Edge and Cloud Collaborative Entity Recommendation Method towards the IoT Search

There are massive entities with strong denaturation of state in the physical world, and users have urgent needs for real-time and intelligent acquisition of entity information, thus recommendation technologies that can actively provide instant and precise entity state information come into being. Existing IoT data recommendation methods ignore the characteristics of IoT data and user search behavior; thus the recommendation performances are relatively limited. Considering the time-varying characteristics of the IoT 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. Then, an entity identification method suitable for edge is presented, which takes into account the feature information of entities and carries out effective entity identification based on the deep clustering model, so as to improve the real-time and accuracy of entity state information search. 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 performance of entity recommendation in comparison with traditional methods.

Personalized Spatio-Temporal OLAP Queries Suggestion Based on User Behavior and a New Similarity Measure

Spatio-temporal data warehouses store enormous amount of data. They are usually exploited by spatio-temporal OLAP systems to extract relevant information. For extracting interesting information, the current user launches spatio-temporal OLAP (ST-OLAP) queries to navigate within a geographic data cube (Geo-cube). Very often choosing which part of the Geo-cube to navigate further, and thus designing the forthcoming ST-OLAP query, is a difficult task. So, to help the current user refine his queries after launching in the geo-cube his current query, we need a ST-OLAP queries suggestion by exploiting a Geo-cube. However, models that focus on adapting to a specific user can help to improve the probability of the user being satisfied. In this chapter, first, the authors focus on assessing the similarity between spatio-temporal OLAP queries in term of their GeoMDX queries. Then, they propose a personalized query suggestion model based on users' search behavior, where they inject relevance between queries in the current session and current user' search behavior into a basic probabilistic model.

Predicting implicit search behaviors usinglog analysis

Search engines provide ranked information based on the query given by the user. Understanding user search behavior is an important task for satisfaction of the users with the needed information. Understanding user search behaviors and recommending more information or more sites to the user is an emerging task. The work is based on the queries given by the user, the amount of time the user spending on the particular page, the number of clicks done by the user particular URL. These details will be available in the dataset of web search log. The web search log is nothing but the log which contains the user searching activities and other details like machine ID, browser ID, timestamp, query given by the user, URL accessed etc., four things considered as the important: 1) Extraction of tasks from the sequence of queries given by the user 2) suggesting some similar query to the user 3) ranking URLs based on the implicit user behaviors 4) increasing web page utilities based on the implicit behaviors. For increasing the web page utility and ranking the URLs predicting implicit user behavior is a needed task. For each of these four things designing and implementation of some algorithms and techniques are needed to increase the efficiency and effectiveness.

Users’ search in OPAC: Findings of search statistics analysis at RAS SB State Public Scientific and Technological Library

OPAC user search behavior study was conducted at RAS SB State Public Scientific and Technological Library based on OPAC log files information in statistical database for 2016. The frequency of information retrieval languages, the keyword language in the first place, and the information retrieval language of subject headings in the second place, was assessed. User search behavior in OPAC using keywords is characterized. Different search request structures in this language are discussed. Individual search stories are analyzed. Typical search strategies, formulations, update methods are defined. The author concludes on the urgency of problems OPAC users face and suggests how to improve the situation.

User search terms and controlled subject vocabularies in an institutional repository

Purpose The purpose of this paper is to investigate the search behavior of institutional repository (IR) users in regard to subjects as a means of estimating the potential impact of applying a controlled subject vocabulary to an IR. Design/methodology/approach Google Analytics data were used to record cases where users arrived at an IR item page from an external web search and subsequently downloaded content. Search queries were compared against the Faceted Application of Subject Terminology (FAST) schema to determine the topical nature of the queries. Queries were also compared against the item’s metadata values for title and subject using approximate string matching to determine the alignment of the queries with current metadata values. Findings A substantial portion of successful user search queries to an IR appear to be topical in nature. User search queries matched values from FAST at a higher rate than existing subject metadata. Increased attention to subject description in IR records may provide an opportunity to improve the search visibility of the content. Research limitations/implications The study is limited to a particular IR. Data from Google Analytics does not provide comprehensive search query data. Originality/value The study presents a novel method for analyzing user search behavior to assist IR managers in determining whether to invest in applying controlled subject vocabularies to IR content.

Impact of device on search pattern transitions

Purpose This paper discusses the differences in search pattern transitions for mobile phone, tablet and desktop devices by mining the transaction log data of a library online public access catalogue (OPAC). We aimed to analyze the impacts of different devices on user search behavior and provide constructive suggestions for the development of library OPACs on different devices. Design/methodology/approach Based on transaction logs which are 9 GB in size and contain 16,140,509 records of a university library OPAC, statistics and clustering were used to analyze the differences in search pattern transitions on different devices in terms of two aspects: search field transition patterns and query reformulation patterns. Findings Search field transition patterns are influenced by the input function and user interfaces of different devices. As reformulation times increase, the differences between query reformulation patterns among different devices decrease. Practical implications Mobile-side libraries need to optimize user interfaces, for example by setting web page labels and improving input capabilities. Desk-side libraries can add more suggestive content on the interface. Originality/value Unlike previous studies, which have analyzed web search, this paper focuses on library OPAC search. The search function of mobile phones, tablets and desktops were found to be asymptotic, which was a good illustration of how devices have a large impact on user search behavior.