Screen peeping prevention method based on intelligent detection and related equipment thereof

Abstract

The embodiment of the invention belongs to the technical field of artificial intelligence, is applied to the field of intelligent communities, and relates to a screen peeping prevention method based on intelligent detection and related equipment thereof.The method comprises the steps that when it is monitored that a current page is a key page, sensitive data in the key page is hidden; acquiring a shot picture, performing portrait feature extraction operation on the shot picture, if the extraction fails, keeping hiding the sensitive data, and if the extraction succeeds, acquiring portrait features; performing matching operation on the portrait features and owner features stored in a database to obtain a matching degree; whether the matching degree is larger than or equal to a matching threshold value or not is judged, and if yes, sensitive data in the key page is modified to be in a display state. Wherein the shot picture can be stored in the block chain. According to the invention, on the premise of ensuring user privacy and high accuracy, the storage amount and the processing amount of data are reduced.

Description

Technical field [0001] This application involves the field of artificial intelligence technology, especially for intelligent detection -based anti -screen methods and related devices. Background technique [0002] When involving user -sensitive data display, users have higher requirements for privacy and portability. In the past, many devices could not accurately analyze user portraits. Different customers and related data for users and accurately distributed related data, and they could not meet the dual demands of privacy and convenience at the same time. [0003] In order to solve this situation, the methods of common use in the industry are: [0004] First, the background window platform, artificially analyzes user portraits, classifies different customer bases, corresponding to the corresponding customer base strategy, after reading the matching strategy data at the front end, according to the display / hidden sign of the data background mark, the corresponding display is perf...

AI Technical Summary

Problems solved by technology

Disadvantages of this method: the rules are not flexible, the cost of manual classification is high, and the range of label recognition is relatively fixed

However, the disadvantages of this method are also obvious: the amount of stored data is large, and there is a risk of data inconsistency at multiple terminals for mixed storage data and the inconvenience of requiring users to manually mark each time

[0006] To sum up, the customer group tags classified through the background window can mark the demands of different customer groups according to the strategy, reducing labor costs, but the pertinence is not strong; the customers identified through the background data are personalized and hidden, and the accuracy is high. However, the amount of change identification data is large, and the cost of manual maintenance is high

Images