The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Nowadays, with the massive demand for sports news, automatic generation systems based on the template technology has been deployed, which could generate massive sports news quickly and effectively. However, by using one simple template for one scenario, the pattern of text generated by such system is single. In this paper, we propose an automatic generation method based on knowledge rules to select...
In this paper, we do a research on the keyword extraction method of news articles. We build a candidate keywords graph model based on the basic idea of TextRank, use Word2Vec to calculate the similarity between words as transition probability of nodes' weight, calculate the word score by iterative method and pick the top N of the candidate keywords as the final results. Experimental results show that...
Nowadays, with the rapid economic development, the amount of social information is also going up. Facing the daily explosive growth of the news quantity, the audience can difficultly get important information. To this end, the paper puts forward a method of Chinese news event extraction based on subject elements, which mixes the study of news topic sentence extraction and the research of event extraction...
With the rapid development of Internet, text categorization becomes a mission-critical technology that organizes and processes large amounts of data in document. Deep belief networks have powerful abilities of learning and can extract highly distinguishable features from the high-dimensional original feature space. So a new Chinese text categorization algorithm based on deep learning structure and...
Feature dimension reduction is an important part in text categorization, and it even becomes more important for child classification in hierarchical text classification. It is presented that Chinese text feature selection method based on category distinction and feature location information in this paper. Experimental results show that the proposed method has a higher precision and recall rate than...
In recent years, text categorization based on machine learning is a widely used technology in the field of natural language processing and text mining and has gained many advances. Feature selection is one of the key problems in text categorization. The chief obstacles to feature selection are noise and sparseness. In this paper, we propose an approach of Chinese text feature selection based on CV...
Information push has become a key technology in the age of new media, which is especially important in organizations of news gathering and pressing. This paper first introduced the cloud push technology, and then analyzed the demand for comprehensive information push in current news media, stated the significance of the push system. The push system was designed and implemented finally.
With the rapid development of the Internet, text messages on the network is also an exponential growth. Facing the vast network of information, how to quickly and efficiently identify the different sites of similar news-text plays a major role in strengthening the integrated management of network information. Existing text similarity algorithm has many disadvantages when used in Chinese news-texts,...
Shot boundary detection (SBD) is the first step in video management and retrieval system. Existing SBD techniques, however, are mostly based on original frame histograms, which process too much data and are sensitive to flashes and small motions. Furthermore, they mainly perform boundary detection between each two frames, which are unreliable when there appear noises. To address these problems, we...
Social tagging has been widely used in Web2.0 applications. The main purpose of it is to organize and utilize digital resources effectively. This article introduces an optimized tagging recommendation model. It can be divided into four layers which are respectively based on essential data, character analysis, semantic data mining and user advanced behavior analysis. This model can provide flexible...
As a conception modeling tool, ontology can describe the information system in the semantic and the knowledge level, it can also express the relations of concepts, the inheritance hierarchy of concepts, potential relationships and axioms precisely, and so on. Meanwhile, it provides a solution for many problems of massive information caused by the rapid development of the Internet, such as how to organize,...
Web content extraction is actually the process of transforming web unstructured information into structured information. Knowledge base has the advantages of ordering information and knowledge, also be used conveniently. So it's convenient to retrieve information and knowledge, and it makes base for effective use. Knowledge base will speed up the knowledge and the flow of information and make for...
This paper proposes a solution to manage copyright information of TV program. We design a three-dimensional model to describe the complete program copyright information. And then we introduce a Copyright Information Management System in detail, named CIMS, which works well in CCTV-7 for more than one year and plays an important role in the whole process of program production, storage and exploitation.
This paper introduces a DRM system for electronic document publication. Through merging the process of encryption and authentication, and the system can prevent from attacking through reverse engineering to a certain degree. In this system, a part of the encryption key is dynamically generated during the authentication process. So every client will obtain a deferent encrypted data when requesting...
In view of the lack of security and management mechanism in peer to peer (P2P) network, this paper designs an operational and scalable intelligent node overlay network which is P2P-oriented with digital right management functionality and good authentication and accounting capabilities supporting large-scale deployment. It not only can convenience the network communication and make the share and interact...
In order to use the multimedia sources efficiently, finding the semantic content behind the resources and analyzing them, a framework to uniformly describe multimedia resources is used in this paper by using the theory of ontology. Based on fifteen elementary metadata of Dublin Core Metadata Element Set, the notion of the Basic Metadata and Expand Metadata are defined to realize the unify description...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.