Passing equipment control method and device based on face recognition and voice interaction, machine readable medium and equipment

Abstract

The invention discloses a passing equipment control method based on face recognition and voice interaction. The method comprises the steps of carrying out the face recognition of a face image, collected by the passing equipment, of a target object, and generating a corresponding behavior type according to a face recognition result, when the behavior type is not passed, controlling the passing equipment to perform multiple rounds of voice interaction with the target object, and controlling the passing equipment to be opened or kept closed according to the voice interaction result. Different conditions of the face recognition result can be processed and classified, for example, the recognition result is fuzzy under a strong illumination background, and according to the judgment result, the system further interacts with the user by adopting a voice question and answer mode to confirm the identity of the user, so that further judgment and decision are made.

Description

technical field [0001] The present invention relates to the field of artificial intelligence, in particular to a traffic equipment control method, device, machine-readable medium and equipment based on face recognition and voice interaction. Background technique [0002] In the access control system at the entrance of an office building, it is necessary to collect the user's face information or conduct identity authentication through voice interaction, so as to decide whether to allow him to pass. At the same time, in order to provide corresponding voice guidance services for different user roles, it needs to be combined with the employee information system and visitor reservation system. [0003] At present, the general process of the intelligent access control system is that the user first performs face recognition through snapshots. If the face recognition result exceeds the set threshold, the access control will be opened and a corresponding welcome message will be given...

AI Technical Summary

Problems solved by technology

However, because the results of face recognition are greatly affected by different lighting backgrounds or shooting angles and the situation of visiting without an appointment, there will be many processes that first pass the judgment of the face recognition module and then interact through the voice module In some cases, the two modules are independent systems, which makes the operation efficiency of the smart access control as a whole system not high, thus affecting the user experience

[0004] On the other hand, in the voice interaction module, the dialog Q&A established based on the rules enables the module to reply to the set questions only according to the intentions and entities extracted by the natural language understanding sub-module. For questions outside the set, the system It is impossible to make an effective reply and provide corresponding guidance to users, and such problems often occur when users of different roles use the access control system, such as visitors without reservations in systems such as takeaway staff

Therefore, rule-based voice interaction modules are usually only suitable for communication scenarios where users and scenarios are relatively certain, and cannot meet the needs of multi-role users

Images