Method and device for updating product defect detection model, storage medium and terminal equipment
A technology for detecting model and product defects, which is applied in the computer field to achieve the effect of improving applicability and detection accuracy
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0049] See figure 1 The embodiment of the present invention provides a method for updating a product defect detection model, which is executed by the training engine of the detection system, and includes steps S10 to S40, which are specifically as follows:
[0050] S10, receiving a first detection model generated by training.
[0051] In the embodiment of the present invention, the first detection model can refer to a new detection model generated by training, and the second detection model can refer to an old detection model running in the system. The two detection models have the same structure and are used for Detect product defects in product pictures input to the detection system.
[0052] The conditions that trigger the generation of a new detection model can be:
[0053] Judging whether the current statistical detection accuracy of the detection system is lower than the update threshold;
[0054] If yes, obtain training data from the training database; and
[0055] Training and g...
Embodiment 2
[0070] See Figure 5 , An embodiment of the present invention provides a device for updating a product defect detection model, including:
[0071] The model receiving module 10 is configured to receive the first detection model generated by training;
[0072] The first model replacement module 20 is used to replace the second detection model run by the server in the detection system with the first detection model, and make the number of servers running the first detection model and the operating location in the replacement detection system The ratio between the number of servers of the second detection model meets the replacement ratio; the first detection model represents a new detection model generated by current training, and the second detection model represents an old detection model running in the detection system The detection model is used to detect product defects in product pictures input to the detection system;
[0073] The accuracy statistics module 30 is used to count ...
Embodiment 3
[0085] The embodiment of the present invention also provides a terminal device, such as Image 6 As shown, the device includes a memory 21 and a processor 22, and a computer program that can run on the processor 22 is stored in the memory 21. When the processor 22 executes the computer program, the method for generating a traffic guidance map in the foregoing embodiment is implemented. The number of the memory 21 and the processor 22 may be one or more.
[0086] The equipment also includes:
[0087] The communication interface 23 is used for communication between the processor 22 and external devices.
[0088] The memory 21 may include a high-speed RAM memory, or may also include a non-volatile memory (non-volatile memory), for example, at least one disk memory.
[0089] If the memory 21, the processor 22, and the communication interface 23 are implemented independently, the memory 21, the processor 22, and the communication interface 23 can be connected to each other through a bus ...
PUM
Login to view more Abstract
Description
Claims
Application Information
Login to view more - R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap