Patents by Inventor Wenbiao Zhao
Wenbiao Zhao has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Publication number: 20240153500Abstract: Implementations of the present specification provide a data processing method, apparatus, and device. The method includes: obtaining to-be-detected target data, and obtaining a target probability that the target data corresponds to each candidate user intention, where the target data includes input data of a user in a human-computer interaction process; dividing the target data to obtain a plurality of pieces of subdata, and obtaining, based on a predetermined gradient integration algorithm, a contribution of each piece of subdata to a correspondence between the target data and each candidate user intention; and determining a target user intention corresponding to the target data based on the target probability that the target data corresponds to each candidate user intention and the contribution of each piece of subdata to the correspondence between the target data and each candidate user intention.Type: ApplicationFiled: November 2, 2023Publication date: May 9, 2024Inventors: Wenbiao ZHAO, Jinzhen LIN, Zhenzhe YING, Lanqing XUE, Weiqiang WANG, Ke XU, Qi LI
-
Patent number: 11978000Abstract: One embodiment of the present disclosure provides a system and method for determining a decision-making strategy. During operation, the system can obtain sample data corresponding to a service. The system can pre-determine, based on the sample data and the service, a basic parametric shape model and can generate a plurality of shape parameters for the basic parametric shape mode. The system can then generate one or more parametric shape models with different shapes based on the plurality of shape parameters. The system can determine goodness-of-fit of the one or more parametric shape models with respect to a pre-defined decision-making strategy. Next, the system can in response to determining that the goodness-of-fit of at least one parametric shape model satisfies a set of objectives, outputting the at least one parametric shape model as an optimum decision-making strategy for the service.Type: GrantFiled: July 31, 2020Date of Patent: May 7, 2024Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.Inventors: Dapeng Fu, Wenbiao Zhao, Hong Jin
-
Publication number: 20240070182Abstract: Implementations of the present specification disclose an event risk detection method, apparatus, and device.Type: ApplicationFiled: August 28, 2023Publication date: February 29, 2024Inventors: Wenbiao ZHAO, Haotian WANG, Xiaofeng WU, Weiqiang WANG
-
Patent number: 11538039Abstract: One embodiment provides a method and system for managing risk-control commands. During operation, the system can obtain statistics associated with a plurality of risk-control commands issued by a risk-control system corresponding to a plurality of transactions on an online financial platform, and determine, based on the monitored plurality of risk-control commands, whether a subset of risk-control commands meets an anomaly condition. In response to determining that the subset of risk-control commands does not meet the anomaly condition, the system can forward the subset of risk-control commands to the online financial platform to facilitate the online financial platform in performing corresponding transactions according to the subset of risk-control command. In response to determining that the subset of risk-control commands meets the anomaly condition, the system can prevent the subset of risk-control commands from being forwarded to the online financial platform.Type: GrantFiled: July 24, 2020Date of Patent: December 27, 2022Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.Inventors: Lijie Zhang, Wenbiao Zhao, Yunfeng Peng
-
Patent number: 11494774Abstract: A method for identifying a risk pertaining to a transaction to be processed, includes: identifying a risk pertaining to a transaction to be processed via a fast identification layer in a risk control system, thereby obtaining a first identification result; identifying a risk of interference pertaining to the transaction to be processed via a model for identifying transactions susceptible to interference, thereby obtaining a second identification result; and determining a processing manner for the transaction to be processed based on the first identification result and the second identification result, the processing manner including releasing the transaction to be processed, or further identifying the risk pertaining to the transaction to be processed via the in-depth identification layer in the risk control system.Type: GrantFiled: June 13, 2019Date of Patent: November 8, 2022Assignee: Advanced New Technologies Co., Ltd.Inventors: Yicheng Lu, Tao Chen, Wenbiao Zhao
-
Patent number: 11367075Abstract: A method for identifying a risk pertaining to a transaction to be processed, includes: identifying a risk pertaining to a transaction to be processed via a fast identification layer in a risk control system, thereby obtaining a first identification result; identifying a risk of interference pertaining to the transaction to be processed via a model for identifying transactions susceptible to interference, thereby obtaining a second identification result; and determining a processing manner for the transaction to be processed based on the first identification result and the second identification result, the processing manner including releasing the transaction to be processed, or further identifying the risk pertaining to the transaction to be processed via the in-depth identification layer in the risk control system.Type: GrantFiled: January 28, 2020Date of Patent: June 21, 2022Assignee: Advanced New Technologies Co., Ltd.Inventors: Yicheng Lu, Tao Chen, Wenbiao Zhao
-
Patent number: 11222285Abstract: A feature-selection system obtains a training data set and associated features; divides the training data set into a first number of training data subsets; and forms a plurality of feature-selecting data sets. A feature-selecting data set comprises a second number of training data subsets. The system processes, in parallel, each feature-selecting data set, which comprises: computing a first evaluation index for the features based on the feature-selecting data set; obtaining a group of index ranks corresponding to the features based on the first evaluation index; and obtaining a group of importance ranks corresponding to the features based on the feature-selecting data set and a machine-learning model. The system further obtains a group of total ranks by fusing groups of index ranks and groups importance ranks obtained from processing the plurality of feature-selecting data sets; and selecting target features from the features based on the group of total ranks.Type: GrantFiled: January 29, 2021Date of Patent: January 11, 2022Assignee: Advanced New Technologies Co., Ltd.Inventors: Yuzhou Tang, Hong Jin, Weiqiang Wang, Wenbiao Zhao
-
Patent number: 11132624Abstract: A model integration method and device are provided. The method includes: obtaining an integrated model, the integrated model having one integrated output value and a plurality of input values, the plurality of input values corresponding to a plurality of output values of a plurality of independent models; performing one or more iterations of optimizing process until a preset iteration stop condition is satisfied: acquiring a prediction output by the integrated model based on a preset test event set; determining an index value of the integrated model based on the prediction output, the index value indicates a performance evaluation of the integrated model; if the index value fails to meet a preset performance requirement; after the preset iteration stop condition is satisfied, determining the integrated model as acceptable.Type: GrantFiled: March 2, 2020Date of Patent: September 28, 2021Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.Inventors: Lujia Chen, Licui Gao, Wenbiao Zhao
-
Patent number: 11120115Abstract: One embodiment provides an identification method and system. The system obtains attribute features of a user, determines a first set of identification products and identification success rates thereof based on the attribute features of the user and a first machine-learning model for determining identification security, and generates a first set of identification product combinations, a respective identification product combination comprising two different identification products.Type: GrantFiled: January 29, 2021Date of Patent: September 14, 2021Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.Inventors: Dapeng Fu, Wenbiao Zhao, Hong Jin
-
Publication number: 20210150012Abstract: One embodiment provides an identification method and system. The system obtains attribute features of a user, determines a first set of identification products and identification success rates thereof based on the attribute features of the user and a first machine-learning model for determining identification security, and generates a first set of identification product combinations, a respective identification product combination comprising two different identification products.Type: ApplicationFiled: January 29, 2021Publication date: May 20, 2021Applicant: Advanced New Technologies Co., Ltd.Inventors: Dapeng Fu, Wenbiao Zhao, Hong Jin
-
Publication number: 20210150415Abstract: A feature-selection system obtains a training data set and associated features; divides the training data set into a first number of training data subsets; and forms a plurality of feature-selecting data sets. A feature-selecting data set comprises a second number of training data subsets. The system processes, in parallel, each feature-selecting data set, which comprises: computing a first evaluation index for the features based on the feature-selecting data set; obtaining a group of index ranks corresponding to the features based on the first evaluation index; and obtaining a group of importance ranks corresponding to the features based on the feature-selecting data set and a machine-learning model. The system further obtains a group of total ranks by fusing groups of index ranks and groups importance ranks obtained from processing the plurality of feature-selecting data sets; and selecting target features from the features based on the group of total ranks.Type: ApplicationFiled: January 29, 2021Publication date: May 20, 2021Applicant: Advanced New Technologies Co., Ltd.Inventors: Yuzhou Tang, Hong Jin, Weiqiang Wang, Wenbiao Zhao
-
Patent number: 11004026Abstract: A method for determining critical values includes obtaining N relation functions between M features and N index values, the N relation functions taking the M features as inputs and the N index values as outputs; generating K combinations, each comprising M critical values of the M features; repeating following steps until a preset stop condition is satisfied: determining a score for each of the K combinations based on the N relation functions to represent an overall quality of the N index values; repeatedly selecting two combinations and exchanging critical values between the two combinations to generate two new combinations until a quantity of the new combinations reaches a preset number; and selecting K combinations from the new combinations; and after the preset stop condition is satisfied, associating the M features with the M critical values in a combination with a highest score.Type: GrantFiled: February 19, 2020Date of Patent: May 11, 2021Assignee: ADVANCED NEW TECHNOLOGIES CO., LTD.Inventors: Kai Xiao, Wenbiao Zhao
-
Publication number: 20200364719Abstract: One embodiment of the present disclosure provides a system and method for determining a decision-making strategy. During operation, the system can obtain sample data corresponding to a service. The system can pre-determine, based on the sample data and the service, a basic parametric shape model and can generate a plurality of shape parameters for the basic parametric shape mode. The system can then generate one or more parametric shape models with different shapes based on the plurality of shape parameters. The system can determine goodness-of-fit of the one or more parametric shape models with respect to a pre-defined decision-making strategy. Next, the system can in response to determining that the goodness-of-fit of at least one parametric shape model satisfies a set of objectives, outputting the at least one parametric shape model as an optimum decision-making strategy for the service.Type: ApplicationFiled: July 31, 2020Publication date: November 19, 2020Applicant: Alibaba Group Holding LimitedInventors: Dapeng Fu, Wenbiao Zhao, Hong Jin
-
Publication number: 20200356996Abstract: One embodiment provides a method and system for managing risk-control commands. During operation, the system can obtain statistics associated with a plurality of risk-control commands issued by a risk-control system corresponding to a plurality of transactions on an online financial platform, and determine, based on the monitored plurality of risk-control commands, whether a subset of risk-control commands meets an anomaly condition. In response to determining that the subset of risk-control commands does not meet the anomaly condition, the system can forward the subset of risk-control commands to the online financial platform to facilitate the online financial platform in performing corresponding transactions according to the subset of risk-control command. In response to determining that the subset of risk-control commands meets the anomaly condition, the system can prevent the subset of risk-control commands from being forwarded to the online financial platform.Type: ApplicationFiled: July 24, 2020Publication date: November 12, 2020Applicant: Allbaba Group Holding LimitedInventors: Lijie Zhang, Wenbiao Zhao, Yunfeng Peng
-
Publication number: 20200202255Abstract: A model integration method and device are provided. The method includes: obtaining an integrated model, the integrated model having one integrated output value and a plurality of input values, the plurality of input values corresponding to a plurality of output values of a plurality of independent models; performing one or more iterations of optimizing process until a preset iteration stop condition is satisfied: acquiring a prediction output by the integrated model based on a preset test event set; determining an index value of the integrated model based on the prediction output, the index value indicates a performance evaluation of the integrated model; if the index value fails to meet a preset performance requirement; after the preset iteration stop condition is satisfied, determining the integrated model as acceptable.Type: ApplicationFiled: March 2, 2020Publication date: June 25, 2020Inventors: Lujia CHEN, Licui GAO, Wenbiao ZHAO
-
Publication number: 20200184393Abstract: A method for determining critical values includes obtaining N relation functions between M features and N index values, the N relation functions taking the M features as inputs and the N index values as outputs; generating K combinations, each comprising M critical values of the M features; repeating following steps until a preset stop condition is satisfied: determining a score for each of the K combinations based on the N relation functions to represent an overall quality of the N index values; repeatedly selecting two combinations and exchanging critical values between the two combinations to generate two new combinations until a quantity of the new combinations reaches a preset number; and selecting K combinations from the new combinations; and after the preset stop condition is satisfied, associating the M features with the M critical values in a combination with a highest score.Type: ApplicationFiled: February 19, 2020Publication date: June 11, 2020Inventors: Kai XIAO, Wenbiao ZHAO
-
Publication number: 20200167792Abstract: A method for identifying a risk pertaining to a transaction to be processed, includes: identifying a risk pertaining to a transaction to be processed via a fast identification layer in a risk control system, thereby obtaining a first identification result; identifying a risk of interference pertaining to the transaction to be processed via a model for identifying transactions susceptible to interference, thereby obtaining a second identification result; and determining a processing manner for the transaction to be processed based on the first identification result and the second identification result, the processing manner including releasing the transaction to be processed, or further identifying the risk pertaining to the transaction to be processed via the in-depth identification layer in the risk control system.Type: ApplicationFiled: January 28, 2020Publication date: May 28, 2020Inventors: Yicheng LU, Tao CHEN, Wenbiao ZHAO
-
Publication number: 20190295092Abstract: A method for identifying a risk pertaining to a transaction to be processed, includes: identifying a risk pertaining to a transaction to be processed via a fast identification layer in a risk control system, thereby obtaining a first identification result; identifying a risk of interference pertaining to the transaction to be processed via a model for identifying transactions susceptible to interference, thereby obtaining a second identification result; and determining a processing manner for the transaction to be processed based on the first identification result and the second identification result, the processing manner including releasing the transaction to be processed, or further identifying the risk pertaining to the transaction to be processed via the in-depth identification layer in the risk control system.Type: ApplicationFiled: June 13, 2019Publication date: September 26, 2019Inventors: Yicheng Lu, Tao Chen, Wenbiao Zhao
-
Publication number: 20090177480Abstract: A system and method are used to identify a targeted consumer. The system includes a partial social security number (SSN) system that identifies a partial SSN issued during a preselected time period and a marketing database system. The marketing database system receives a comparison result from a SSN matching system that identifies at least one individual in a consumer database having a partial SSN that matches the partial SSN identified by the partial SSN system. The marketing database system places identifying information of the at least one individual in a marketing database. In one method, an individual is identified as a targeted consumer based on the individual's age being within a preselected age range and the individual's social security number being issued within a predetermined social security number SSN issue date range. Identifying information of the targeted consumer is stored in a contact database, which a business may use to directly market its goods or services.Type: ApplicationFiled: January 7, 2008Publication date: July 9, 2009Applicant: American Express Travel Related Services Company, Inc.Inventors: Wenhan Chen, John Clements, Di W. Xu, Chao Yuan, Wenbiao Zhao