Construction method and device for cross-equipment electromagnetic fingerprint database on the basis of machine learning

Abstract

The invention discloses a construction method for a cross-equipment electromagnetic fingerprint database on the basis of machine learning. The method comprises the following steps that: firstly, collecting the electromagnetic signal of equipment, and carrying out denoising, specific window bandwidth interception and digital processing on the electromagnetic signal; then, carrying out the machine learning on the processed electromagnetic signal, judging and obtaining the classification and the marking of the electromagnetic signal, and conveying the classification and marking information to a display; and finally, judging the correctness of a displayed equipment identification result by a user, if the displayed equipment identification result is correct, storing the classification and marking information into the electromagnetic fingerprint database, otherwise, collecting the electromagnetic signal of the equipment again, and carrying out machine learning again until the displayed equipment identification result is correct. By use of the method, the electromagnetic signal of the equipment can be accurately obtained so as to establish the electromagnetic fingerprint database, and the electromagnetic fingerprint database can be updated and enlarged while the database is used. The invention also discloses a device for realizing the above method, the support of external marking equipment is not required, cost is saved, and natural interaction with articles is enhanced.

Description

technical field [0001] The invention belongs to the field of electronic device marking, and in particular relates to a method and device for constructing a cross-device electromagnetic fingerprint database based on machine learning. Background technique [0002] With the rapid development of electronic technology and Internet of Things technology, more and more devices use microelectronic circuits, embedded chips and sensors, and combine the conductivity of the device itself, electromagnetic signal mode, etc. to form a unique electromagnetic signal. This unique electromagnetic signature can be used as an electromagnetic fingerprint to uniquely identify a device. [0003] The current cross-device information marking technology and method still have the following defects and deficiencies: [0004] 1) Additional device support is required, for example, radio frequency tags need to be pasted on the target device; [0005] 2) The cost is high, and equipment identification and m...

AI Technical Summary

Problems solved by technology

[0004] 1) Additional device support is required, for example, radio frequency tags need to be pasted on the target device;

[0005] 2) The cost is high, and equipment identification and marking in harsh environments require high-standard electronic signal equipment, which will cause large costs in the case of large-scale deployment;

[0006] 3) The environment is not friendly. When the radio frequency tags need to be removed, they will face problems such as inability to remove them at will, incomplete removal, easy damage to the original tags, and inability to reuse the tags. Moreover, a large number of discarded tags have metal components and The disposal of other compounds is also a severe test for the environment;

[0007] 4) The scalability and compatibility are not strong. The current equipment marking technology and methods often need to print special patterns on the surface of the equipment, such as two-dimensional codes, or need to paste additional electromagnetic marks on the surface of the item, such as radio frequency tags, or need to be printed on the surface of the equipment. A unique electromagnetic signal identification device is embedded inside the item to distinguish it from other items

This kind of unique labeling system or built-in identification equipment often requires a specific detection and interaction system, which brings great inconvenience to cross-category equipment marking and the change and expansion of marking;

[0008] 5) It is impossible to classify and mark the marked information and the human-computer interaction is not strong. The current equipment marking technology and method, after passing the detection of external equipment, cannot classify and mark the obtained information by itself and provide a user interface for information confirmation of

Images