DETERMINING CORRELATION DEGREE, APPARATUS, ELECTRONIC DEVICE, AND COMPUTER-READABLE STORAGE MEDIUM

    公开(公告)号:US20240296762A1

    公开(公告)日:2024-09-05

    申请号:US17919009

    申请日:2021-08-26

    CPC classification number: G09G3/006 G09G2330/12

    Abstract: A method for determining a correlation degree, an apparatus for determining a correlation degree, an electronic device, and a computer-readable storage medium. The method includes: acquiring measurement information and defect information on a display panel, wherein the measurement information includes a measurement value and a measurement location for a measurement indicator, and the defect information includes a defect type; determining an influence weight of the measurement indicator having the measurement value at the measurement location on the defect information of the defect type; and determining a correlation coefficient between the influence weight and the measurement value, and determining a correlation degree between the measurement information and the defect information according to the correlation coefficient. According to the method, it is beneficial to improve the accuracy and speed of analyzing the causes of defects, reduce the cost of analysis, improve the utilization rate of measurement information, and increase the worth of data.

    METHOD FOR DETECTING DEFECT AND METHOD FOR TRAINING MODEL

    公开(公告)号:US20230206420A1

    公开(公告)日:2023-06-29

    申请号:US17764707

    申请日:2021-01-28

    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.

    TASK PROCESSING METHOD BASED ON DEFECT DETECTION, DEVICE, APPARATUS AND STORAGE MEDIUM

    公开(公告)号:US20230030296A1

    公开(公告)日:2023-02-02

    申请号:US17429013

    申请日:2020-10-30

    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.

    DATA DISTRIBUTION SYSTEM AND DATA DISTRIBUTION METHOD

    公开(公告)号:US20220350685A1

    公开(公告)日:2022-11-03

    申请号:US17429912

    申请日:2020-11-18

    Abstract: The present disclosure relates a data distribution system and a data distribution method. The platform includes a channel configuration module and a data engine module, the channel configuration module is connected with an external device, and is configured to convert obtained device data of the external device into preset product model data and store the preset product model data into a second message queue; the data engine module is connected with the channel configuration module and is configured to distribute the preset product model data obtained from the second message queue. In this embodiment, data distribution can be achieved by uniformly analyzing the device data, such that the users of the data distribution system can directly use the device data, which is beneficial to improving the stability, compatibility and portability of the system.

    CONTROL SYSTEM AND POWER LINE NETWORK CONTAINING THE SAME

    公开(公告)号:US20180331844A1

    公开(公告)日:2018-11-15

    申请号:US15527012

    申请日:2016-11-07

    Inventor: Hong WANG

    Abstract: A control system for controlling a power line network having a power line, at least one electric appliance and at least one controller includes a central control unit, configured to realize programmable controls over the appliance by the controller with signals transmitted through the power line. An on-site control unit includes at least one modulator and at least one demodulator coupled with the central control unit. Each modulator is configured, upon receiving a first control signal from the controller, to generate and transmit a second control signal to the central control unit that is configured, upon receiving the second control signal, to generate and transmit a third control signal to the demodulator. Each demodulator is configured, upon receiving the third control signal, to generate and transmit a fourth control signal to the appliance.

Patent Agency Ranking