Baidu Online Network Technology (Beijing) Co., Ltd.

Beijing Baidu Netcom Science and Technology Co., Ltd.

Beijing Baidu Netcom Science Technology Co., Ltd

Zhi Feng

Yu Zhang

Chuanyuan Song

Shun Zhang

Wei Liu

Ran Duan

Jizhou Huang

Zhiqiang Zhang

Dejing Dou

Yulin Wang

Sen Zhang

Ji Liu

Haoyi Xiong

Siyu Huang

Jing Qu

Xiaoning Yu

Haosu Guo

Haizhu Li

Mengbo Liu

Haozhe An

Yunzhu Wang

Liangliang Lyu

Liangliang Lv

Chengshuo Zhang

Embodiments of the present disclosure provide a data mining system, a data mining method, and a storage medium. The data mining system includes a transfer device, a first trusted execution space and a second trusted execution space. The transfer device is configured to receive a data calling request of the second trusted execution space, obtain data to be called from the first trusted execution space according to the data calling request, and provide the data to be called to the second trusted execution space, so as to perform data mining based on the data to be called and the mining-related data to obtain a data mining result and to provide the data mining result to a device of the data user.

System and method for mining data and storage medium

The present disclosure provides a joint training method and apparatus for models, a device and a storage medium. The method may include: training a first-party model to be trained using a first sample quantity of first-party training samples to obtain first-party feature gradient information; acquiring second-party feature gradient information and second sample quantity information from a second party, where the second-party feature gradient information is obtained by training, by the second party, a second-party model to be trained using a second sample quantity of second-party training samples; and determining model joint gradient information according to the first-party feature gradient information, the second-party feature gradient information, first sample quantity information and the second sample quantity information, and updating the first-party model and the second-party model according to the model joint gradient information.

Joint training method and apparatus for models, device and storage medium

A method for processing commodity information includes: obtaining commodity information of a commodity, in which the commodity information includes a target commodity configuration and a configuration value; obtaining a composite structure of matching conditions associated with the commodity, in which the composite structure is a tree structure of matching conditions with respect to commodity configurations, non-leaf nodes of the tree structure are in an AND-OR relationship, leaf nodes of the tree structure store Boolean expressions, each Boolean expression includes a commodity configuration, a matching value and a matching operator; obtaining a target expression having an AND-OR relationship by traversing the matching conditions in the composite structure; and obtaining a matching result by performing a matching process based on the target expression, the target commodity configuration and the configuration value of the commodity.

Method and apparatus for processing commodity information, device and storage medium

A method and apparatus for processing network usage of a cloud product, a device, a storage medium and a product, and relates to cloud computing and big data in data processing. The specific implementation is: acquiring traffic usage data of a target cloud product within a preset time interval; determining an algorithm list corresponding to the target cloud product; and invoking all pre-configured algorithms corresponding to identifiers of all the algorithms according to the algorithm list to perform corresponding data processing operations on the traffic usage data to obtain a target network usage corresponding to the target cloud product.

Method and apparatus for processing network usage of a cloud product, device, storage medium and product

A method and apparatus for obtaining a privacy set intersection are provided. The method may include: encrypting a privacy set of an intersection initiator by using a homomorphic encryption algorithm to generate a cipher text, a cipher text function, a public key, and a private key of the intersection initiator; delivering the cipher text, the cipher text function, and the public key of the intersection initiator to an intersection server; receiving a to-be-decrypted function value of a privacy set of the intersection server from the intersection server; and decrypting the to-be-decrypted function value of the privacy set of the intersection initiator by using the private key, to obtain an intersection element of the privacy set of the intersection initiator and the privacy set of the intersection server.

Method and apparatus for obtaining privacy set intersection, device and storage medium

The present disclosure provides a multi-party data joint query method, a device, a server and a storage medium. The multi-party data joint query method executed by a manager includes: analyzing a multi-party joint query sentence to obtain a logical execution plan; processing the logical execution plan according to providers of respective nodes in the logical execution plan to obtain a physical execution plan of each provider; and generating a query instruction of each provider according to the physical execution plan of each provider, and sending the query instruction to respective provider. The query instruction is configured to instruct the providers to perform a query cooperatively.

Multi-party data joint query method, device, server and storage medium

Embodiments of the present disclosure disclose a machine learning training method and a server. The method includes: acquiring training data uploaded by the terminal; creating a trusted execution environment in response to a machine learning training request from the terminal; and performing machine learning training based on the trusted execution environment and the training data.

Machine learning training method, controller, device, server, terminal and medium

Embodiments of a secure multi-party computation method are provided. The method can include: dynamically converting a multi-party computation program segment into a first garbled circuit by using a multi-party computation operator of a first main body, and executing garbled gates of the first garbled circuit in sequence through an execution engine of the first main body, to encrypt data of the first main body; transmitting to a second main body the encrypted data of the first main body and identifiers for garbled gates of the first garbled circuit; performing a second encryption on the encrypted data of the first main body by the second main body in sequence according to the received identifiers for the garbled gates of the first garbled circuit, and returning to the first main body a result of the second encryption on the encrypted data of the first main body.

Secure multi-party computation method, device, apparatus and computer-readable storage medium

A data visual analysis method, system and terminal, and a computer readable storage medium are provided. The method includes: obtaining to-be-analyzed parameters and generating a data analysis model, the data analysis model including a plurality of execution units; the data sources collecting data information related to the to-be-analyzed parameters; the execution units performing analysis on the data information collected by the data sources, to obtain execution results of the execution units; and visually outputting the execution results of the execution units.

Data visual analysis method, system and terminal and computer readable storage medium

The present disclosure provides a spark query method and system supporting trusted computing. The method comprises receiving a SQL query statement input by a user; performing parsing, logical plan analysis, logical plan optimization and physical plan generation for the SQL query statement; re-implementing an operator in the physical plan by using SGX API, and generating an execution code; invoking an enclave trusted environment to implement trusted computing for the operator, and executing the execution code. Through the present disclosure, safety of data during the calculation is ensured while the query request is processed in parallel through the spark architecture. Moreover, the spark interface provides the user with more available service and is user-friendly.

Growing community of inventors

Beijing, China

Zhi Feng