公开(公告)号：US20240296163A1

公开(公告)日：2024-09-05

申请号：US17800304

申请日：2021-05-31

Applicant: Beijing Zhongxiangying Technology Co., Ltd. ,  BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Fan ZHANG ,  Haijin WANG ,  Hong WANG ,  Yiming LEI ,  Dong CHAI ,  Wangqiang HE ,  Jianmin WU

IPC: G06F16/2457 ,  G06F16/242

CPC classification number: G06F16/24578 ,  G06F16/2428

Abstract: A data processing method includes: acquiring sample data of each sample of samples produced within a preset time period, the sample data including a value, which is acquired at each acquisition time, of a device parameter of a device through which the sample passes, and a test result of the sample; dividing sample data of the samples into data of positive samples and data of negative samples according to test results of the samples; determining a sample segment point of each sample according to values of the device parameter, so as to obtain N value groups of target values corresponding to each sample; and determining a related quantized value according to a difference between an M-th value group of a positive sample and an M-th value group of a negative sample.

公开(公告)号：US20230206420A1

公开(公告)日：2023-06-29

申请号：US17764707

申请日：2021-01-28

Applicant: Beijing Zhongxiangying Technology Co., Ltd. ,  BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Yaoping WANG, Sr. ,  Zhaoyue LI ,  Haodong YANG ,  Meijuan ZHANG ,  Dong CHAI ,  Hong WANG

IPC: G06T7/00

CPC classification number: G06T7/001 ,  G06T2207/20084 ,  G06T2207/20081

Abstract: A method and device for detecting a defect and method for training a model are provided. The method for detecting the defect includes: acquiring a sample data set and identifying feature information of the sample data set; acquiring an initial model; configuring a training parameter based on the feature information; obtaining a target model by training, according to the training parameter, the initial model with the sample data set; and obtaining defect information of a product by inputting real data of the product into the target model. The training parameter includes at least one of a learning rate descent strategy, a total number of training rounds and a test strategy, the learning rate descent strategy includes a number of learning rate descents and a round number when a learning rate descends, and the test strategy includes a number of tests and a round number when testing.

公开(公告)号：US20230030296A1

公开(公告)日：2023-02-02

申请号：US17429013

申请日：2020-10-30

Applicant: Beijing Zhongxiangying Technology Co., Ltd. ,  BOE TECHNOLOGY GROUP CO., LTD.

Inventor： Meijuan ZHANG ,  Yaoping WANG ,  Zhaoyue LI ,  Yuanyuan LU ,  Wangqiang HE ,  Dong CHAI ,  Hong WANG

IPC: G05B23/02 ,  G05B13/02

Abstract: The present disclosure relates to a task processing method and device based on defect detection, a computer readable storage medium, and a task processing apparatus . The method includes receiving a detection task; determining a task type of the detection task; storing the detection task in a task queue if the task type is a target task type; and executing the detection task in a preset order and generating a feedback signal when a processor is idle. The detection task of the target task type includes an inference task and a training task. Executing the training task includes modifying configuration information according to a preset rule based on product information in the detection task; acquiring training data and an initial model according to the product information; and using the training data to train the initial model according to the configuration information to obtain a target model and store it in memory.

公开(公告)号：US20220113710A1

公开(公告)日：2022-04-14

申请号：US17273177

申请日：2019-11-29

Applicant: BOE Technology Group Co., Ltd.

Inventor： Guoliang SHEN ,  Dong CHAI ,  Haohan WU ,  Tian LAN ,  Weihe LIU

IPC: G05B19/418

Abstract: A system for recommending a maximum quantity of work in process, in which one or more processors of a distributed storage device are configured to execute: acquiring at least part of production data stored in the distributed storage device, the production data includes quantity records and cycle time records of a production line in time periods, and the cycle time record of each time period includes a cycle time at each process station of the production line in said each time period; clustering the quantity records to obtain a plurality of initial classifications, each initial classification includes at least one quantity record; determining a portion of the initial classifications as preferred classifications; determining the maximum quantity of work in process at each process station; and a display device is configured to display the maximum quantity of work in process at each process station determined by an analysis device.