Abstract: Implementations of this specification provide a method and an apparatus for transaction processing in a service blockchain.

Abstract: Methods and apparatuses for retrieving blockchain data are disclosed. One method comprises: receiving a data retrieving request that comprises a target transaction identifier; identifying a transaction storage location that corresponds to the target transaction identifier as a target transaction storage location based on a pre-stored correspondence between transaction identifiers of transactions recorded on a blockchain associated with the blockchain network and transaction storage locations of the transactions; and retrieving data from the target transaction storage location in the blockchain.

Abstract: This disclosure relates to determining model parameters using secret sharing. In some aspects, a first data party device obtains a first share of a Hessian matrix for a data processing model. The first data party device obtains, using secret sharing with the second data party device, a first share of a product of a random number matrix and the Hessian matrix. The first data party device, determines a first share of a first inverse matrix based on a second inverse matrix and the first share of the random number matrix. The first data party device determines the first inverse matrix, a first share of a product of the first inverse matrix and a gradient of a loss function of the data processing model, and a first share of a new model parameter for the data processing model.

Abstract: A computer-implemented method for detecting fraudulent behavior in a facial recognition process includes: receiving, by a computing device, a facial recognition request from a user; collecting bypass information of the user, in which the bypass information includes user device information and user behavior information; inputting the bypass information into at least one decision model to obtain a bypass decision result; and determining, based on the bypass decision result, whether fraudulent behavior is present in the facial recognition process.

Abstract: Disclosed herein are methods, systems, and apparatus, including computer programs encoded on computer storage media, for providing blockchain-based data authorization. One of the methods includes receiving, by a blockchain node, a data acquisition transaction submitted by a data user for obtaining target data possessed by a data owner, determining, by the blockchain node, that the data user has obtained authorization of the target data, and executing, by the blockchain node, a smart contract invoked by the data acquisition transaction to provide one or more of the target data and a computational result of one or more predetermined computational operations performed based on the target data to the data user.

Abstract: Implementations of this specification provide methods and apparatuses for oblivious data transfer between computing devices. An example method includes receiving, by a second computing device, an oblivious transfer from a first computing device. The first computing device splits feature data in a feature dataset into a plurality of sub-data and uses the plurality of sub-data as input, and the second computing device uses label data in a label dataset as input. The second computing device selects target sub-data from the plurality of sub-data input by the first computing device, and determines a first summation result of the selected target sub-data. The second computing device receives from the first computing device a second summation result of the one or more splitting parameters in the splitting parameter set, and calculates a statistical indicator based on the first summation result and the second summation result.

Abstract: This disclosure relates to processing sequential interaction data through machine learning. In one aspect, a method includes obtaining a dynamic interaction graph constructed based on a dynamic interaction sequence. The dynamic interaction sequence includes interaction feature groups corresponding to interaction events. Each interaction feature group includes a first object, a second object, and an interaction time of an interaction event that involved the first object and the second object. The dynamic interaction graph includes multiple nodes including, for each interaction feature group, a first node that represents the first object of the interaction feature group and a second node that represents the second object of the interaction feature group. A current sequence corresponding to a current node to be analyzed is determined. The current sequence is input into a Transformer-based neural network model. The neural network model determines a feature vector corresponding to the current node.

Abstract: An affair processing request is received from a first network node. First affair information determined by the first network node is received. A type of to-be-acquired second affair information excluded from the received first affair information is determined. First information comprising the type of the to-be-acquired second affair information is transmitted to a second network node. Second information is received, the second information including content of the second affair information fed back from the second network node. An affair of the affair processing request is processed on the basis of the received first affair information and the received content of the second affair information.

Abstract: Content of a video is parsed to identify one or more topics of the content. The video is divided into one or more video clips corresponding to a video playback of one or more topics. One or more titles corresponding to, and descriptive of, the one or more video clips are displayed. One or more visual effects corresponding to the one or more titles and indicative of corresponding playback statuses of the one or more video clip are displayed. A video clip is played, where the video clip is based on a particular title of the one or more titles selected from a time point determined based on a corresponding playback status of the video clip.

Abstract: A computer-implemented method includes: determining assets held by a remitter, the assets to be spent in a remittance transaction between the remitter and one or more payees, in which each asset corresponds to a respective asset identifier, a respective asset amount, and a respective asset commitment value; determining a remitter pseudo public key and a remitter pseudo private key; determining a cover party pseudo public key, in which the cover party pseudo public key is obtained based on asset commitment values of assets held by the cover party; and generating a linkable ring signature for the remittance transaction.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for transaction processing are provided. One of the methods includes: receiving a transaction request for a target transaction; loading a transaction template matching a transaction type of the target transaction; processing the target transaction according to the transaction template to obtain transaction information; and writing the transaction information into a blockchain.