Household object searching method and device based on deep learning recommendation system

Abstract

The invention discloses a household object searching method and device based on a deep learning recommendation system, and the method comprises the steps: carrying out the reconstruction based on user information, obtaining a constructed model, and obtaining the implicit representation of a user and / or the implicit representation of a project; sending the constructed model to a tracking and monitoring camera device, and according to the implicit representation of the user and / or the implicit representation of the item, backtracking the place where the item appears through the tracking and monitoring camera device to obtain a recommendation list; and based on the recommendation list, obtaining a searchable place of the article, and finding the article.

Description

technical field [0001] The embodiment of this description relates to the field of artificial intelligence technology, and in particular to a method and device for finding objects at home based on a deep learning recommendation system. Background technique [0002] In recent years, artificial intelligence technology has become a hot spot in today's science and technology. Major scientific and technological countries including China have formulated artificial intelligence development strategies one after another. Artificial intelligence technology has developed rapidly. Human beings have entered a new era of artificial intelligence, and artificial intelligence technology has penetrated into all aspects of life. [0003] In family life, there will always be situations when you need to find something urgently. Under the existing technology, it is generally to modify the item, such as adding some chips for positioning, but this method of finding objects at home is expensive, and ...

AI Technical Summary

Problems solved by technology

Under the existing technology, it is generally to modify the item, such as adding some chips for positioning, but this method of finding objects at home is expensive, and the project is trivial and complicated

And because the current recommendation algorithm has relatively large limitations, when the scoring is very sparse, the prediction accuracy will be seriously reduced, and deep learning is applied to the recommendation system, due to its state-of-the-art performance and high-quality recommendations, it can be better. Understand the needs of users

Images