Research on the User Interest Modeling of Personalized Search Engine

At present, how to enable Search Engine to construct user personal interest model initially, master user＇s personalized information timely and provide personalized services accurately have become the hotspot in the research of Search Engine area. Aiming at the problems of user model＇s construction and combining techniques of manual customization modeling and automatic analytical modeling, a User Interest Model （UIM） is proposed in the paper. On the basis of it, the corresponding establishment and update algorithms of User lnterest Profile （UIP） are presented subsequently. Simulation tests proved that the UIM proposed and corresponding algorithms could enhance the retrieval precision effectively and have superior adaptability.

Learning Hierarchical User Interest Models from Web Pages

We propose an algorithm for learning hierarchical user interest models according to the Web pages users have browsed. In this algorithm, the interests of a user are represented into a tree which is called a user interest tree, the content and the structure of which can change simultaneously to adapt to the changes in a user＇s interests. This expression represents a user＇s specific and general interests as a continuurn. In some sense, specific interests correspond to shortterm interests, while general interests correspond to longterm interests. So this representation more really reflects the users＇ interests. The algorithm can automatically model a us er＇s multiple interest domains, dynamically generate the in terest models and prune a user interest tree when the number of the nodes in it exceeds given value. Finally, we show the experiment results in a Chinese Web Site.

Enhancing Next-Item Recommendation Through Adaptive User Group Modeling

Session-based recommender systems are increasingly applied to next-item recommendations.However,existing approaches encode the session information of each user independently and do not consider the interrelationship between users.This work is based on the intuition that dynamic groups of like-minded users exist over time.By considering the impact of latent user groups,we can learn a user’s preference in a better way.To this end,we propose a recommendation model based on learning user embeddings by modeling long and short-term dynamic latent user groups.Specifically,we utilize two network units to learn users’long and short-term sessions,respectively.Meanwhile,we employ two additional units to determine the affiliation of users with specific latent groups,followed by an aggregation of these latent group representations.Finally,user preference representations are shaped comprehensively by considering all these four aspects,based on an attention mechanism.Moreover,to avoid setting the number of groups manually,we further incorporate an adaptive learning unit to assess the necessity for creating a new group and learn the representation of emerging groups automatically.Extensive experiments prove our model outperforms multiple state-of-the-art methods in terms of Recall,mean average precision(mAP),and area under curve(AUC)metrics.

Formal Reduction of Interfaces to Large-scale Process Control Systems

A formal methodology is proposed to reduce the amount of information displayed to remote human operators at interfaces to large-scale process control plants of a certain type. The reduction proceeds in two stages. In the first stage, minimal reduced subsets of components, which give full information about the state of the whole system, are generated by determining functional dependencies between components. This is achieved by using a temporal logic proof obligation to check whether the state of all components can be inferred from the state of components in a subset in specified situations that the human operator needs to detect, with respect to a finite state machine model of the system and other human operator behavior. Generation of reduced subsets is automated with the help of a temporal logic model checker. The second stage determines the interconnections between components to be displayed in the reduced system so that the natural overall graphical structure of the system is maintained. A formal definition of an aesthetic for the required subgraph of a graph representation of the full system, containing the reduced subset of components, is given for this purpose. The methodology is demonstrated by a case study.

Information perception and feedback mechanism and key techniques of multi-modality human-robot interaction for service robots

With the increasing of the elderly population and the growing hearth care cost, the role of service robots in aiding the disabled and the elderly is becoming important. Many researchers in the world have paid much attention to heaRthcare robots and rehabilitation robots. To get natural and harmonious communication between the user and a service robot, the information perception/feedback ability, and interaction ability for service robots become more important in many key issues.

Data Logic Structure and Key Technologies on Intelligent High-precision Map

Taking autonomous driving and driverless as the research object,we discuss and define intelligent high-precision map.Intelligent high-precision map is considered as a key link of future travel,a carrier of real-time perception of traffic resources in the entire space-time range,and the criterion for the operation and control of the whole process of the vehicle.As a new form of map,it has distinctive features in terms of cartography theory and application requirements compared with traditional navigation electronic maps.Thus,it is necessary to analyze and discuss its key features and problems to promote the development of research and application of intelligent high-precision map.Accordingly,we propose an information transmission model based on the cartography theory and combine the wheeled robot’s control flow in practical application.Next,we put forward the data logic structure of intelligent high-precision map,and analyze its application in autonomous driving.Then,we summarize the computing mode of“Crowdsourcing+Edge-Cloud Collaborative Computing”,and carry out key technical analysis on how to improve the quality of crowdsourced data.We also analyze the effective application scenarios of intelligent high-precision map in the future.Finally,we present some thoughts and suggestions for the future development of this field.

UTM:A trajectory privacy evaluating model for online health monitoring

A huge amount of sensitive personal data is being collected by various online health monitoring applications.Although the data is anonymous,the personal trajectories(e.g.,the chronological access records of small cells)could become the anchor of linkage attacks to re-identify the users.Focusing on trajectory privacy in online health monitoring,we propose the User Trajectory Model(UTM),a generic trajectory re-identification risk predicting model to reveal the underlying relationship between trajectory uniqueness and aggregated data(e.g.,number of individuals covered by each small cell),and using the parameter combination of aggregated data to further mathematically derive the statistical characteristics of uniqueness(i.e.,the expectation and the variance).Eventually,exhaustive simulations validate the effectiveness of the UTM in privacy risk evaluation,confirm our theoretical deductions and present counter-intuitive insights.

Detection of scene-irrelevant head movements via eye-head coordination information

Background Accurate motion tracking in head-mounted displays(HMDs)has been widely used in immersive VR interaction technologies.However,tracking the head motion of users at all times is not always desirable.During a session of HMD usage,users may make scene-irrelevant head rotations,such as adjusting the head position to avoid neck pain or responding to distractions from the physical world.To the best of our knowledge,this is the first study that addresses the problem of scene-irrelevant head movements.Methods We trained a classifier to detect scene-irrelevant motions using temporal eye head-coordinated information sequences.To investigate the usefulness of the detection results,we propose a technique to suspend motion tracking in HMDs where scene-irrelevant motions are detected.Results/Conclusions Experimental results demonstrate that the scene-relevancy of movements can be detected using eye-head coordination information,and that ignoring scene-irrelevant head motions in HMDs improves user continuity without increasing sickness or breaking immersion.

A Solution to Knowledge Management in Networked Collaborative Design

Concerning the demands in networked collaborative innovative design, a knowledge-based collaborative design model is introduced the model of knowledge integration along with its relevant supporting techniques are presented. After illustrating the general knowledge search paradigm, a kind of dynamic user model is proposed to improve knowledge search efficiency. At last a short introduction of the system’s implementation is described.

On the Modeling of Honest Players in Reputation Systems

Reputation mechanisms are a key technique to trust assessment in large-scale decentralized systems. The effectiveness of reputation-based trust management fundamentally relies on the assumption that an entity＇s future behavior may be predicted based on its past behavior. Though many reputation-based trust schemes have been proposed, they can often be easily manipulated and exploited, since an attacker may adapt its behavior, and make the above assumption invalid. In other words, existing trust schemes are in general only effective when applied to honest players who usually act with certain consistency instead of adversaries who can behave arbitrarily. In this paper, we investigate the modeling of honest entities in decentralized systems. We build a statistical model for the transaction histories of honest players. This statistical model serves as a profiling tool to identify suspicious entities. It is combined with existing trust schemes to ensure that they are applied to entities whose transaction records are consistent with the statistical model. This approach limits the manipulation capability of adversaries, and thus can significantly improve the quality of reputation-based trust assessment.

Personalization Method of E-Catalog Based on User Interesting Degree

The user interesting degree evaluation index is designed to fulfill the users' real needs,which includes the user' attention degree of commodity,hot commodity and preferential commodity.User interesting degree model(UIDM) is constructed to justify the value of user interesting degree;the personalization approach is presented;operations of add and delete nodes(branches) are covered in this paper.The improved e-catalog is more satis?ed to users' needs and wants than the former e-catalog which stands for enterprises,and the improved one can complete the recommendation of related products of enterprises.

Joint model of user check-in activities for point-of-interest recommendation

With the rapid development of location-based networks, point-of-interest（POI） recommendation has become an important means to help people discover interesting and attractive locations, especially when users travel out of town. However, because users only check-in interaction is highly sparse, which creates a big challenge for POI recommendation. To tackle this challenge, we propose a joint probabilistic generative model called geographical temporal social content popularity（GTSCP） to imitate user check-in activities in a process of decision making, which effectively integrates the geographical influence, temporal effect, social correlation, content information and popularity impact factors to overcome the data sparsity, especially for out-of-town users. Our proposed the GTSCP supports two recommendation scenarios in a joint model, i.e., home-town recommendation and out-of-town recommendation. Experimental results show that GTSCP achieves significantly superior recommendation quality compared to other state-of-the-art POI recommendation techniques.

ACTPred: Activity Prediction in Mobile Social Networks

A current trend for online social networks is to turn mobile.Mobile social networks directly reflect our real social life,and therefore are an important source to analyze and understand the underlying dynamics of human behaviors （activities）.In this paper,we study the problem of activity prediction in mobile social networks.We present a series of observations in two real mobile social networks and then propose a method,ACTPred,based on a dynamic factor-graph model for modeling and predicting users＇ activities.An approximate algorithm based on mean fields is presented to efficiently learn the proposed method.We deploy a real system to collect users＇ mobility behaviors and validate the proposed method on two collected mobile datasets.Experimental results show that the proposed ACTPred model can achieve better performance than baseline methods.

Personalized Service System Based on Hybrid Filtering for Digital Library

Personalized service systems are an effective way to help users obtain recommendations for unseen items, within the enormous volume of information available based on their preferences. The most commonly used personalized service system methods are collaborative filtering, content-based filtering, and hybrid filtering. Unfortunately, each method has its drawbacks. This paper proposes a new method which unified partition-based collaborative filtering and meta-information filtering. In partition-based collaborative filtering the user-item rating matrix can be partitioned into low-dimensional dense matrices using a matrix clustering algorithm. Recommendations are generated based on these low-dimensional matrices. Additionally, the very low ratings problem can be solved using meta-information filtering. The unified method is applied to a digital resource management system. The experimental results show the high efficiency and good performance of the new approach.

News recommendation based on time factor and word embedding

Existing algorithms of news recommendations lack in depth analysis of news texts and timeliness. To address these issues, an algorithm for news recommendations based on time factor and word embedding(TFWE) was proposed to improve the interpretability and precision of news recommendations. First, TFWE used term frequency-inverse document frequency(TF-IDF) to extract news feature words and used the bidirectional encoder representations from transformers(BERT) pre-training model to convert the feature words into vector representations. By calculating the distance between the vectors, TFWE analyzed the semantic similarity to construct a user interest model. Second, considering the timeliness of news, a method of calculating news popularity by integrating time factors into the similarity calculation was proposed. Finally, TFWE combined the similarity of news content with the similarity of collaborative filtering(CF) and recommended some news with higher rankings to users. In addition, results of the experiments on real dataset showed that TFWE significantly improved precision, recall, and F1 score compared to the classic hybrid recommendation algorithm.

Enhancing accessibility to web mapping systems with technology-aligned adaptive profiles

Web-based geographic information systems have advanced rapidly on the back of web-based technologies,increased bandwidths and access to Digital Earth imagery and functionality.However,these advances are causing its capabilities to slowly overtake those of end-users.Additionally,the introduction of non-desktop devices such as smartphones,tablets and netbooks is starting to undo progress made towards standardisation of web-based technology.Large varia-tions in screen sizes,computational power,bandwidth,and operating environ-ments are once again introducing the need to ensure software remains functional across different platforms,standards-compliant or not.These two issues highlight the need for a mechanism to tune content and capability to end-users and their environment,to prevent information and complexity overload in a field already troubled by poor usability,while promoting cross-platform compatibility.This paper proposes the use of adaptivity to accommodate for users from different backgrounds accessing web mapping systems in different technical environments.It describes adaptive profiles aligned to the finite number of states a system can adopt,rather than the limitless range of user or environment characteristics that cannot be adapted to.Each profile consists of a combination of adaptive states comprising functionality,information detail,or technical demands to optimise for individual users or technical environments.

Implementation of a new network equilibrium model of travel choices

This paper develops a new combined network equilibrium model by using more behaviorally sound mathematical forms to represent the four travel choices（i.e., trip frequency,destination, mode, and route） in a conventional travel demand forecasting process. Trip frequency choice relates to the traveler decision on “making a trip” or “not making a trip”so it is given by a binary logit model. Destination choice is formulated as a parameterized dogit model of which the captivity parameters（expressed as functions of independent variables） allow individual travelers to be captive to specific destinations. Mode choice is given by a two-level nested logit model to avoid IIA restriction. Trip assignment is based on Wardrop＇s “user-optimized” principle. All model forms describing travel choices are in response to the level of services incurred by the transportation system. Through the introduction of inclusive values, the traveler decisions concerning trip frequency, destination, mode, and route choices are inherently interrelated and jointly determined.To obtain solutions of the new combined model, it was reformulated as an equivalent convex programming problem with linear constraints, a great advantage from the computational aspects. The model was applied empirically to a transportation network in New Jersey. The application results show that the new model is consistently better than the commonly used logit combined model in reproducing the observed trip flows from origin zones, origin to destination（O-D） trip flows, O-D trip flows by mode, and trip flows on the network links.

A congestion bottleneck analysis model for tourist block street network

The development of the tourism industry has led to increased pressure of people flow in tourist blocks.Therefore,it is critical to ease the traffic pressure in these blocks.This paper aims to identify the bottleneck links of street networks in tourist blocks to achieve the effective prevention of congestion accidents.A logit stochastic user equilibrium model combined with spatial syntax is presented to study the travelers’route choice behavior.The nonlinear Bureau of Public Roads function is applied to calculate the time impedance of each street.A case analysis of the Chongqing Ciqikou tourist block shows that the bottleneck link has the features of high integration and a large degree of negative time impedance evolution.The research’s results are more consistent with practical circumstances because the influence of the road network topological structure on pedestrian path selection has been considered.