Method and device for processing product manufacturing messages, electronic device, and computer-readable storage medium

Patent metadata

Field	Value
Publication number	US-12020516-B2
Application number	US-201917044160-A
Country	US
Kind code	B2
Filing date	Dec 20, 2019
Priority date	Dec 20, 2019
Publication date	Jun 25, 2024
Grant date	Jun 25, 2024

Abstract

A method and a device for processing product manufacturing messages, and an electronic device are disclosed. The method for processing product manufacturing messages includes: monitoring a plurality of product manufacturing messages; establishing a product defect analysis task queue based on the plurality of product manufacturing messages; distributing product defect analysis tasks to product manufacturing assisting devices based on the product defect analysis task queue, wherein the product defect analysis tasks include a task of identifying product defect content based on a defect identification model; wherein the product defect content includes any one or more of: product defect type, product defect location, and product defect size.

First claim

The invention claimed is:

1. A method for processing product manufacturing messages, comprising:
monitoring a plurality of product manufacturing messages;
establishing a product defect analysis task queue based on the plurality of product manufacturing messages; and
distributing product defect analysis tasks to product manufacturing assisting devices based on the product defect analysis task queue, wherein the product defect analysis tasks include a task of identifying product defect content based on a defect identification model;
wherein the product defect content includes any one or more of: product defect type, product defect location, and product defect size;
wherein the plurality of product manufacturing messages include at least one single-product manufacturing message and at least one LOT-products manufacturing message, and the monitoring the plurality of product manufacturing messages comprises:
monitoring LOT-products manufacturing messages by interrupt, the LOT-products manufacturing message being a collection of product manufacturing messages of the plurality of products of the same LOT; and
monitoring single-product manufacturing messages by polling during interruption intervals, the single-product manufacturing message being product manufacturing messages of a single product.

2. The method for processing product manufacturing messages according to claim 1 , further comprising:
sending registration information to a product manufacturing message serving device, wherein the registration information includes product manufacturing site information and/or first product information;
monitoring a first product manufacturing message sent from the product manufacturing message serving device, based on the registration information, wherein the first product manufacturing message is associated with the product manufacturing site information and/or the first product information.

3. The method for processing product manufacturing messages according to claim 2 , further comprising:
monitoring a second product manufacturing message sent from the product manufacturing message serving device, wherein the second product manufacturing message is irrelevant to the registration information;
determining whether a list of product manufacturing keywords includes a product manufacturing keyword in the second product manufacturing message;
reserving the second product manufacturing information in a case where the list of product manufacturing keywords includes the product manufacturing keyword in the second product manufacturing message; and
discarding the second product manufacturing information in a case where the list of product manufacturing keywords does not include the product manufacturing keyword in the second product manufacturing message.

4. The method for processing product manufacturing messages according to claim 1 , wherein, the establishing the product defect analysis task queue based on the plurality of product manufacturing messages further comprises:
establishing the product defect analysis task queue by sorting the product defect analysis tasks based on any one or more of: the order in which the product manufacturing messages are received, priorities of products, and a product scheduling plan.

5. The method for processing product manufacturing messages according to claim 1 , wherein, the defect identification model includes any one or more of: a feedforward neural network defect identification model, a convolutional neural network model, a recurrent neural network model, and a generative adversarial network model.

6. The method for processing product manufacturing messages according to claim 1 , further comprising:
obtaining a plurality of product images based on the plurality of product manufacturing messages;
obtaining product defects from the plurality of product images; wherein the obtaining product defects from the plurality of product images comprises any one or more of:
performing any one or more of: rotation, scaling, color transformation and interception of a product image of the plurality of product images in a case of an uneven distribution of the quantity of the product defects in the product image;
magnifying an image region in which a product defect is located in a case where the image region is smaller than a first predetermined threshold;
merging product images corresponding to any two product defects in a case where a similarity between the two product defects is greater than a second predetermined threshold; and
obtaining a frequency domain image of a product image of the plurality of product images in a case where a similarity between positive samples and negative samples in the product image is greater than a third predetermined threshold, and adjusting the positive samples or negative samples based on the frequency domain image;
generating the product defect analysis tasks based on the product defects.

7. The method for processing product manufacturing messages according to claim 1 , wherein the distributing product defect analysis tasks to product manufacturing assisting devices comprises:
obtaining a product type and a product defect analysis task type from the plurality of product manufacturing messages;
generating a product defect analysis request message based on the product type and the product defect analysis task type.

8. The method for processing product manufacturing messages according to claim 7 , wherein the product manufacturing assisting devices include a first product manufacturing assisting device and a second product manufacturing assisting device,
wherein the distributing product defect analysis tasks to product manufacturing assisting devices based on the product defect analysis task queue further comprises:
determining whether an AI defect identification model corresponding to the product type is present;
sending a first product defect analysis request message to the first product manufacturing assisting device in a case where the AI defect identification model corresponding to the product type is not present, wherein the first product defect analysis request message comprises the product type, a storage address of product images, a quantity of the plurality of product images, and a task identity for training the AI defect identification model;
sending a second product defect analysis request message to the second product manufacturing assisting device in a case where the AI defect identification model corresponding to said product type is present, wherein the second product defect analysis request message comprises the product type, a storage address of the product images, and a quantity of the product images.

9. The method for processing product manufacturing messages according to claim 8 , further comprising:
receiving a first product defect analysis response message sent by the first product manufacturing assisting device, wherein the first product defect analysis response message comprises one or more of: identity, accuracy, and recall of the AI defect identification model;
wherein the AI defect identification model is determined based on the product type, the storage address of the product images, and the quantity of the product images.

10. The method for processing product manufacturing messages according to claim 8 , further comprising:
receiving a second product defect analysis response message sent by the second product manufacturing assisting device, wherein the second product defect analysis response message comprises one or more of: product image identity, product defect location, product defect identity, and repair identity;
wherein the product defect location, the product defect identity and the repair identity are deter

Assignees

• Boe Technology Group Co Ltd

Inventors

• Zhang Meijuan
• Wang Yaoping
• Li Zhaoyue
• Lu Yuanyuan
• Chai Dong
• Wang Hong

Classifications

• H10P72/0616

  Monitoring of warpages, curvatures, damages, defects or the like · CPC title

• Y02P90/30

  Computing systems specially adapted for manufacturing · CPC title

• B29C45/76

  Measuring, controlling or regulating {(measuring in general G01; controlling or regulating in general G05)} · CPC title

• G06F11/3688

  for test execution, e.g. scheduling of test suites · CPC title

• G06T7/001

  using an image reference approach · CPC title