The Knowledge Graph (KG) is a model that represents structured knowledge by capturing entities and their relationships in the real world. It is widely used in search engines, recommendation systems, and natural language processing. Knowledge Representation Learning (KRL) transforms semantic information from knowledge graphs into continuous vector space representations, thereby improving knowledge acquisition and reasoning capabilities. However, current KRL faces issues such as underutilization of entity attribute information and difficulty in handling zero-shot scenarios. This paper proposes the Integrated Embedding Model (IEM) to address these issues. IEM employs a BERT-based attribute encoder and attention mechanism to weigh different attribute types, creating reliable attribute information embedding. During training, IEM merges structure and attribute representations, demonstrating excellent performance in knowledge graph completion tasks. Additionally, this paper introduces the Open Domain Representation Learning Model (ODRLM) for entity and link prediction in open domain knowledge graphs. ODRLM enhances the representation of zero-shot entities and relationships through three stages of optimization. Experimental results show that this model significantly improves both entity and relationship prediction accuracy, effectively addressing challenges in knowledge graph completion, especially in Zero-shot scenarios.
KEYWORDS: Optical fiber cables, Data privacy, Inspection, Geographic information systems, Bayesian inference, Optical transmission, Lithium, Detection and tracking algorithms, Model based design, Matrices
To protect the location privacy of key nodes in transmission routing, we have studied a trajectory privacy preserving method for transmission resources. By anonymizing the gis information of the whole route, that is, anonymizing all the location information including the first and last stations of the route. Firstly, the internal point of the whole optical cable is protected by grid protection method, and then a method based on Bayesian reasoning is proposed to protect the location privacy of the endpoints including starting point and destination. Through Bayesian inference process, it is proved that the starting point of optical cable routing can be protected by shear the point closest to the starting point and the destination, and the destination location protection algorithm can be obtained in the same way. In order to further improve the endpoints protection performance, we divide the day into different time spans according to the scene of optical cable inspection, and then integrate the anonymization process into this time span. By comparing the two endpoints prediction algorithms with Syn_sub and PBT, it is proved that the proposed endpoints protection algorithm is more effective than the classical algorithm.
With rapid economic, technological, and industrial development, the transport network is under increasing load pressure. Making the best use of existing road network resources and traffic management resources, improving traffic and travel management, and increasing the efficiency of road use are essential issues we need to face. In this paper, the traditional BPR model is modified to take into account complications such as intersections, traffic accidents, road maintenance under congestion, and delay time due to queueing under congestion. The queueing time of a congested traffic flow is estimated using a trajectory tracking method using the cell phone signal of the driver and the base station data in the traffic network. The traditional BPR model was creatively modified to develop a modified BPR functional model for estimating traffic delay, which can be applied in transportation network planning. The final experimental model simulates the effect of traffic delay during vehicle movement, reflecting road flow, and providing effect support for road network planning.
Knowledge Graph Completion (KGC) aims at predicting missing information for knowledge graphs. Most methods concentrate on learning entities’ representations with structural information indicating the relations between entities, while the utilization of entity attribute information is not sufficient for KGC. How to use the complex and diverse entity attribute information for KGC is still a challenging problem. In this paper, we propose a novel joint model Entity Structural and Attribute Embedding (ESAE) for KGC, which takes advantage of the entity structural and attribute information. Specifically, we first design a novel encoder Attribute Encoder (AE), which encodes both entity attribute types and values to generate the entities’ attribute-based representations. Based on AE, we use the structure-based and attribute-based representations in ESAE. We evaluate our method on the KGC task. Experimental results on real-world datasets show that our method outperforms other baselines on KGC.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.