A smart home scene generation and recommendation method, device, equipment and medium

By filtering and combining the triggering conditions and actions of user activation, the activation probability of the target user is calculated, and a personalized smart home scene recommendation list is generated, which solves the problem of the inability to make personalized recommendations in the existing technology and improves the user experience.

CN115905645BActive Publication Date: 2026-06-12SHENZHEN CHENBEI TECH CO LTD
1 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
SHENZHEN CHENBEI TECH CO LTD
Filing Date
2022-11-28
Publication Date
2026-06-12

AI Technical Summary

⚠Technical Problem

Most existing smart home scenarios are official templates and cannot be recommended based on users' personalized needs, making it difficult for users to quickly find scenarios that meet their needs and resulting in a poor user experience.

⚗Method used

By filtering out trigger conditions and actions that meet preset filtering criteria from scenarios activated by users within a preset time period, target scenarios are generated. The probability of target users activating each target scenario is calculated, and a scenario recommendation list is generated to achieve personalized recommendations.

🎯Benefits of technology

It improves the user experience, enabling users to quickly find scenarios that meet their needs, and enhances the usability and personalized recommendation effect of smart home scenarios.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The application provides a smart home scene generation and recommendation method and device, equipment and medium, the method comprises: based on the user group in the preset time period, the user enabled scene is filtered out from the trigger condition and the execution action which meet the preset screening condition in the user enabled scene; the scene includes at least one trigger condition and at least one execution action;The trigger condition and the execution action screened out are combined to generate at least one target scene;Calculate the enable probability of target user to each target scene, obtain the value of the enable probability of each target scene;According to the value of the enable probability of each target scene, a scene recommendation list is generated by sorting. The application can realize automatic scene construction and realize personalized recommendation for users.
Need to check novelty before this filing date? Find Prior Art