clip is a document is determined based on a comparison between the identification score and an identification threshold.

Abstract: Disclosed are computer-implemented methods, non-transitory computer-readable media, and systems for authentication. One computer-implemented method includes obtaining a first image, where the first image is an image of an identification (ID) document captured when the ID document is tilted at a first angle relative to a projected light source. A second image is obtained, where the second image is an image of the ID document captured when the ID document is tilted at a second angle relative to the projected light source. The ID document is authenticated based on identification of a first illuminated region and a second illuminated region, where the first illuminated region is associated with the first image and the second illuminated region is associated with the second image, and a comparison between a first position of the first illuminated region and a second position of the second illuminated region.