It is very difficult to evaluate the effects of government governance.Without a good evaluation method and evaluation system,the effects of government governance cannot be guaranteed.Understanding the intention of web users in the topic of government governance from the perspective of natural language question-and-answering was proposed.By constructing a knowledge graph of intentions,equivalent questions and intentions were associated.The definition,construction framework and usage examples in government governance were illustrated,showing that knowledge graph of intentions is an effective way to evaluate the effects of government governance.In the context of government governance,by using the knowledge graphs of intentions,the intention fields between different governance subjects under the same governance topic were analyzed and compared,the effects of specific governance subjects on specific governance topics were analyzed,and the issues remained in government governance were found.
Specific to problems such as insufficient data resource sharing and difficulty in implementing artificial intelligence applications in the current construction process of smart cities,based on resource description framework of knowledge graph,ontology knowledge system carrier,and digital twins,a knowledge graph model of smart city with data of people as the core was proposed,and a construction method of ontology and sub-ontology in multi-domain knowledge graph supporting the model was also proposed.The idea of “sky,earth and people” model was innovatively proposed,which will play a positive role in how the data of smart city serve urban residents,how to implement artificial intelligence algorithm models and smart city applications.
With the increasing of software scale and software evolution, it is more and more important to construct software project knowledge graph for software maintenance and software development. Automatically constructing software knowledge graph with complex structure and rich semantic relations based on the multi-source heterogeneous mass data such as source code, mailing list, issue report and Q＆amp;amp;A document generated in the process of software project development is a key challenge to be solved urgently in the field of software engineering. A code-centric software knowledge model was proposed, a two-layer plugin framework for knowledge graph construction and software Q＆amp;amp;A was provided, which improves the efficiency of software understanding and software reuse. At present, software project knowledge graph has successfully deployed in the Apache open source community and in the domestic famous enterprises.
Entity relationship extraction technology can automatically extract information from massive unstructured texts to construct large-scale knowledge graph, enrich the content of existing knowledge graph, and provide support for reasoning and application of knowledge graph.Although the cascading entity relation extraction technology has achieved good results, it has some shortcomings in the vector representation of the subject and the decoding of pointer network.In order to solve the representation problem of subject vectors, attention mechanism and mask mechanism were used to generate subject vectors.In addition, to solve the problem that long entities have been decoded in pointer network due to missing label, an entity sequence marker task was introduced to assist pointer network decoding entities.There is a 0.88% improvement over the previous model on the large-scale entity relationship dataset DuIE 2.0.
Temporal knowledge graph (TKG) are obtained by adding the time information of real-world knowledge to classical knowledge graphs.Recently, TKG completion has drawn much attention and become a hot topic in research.Two main methodologies for TKG completion were summarized, one based on symbolic logic whereas and the other based on knowledge representation learning.The pros and cons of these two different methodologies were discussed, highlighting some directions for enhancing TKG completion in future research.Also, seven benchmark datasets for TKG completion and evaluation results of several typical models on the benchmark datasets were introduced.
Knowledge reasoning over knowledge graph aims to discover new knowledge according to the existing knowledge.It is a pivotal technology to realize the human reasoning and decision-making ability of machine.The modern methods of knowledge reasoning over knowledge graph were studied systematically.And the methods based on vector representations with a unified framework were introduced, including the methods based on embedding into Euclidean space and hyperbolic space, and based on deep learning methods such as convolution neural network, capsule network, graph neural network, etc.Simultaneously, the applications of knowledge reasoning in various technical fields and industries were presented, and the existing challenges and opportunities were pointed out as well.
Recently, knowledge graph based question answering has been widely used in many fields such as medical care, finance, and government affairs.Users are no longer satisfied with question answering service of single-hop entity attributes, but want service which can handle complex multi-hop question.In order to accurately and deeply understand multi-hop questions, various types of reasoning methods have been proposed.The latest research methods of multi-hop knowledge graph based question answering were systematically introduced, as well as related datasets and evaluation metrics.These
In recent years, the construction technology of knowledge graphs have been greatly developed, and the constructed knowledge graphs have been applied to many fields.On this basis, the researchers turned their attention from the knowledge graph to the event graph.The event graph takes the event as the core and accurately describes the event information and the relationship between the events.The key technologies of event graphs construction, reasoning and applications were summarized, including event extraction, event information completion, event relationship inference and event prediction.Finally, the specific application scenarios of the event graphs were given, and the future research trends were prospected in view of the challenges existing in the event graph research.
In recent years, knowledge graph has been widely applied to organize data in a uniform way and enhance many tasks that require knowledge.For example, it has been widely used in the field of e-commerce.However, such knowledge services usually include tedious data selection and model design for knowledge infusion, which might bring inappropriate results.Thus, to solve this problem, the method of first pre-training then providing knowledge vector service was put forward, and a pre-trained knowledge graph model (PKGM) was proposed for our billionscale e-commerce product knowledge graph, providing item knowledge services in a uniform way for embeddingbased models without accessing triple data in the knowledge graph.PKGM was tested in three knowledge-related tasks including item classification, same item identification, and recommendation.Experimental results show PKGM successfully improves the performance of each task.
Since the accounting risk events exhibit complexity increasingly and occur frequently, a method merged by industrial knowledge and financial knowledge graph was proposed to recognize and prevent commercial bank's accounting risk more precisely.Based on the financial knowledge graph of account transaction, deep graph connected risk features were extracted via various graph analysis and mining technologies.Combining the graph features with industrial knowledge, 249 single rules and 425 assembled rules were constructed to form a more affluent and flexibly configurable anti-fraud strategy system, which was then applied to verify commercial bank's current accounts and select the high suspicious ones.The experimental results show that the risk recognition accuracy rate of the intelligent strategy is much higher than the traditional one and reaches up to 85% above, which significantly promotes the efficiency of the accounting risk verification.
To solve the issues of simple representations on spectrum situation, much dependence on artificial experience in manual management and low efficiency and accuracy in the current spectrum management, meeting the requirements of automation, precision and real time for future spectrum management, the theory and technology of knowledge graph were introduced into spectrum management.The definition of spectrum knowledge graph, the knowledge schema it depends on and its representation in the form of triples were proposed.The intelligent spectrum management framework based on spectrum knowledge graph, consisting of the graph layer, the equipment layer and the scenario layer, was constructed.Typical applications based on spectrum knowledge graph were discussed, including the recommendation system for spectrum usage, the search engine on spectrum management, and question answering for spectrum management.Experiments demonstrate the spectrum knowledge graph can play a role of guidance by spectrum knowledge in spectrum usage recommendation.
With the continuous iterative updating of Internet technology, the semantic understanding of massive data is becoming more and more important.Knowledge graph is a kind of semantic network that reveals the relationship between entities.Medicine is one of the most widely used vertical fields of knowledge graph.The construction of medical knowledge graph is also a hot research in the field of artificial intelligence at home and abroad.Starting from the ontology construction of medical knowledge graph, named entity recognition, entity relationship extraction, entity alignment, entity linking, knowledge graph storage and application of knowledge graph were reviewed.The difficulties, existing technologies, challenges and future research directions in the process of constructing medical knowledge graph in recent years were introduced.Finally, the application of knowledge graph and the future development direction of medical knowledge graph were discussed.
Aiming at the problem of insufficient research on the knowledge base of distributed denial of service (DDoS) network attacks, a method for constructing a knowledge base of DDoS attacks malicious behavior was proposed.The knowledge base was constructed based on the knowledge graph, and contains two parts: a malicious traffic detection database and a network security knowledge base.The malicious traffic detection database detects and classifies malicious traffic caused by DDoS attacks, the network security knowledge base detects DDoS attacks from traffic characteristics and attack frameworks model malicious behaviors, and perform inference, tracing and feedback on malicious behaviors.On this basis, a distributed knowledge base was built based on the DDoS open threat signaling (DOTS) protocol to realize the functions of data transmission between distributed nodes, DDoS attack defense, and malicious traffic mitigation.The experimental results show that the DDoS attack malicious behavior knowledge base can effectively detect and mitigate the malicious traffic caused by DDoS attacks at multiple gateways, and has the knowledge update and reasoning function between the distributed knowledge bases, showing good scalability.
To solve the difficulty of attack detection caused by the 0day vulnerability, a prediction method of 0day attack path based on cyber defense knowledge graph was proposed.The cyber defense knowledge graph was constructed to refine the discrete security data such as threat, vulnerability and asset into the complete and high-related knowledge format by extracting concepts and entities related to network attack from cyber security ontology research finds and databases.Based on the knowledge integrated by the knowledge graph, assumed and restricted the unknown attributes such as the existence, availability and harmfulness of 0day vulnerabilities, and model the concept of ＆quot;attack＆quot; as a relationship between attacker entities and device entities in the knowledge graph to transform the attack prediction to the link prediction of knowledge graph.According to this, apply path ranking algorithm was applied to mine the potential 0day attack in the target system and construct the 0day attack graph.Predicted the 0day attack path by utilizing the scores output by classifiers as the occurrence probabilities of single step attack and computing the occurrence probabilities of different attack paths.The experimental result shows that with the help of complete knowledge system provided by knowledge graph, the proposed method can reduce the dependence of prediction analysis on expert model and overcome the bad influence of 0day vulnerability to improve the accuracy of 0day attack prediction.And utilizing the characteristic that path ranking algorithm reasons based on the structure of graph can also help to backtrack the reasons of predicting results so as to improve the explainability of predicting.
Collective knowledge graphs refer to knowledge graphs that are managed and maintained in a decentralized or distributed manner through group collaboration.Compared with the existing centrally managed knowledge graph, the collective knowledge graph has the characteristics of knowledge right confirmation, privacy protection, crowd sourcing incentive, and credible traceability.Tring to explore the technical challenges faced by building and applying a collective knowledge graph platform.For meta knowledge transfer, the knowledge incompleteness of a single knowledge graph by knowledge transfer among multiple knowledge graphs from different sources under a decentralized and autonomous framework was considered.The main difficulty was to enhance the respective knowledge graph representation by sharing useful knowledge with each other as much as possible while fully protecting the autonomous ownership of knowledge.For federated graph reasoning, the knowledge graph reasoning in a distributed environment under the privacy-preserving by means of the federated learning mechanism was considered.Meta knowledge transfer focused on transferring entity-independent knowledge between knowledge graphs with overlapped relation set, while federated graph reasoning aimed at learning better entity embeddings for knowledge graphs with overlapped entity set.The model design and experimental validation for each of these two problems were conducted.
Achieving intelligence in industrial control systems is a prevailing trend in recent years, with numerous new technologies and ideas prompted.Knowledge graph is a fundamental resource for artificial intelligence, and domain-specific knowledge graph construction attracts a lot of research attentions.However, knowledge graph construction for control systems is still in the early stage of exploitation.In this paper, structural characteristics and task requirements of process control systems were analyzed.Furthermore, a knowledge graph construction methodology architecture for process control systems was proposed.Firstly, a brief summary on existing related works was given.After that, the characteristics of process industry control systems were analyzed, and the corresponding knowledge graph construction principles and procedures were proposed.Cyber-physical assets management was taken as a case study for detailed explanation.Finally, a prospect for the future research directions of knowledge graph construction for process control systems was made.
Volumn Content
