4 results about "Label Information Base" patented technology

The invention discloses a bottle body label real-time printing method and system based on image recognition, and the method comprises the steps: obtaining an image data set of a to-be-labeled bottle batch in a pre-recognition region, carrying out the image depth analysis of the image data set through a YOLO model, and obtaining the type and number of the to-be-labeled bottle batch; label printing instructions are generated in batches according to the types and number information of the bottles in batches, and the label printing instructions are classified and stored in a label information base according to the types of the bottles; when the single bottle arrives at the labeling station, the single bottle is quickly identified, the type of the bottle is confirmed, a matched label printing instruction is called from the label information base according to the confirmed type information, and a printer is driven to print a label; and the labels printed in real time are attached to the label attaching positions of the single bottles. The overall labeling efficiency and accuracy are improved by introducing the batch image depth analysis of the pre-recognition area and the batch generation and pre-storage mechanism of the label instruction.

The present invention relates to a method and system for collaborative updating of an AI model based on edge computing, and belongs to the field of Internet of Things technology. Among them, the method includes: collecting IoT data and video stream data, annotating information through a label information library and forming a local data set; the edge node broadcasts the AI ​​model to the terminal device according to the park application service; the terminal device calculates the local update parameters of the AI ​​model, calculates the weight index corresponding to the terminal device through the scheduling framework and uploads it to the edge node; the edge node constructs a resource matching terminal sequence according to the weight index and channel status and allocates bandwidth resources; if the terminal device receives a gradient upload instruction, the local update parameters are uploaded to the edge node through a multi-access channel; the edge node calculates the global gradient based on the received local update parameters, and updates the AI ​​model based on the global gradient. The ability of the terminal device management system to cope with heterogeneous management and low communication efficiency is improved.

The application relates to a control method of a label device, the method comprising: determining a broadcast duty cycle of the label device, the broadcast duty cycle being adaptively adjusted; periodically broadcasting label information based on the broadcast duty cycle; and receiving a feedback message for the label information from a payment device, thereby generating a payment voucher. The application also relates to a label device, a payment device and a computer storage medium.