Hot topic detection method and device

Abstract

The invention relates to the technical field of computers, in particular to a hot topic detection method. The hot topic detection method comprises the following steps: extracting a key sentence of a target text as an abstract of the target text based on a preset entity knowledge base; Calculating a document fingerprint of the abstract by using an LSH algorithm; And performing clustering analysis on the document fingerprint based on a KNN algorithm to determine the topic category of the target text. According to the hot topic detection method, sentences of a target text are evaluated on the basis of entities in an entity knowledge base; According to the method, the target text key sentence is extracted as the abstract according to the evaluation result, so that the extracted abstract can betightly combined with the specific application scene, more topic information can be reserved, the precision of subsequent document clustering can be ensured, and a high-quality topic detection function can be realized.

Description

technical field [0001] The invention relates to the field of computer technology, in particular to a hot topic detection method and device. Background technique [0002] With the rapid development of the Internet, the Internet has become the most important source of information in people's work and life, which greatly meets people's needs for the latest information acquisition. However, the growth of information on the Internet is too rapid, and the so-called "information explosion" has appeared. At this time, for users, it will take a lot of time to screen and sort out all kinds of information. Moreover, due to the serious "fragmentation" of Internet information, it is difficult to form an effective knowledge system, which is not conducive to information analysis and monitoring. [0003] In view of the above problems, at this stage, the hot topic detection method is usually used to organize the fragmented information flow into a document set with topics as units. Lay a go...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the above problems in the prior art, that is, the existing hot topic detection method contains less topic information due to the extracted document features and cannot be combined with specific application scenarios, resulting in insufficient subsequent clustering accuracy.

Images