Research On Entity Intelligent Search And Recommendation Strategy For The Internet Of Things

With the growing maturity of the Internet of Things,the explosion of the number of entities in the physical world,the Internet of Things search technology collects and integrates the physical information in the physical world through sensors to provide users with the status information of the required entities in real time.Due to the heterogeneity and mass of entities,the information collected by the sensor is too complicated,and it is difficult for the user to accurately obtain the entity information.The dynamic nature of the entity causes the traditional Internet search or recommendation method fail to meet the real-time requirements of Io T search.And users have high demands for real-time acquisition of entity information,thus a search and recommendation method that can accurately obtain denaturation of entity state information is required.Firstly,this thesis introduces the research background and typical application scenarios of Io T search,and describes the characteristics of Io T search technology.Then,this thesis summarizes the current status of domestic research,focusing on introducing and analyzing physical entity search strategies and physical entity recommendation strategies.Secondly,this thesis proposes an edge-cloud collaboration entity search method for Internet of Things(Io T)search.An entity search system architecture of edge and cloud collaboration is designed,which searches entity information with the collaboration of cloud and edge.Furthermore,an entity identification method suitable for edge is proposed,which takes into account the feature information of entities and carries out effective entity identification based on the depth clustering model,so as to improve the real-time and accuracy of entity state information search.Simulation results demonstrate that the proposed method can effectively improve the real-time and accuracy of entity search compared with traditional methods.Thirdly,this thesis proposes an edge-cloud collaboration entity recommendation method for Internet of Things(Io T)search.Existing Io T data recommendation methods ignore the characteristics of Io T data and user search beheavior,thus the recommendation performances are relatively limited.Considering the time-varying characteristics of the Io T entity state and the characteristics of user search behavior,an edge-cloud collaborative entity recommendation method is proposed via combining the advantages of edge computing and cloud computing.First,an entity recommendation system architecture based on the collaboration between edge and cloud is designed.Furthermore,an interest group division method applied in cloud is devised,which fully considers user's potential search needs and divides user interest groups based on clustering model for enhancing the quality of recommendation system.Simulation results demonstrate that the proposed recommendation method can effectively improve the real-time and accuracy performances of entity recommendation in comparison with traditional methods.Lastly,this thesis summarizes all the work and briefly prospects the possible future research directions.