Type extraction system and method for professional document knowledge entity

Abstract

The invention discloses a type extracting system for a professional literature intellectual entity. The system comprises a user inquiring and feedback interface, an online crawler and management module, an intellectual entity identification module, an intellectual entity type extracting module, a type label propagation and index database establishment module, an intellectual entity type relational graph model establishment module, and a data visualization module. The system provided by the invention can be used for extracting the type of the entity according to key words of the entity searched by a user, and presenting a type relation and a hierarchical relation between intellectual entities and a timing sequence evolution mode in a visualization manner. Furthermore, the invention further provides a type extracting method for the professional literature intellectual entity. With the adoption of the method disclosed by the invention, type label extraction can be effectively carried out on the intellectual entities in professional fields; the problem of limitation and subjectivity in manual type predefinition can be solved; and the structured realization of a professional knowledge network is easily realized.

Description

technical field [0001] The invention relates to the field of text mining and information extraction, in particular to a type extraction system and extraction method for professional document knowledge entities. Background technique [0002] With the rapid popularization of the Internet and the development of hardware storage technology, people can easily browse and obtain various digital resources on different devices, and can also obtain the required professional literature through numerous academic databases or academic search engines , such as Google Scholar, Baidu Academic, Cnki, Wanfang Data, etc.. From this point of view, obtaining massive electronic resources from the Internet has indeed become an easy and simple matter, but the problem that arises is that the existing knowledge services can no longer meet people's needs for "fast, simple and accurate" information. need. In the face of such knowledge service needs, we need to perform entity recognition for such prof...

AI Technical Summary

Problems solved by technology

Among them, Google knowledge graph regards the user's search object as an entity, rather than simply keyword matching search, which can effectively obtain some attributes and specific information related to the entity; Google Trends analyzes the user's search records and obtains The hot trend of some keywords; the domestic "synonym Cilin" uses Internet data to mine the hyponymy relationship of entities to obtain the hyponymy relationship of most entities, but it lacks special professional literature knowledge entities. The knowledge context retrieval of Wanfang Data is to correlate the keywords of the documents according to the relationship between the relevant documents and the reference documents, and then display the words most relevant to the user's search terms in a certain period of time in a chronological order

[0004] The existing type extraction technology mainly has the following deficiencies: A) types need to be manually pre-defined, with limitations; B) a large amount of manual annotation is required, which is time-consuming and labor-intensive; C) type extraction for professional fields is still Most of the commonly used entity information extraction methods are not applicable in the professional field; D) Lack of intuitive and visual tree diagram visualization demonstration, most systems are still based on text and data presentation

Images