Commodity warehouse-in and warehouse-out management system and method applied to individual vendors
A management system and management method technology, applied in the direction of data processing applications, neural learning methods, special scales, etc., can solve the problems of unsuitable mobile vendors, no motion communication function, and inconvenient commodity management system, so as to improve efficiency and reduce burden effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
specific Embodiment approach 1
[0020] Specific implementation mode one: refer to figure 1 This embodiment will be described in detail. A merchandise in-out warehouse management system applied to individual vendors described in this embodiment includes: a hardware acquisition system and a cloud server.
[0021] The hardware acquisition system is based on the STM32 development board, which is embedded with an acquisition unit for collecting commodity images, which is used to filter the commodity images, and then send the filtered commodity images to the preprocessing unit of the recognition unit, which is used to process the commodity images. Recognize, and perform non-maximum value suppression on the recognition result, obtain the recognition unit of the type and quantity of the product, and the display unit for displaying the type and quantity of the product. The acquisition unit is a camera, the recognition unit is a main control chip, and the display unit is a touch screen. Also includes a WIFI module fo...
specific Embodiment approach 2
[0034] Specific implementation mode two: refer to Figure 4 Specifically explaining this embodiment, a method for managing goods in and out of warehouses applied to individual vendors described in this embodiment includes the following steps:
[0035] Collect product images and product weights.
[0036] Perform filtering preprocessing on the commodity image to obtain the preprocessed commodity image.
[0037] The preprocessed commodity image is sent to a convolutional neural network trained by the YOLO algorithm for recognition, and the convolutional neural network is a Darknet-53 network.
[0038] Non-maximum suppression is performed on the recognition result to obtain the type and quantity of the product in the product image.
[0039] Enter the weight, type and quantity of the goods into the MySQL database for storage.
[0040] Display the weight, type and quantity of the goods through the mobile phone.
[0041] In this embodiment, a WeChat applet is embedded in the mobi...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


