公开(公告)号：US11244402B2

公开(公告)日：2022-02-08

申请号：US16022194

申请日：2018-06-28

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Yuxiang Lei ,  Guanru Li ,  Wei Ding ,  Jing Huang ,  Chunping Tan ,  Shiyi Chen ,  Mingqian Shi ,  Peilin Zhao ,  Longfei Li ,  Zhiqiang Zhang

IPC: G06Q40/08 ,  G06K9/62 ,  G06N3/02 ,  H04L29/08

Abstract: A plurality of variable data of personal attribute information associated with at least one vehicle insurance user is received at a prediction server. Based on a service scenario requirement, a pre-constructed prediction algorithm is selected. The plurality of variable data is processed by one or more processors using the pre-constructed prediction algorithm. At least one prediction result is generated as the prediction server.

公开(公告)号：US11176330B2

公开(公告)日：2021-11-16

申请号：US16814842

申请日：2020-03-10

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiexiong Lin ,  Taifeng Wang ,  Jing Huang ,  Mengshu Sun

IPC: G06F40/30 ,  G06N20/00 ,  G06N3/08 ,  G06F40/279 ,  G06N3/04 ,  G06Q30/02

Abstract: Implementations of this disclosure provide methods and apparatuses for generating recommendation information. An example method includes matching text content from a text content library based on a plurality of predetermined scenario-related words; extracting keywords from the related text content, to generate a plurality of training samples; and for each training sample, providing a source sequence of a sequence pair corresponding to the training sample as an input to a recommendation information generation model, obtaining, from the recommendation information generation model, a predicted word, and adjusting a model parameter of the recommendation information generation model based on a comparison between the predicted word and a corresponding word in a target sequence of the sequence pair corresponding to the training sample, to train the recommendation information generation model.

公开(公告)号：US20210027018A1

公开(公告)日：2021-01-28

申请号：US16814842

申请日：2020-03-10

Applicant: Advanced New Technologies Co., Ltd.

Inventor： Xiexiong Lin ,  Taifeng Wang ,  Jing Huang ,  Mengshu Sun

IPC: G06F40/30 ,  G06N3/08 ,  G06N3/04 ,  G06F40/279

Abstract: Implementations of this disclosure provide methods and apparatuses for generating recommendation information. An example method includes matching text content from a text content library based on a plurality of predetermined scenario-related words; extracting keywords from the related text content, to generate a plurality of training samples; and for each training sample, providing a source sequence of a sequence pair corresponding to the training sample as an input to a recommendation information generation model, obtaining, from the recommendation information generation model, a predicted word, and adjusting a model parameter of the recommendation information generation model based on a comparison between the predicted word and a corresponding word in a target sequence of the sequence pair corresponding to the training sample, to train the recommendation information generation model.