Evaluation information generation method and device

Abstract

The embodiment of the invention provides an evaluation information generation method and device. The evaluation information generation method includes the steps that comment data of information points are captured; user individual information associated with the information points are obtained; short comment sentences matched with the category of the user individual information is split in the comment data according to the preset rule; the short comment sentences are combined into natural language, and evaluation information is generated. By means of the evaluation information generation method and device, the defect that through an existing method, evaluation information formed by independent labels is obtained is overcome, and the readability of the evaluation information is improved by generating the natural language including the evaluation information; furthermore, by combining the user individual information, a great amount of information unconcerned by users can be shielded for the users, the evaluation information required by the users can be provided directly, the evaluation information is made to be more simple and direct, interference information is reduced, and meanwhile, the cost of obtaining the required information is lowered for the users.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to an evaluation information generation method and an evaluation information generation device. Background technique [0002] At present, with the rapid development of Internet technology, people can easily check the evaluation information of a Point of Interest (POI) such as tourist attractions, hotels, restaurants, etc. through the Internet. [0003] The existing POI evaluation information generation method can be as follows: first, capture the comment data on POI on the Internet (including online travel websites, social media, review websites, travel notes, etc.), and then preprocess the comment data, including extracting its structure Information (such as scoring, submission time, submitter information, specific evaluation content, etc.); and then extract the semantic points of the preprocessed comment data, that is, the comment words and count the word fr...

AI Technical Summary

Problems solved by technology

[0004] However, the evaluation information generated according to the above method is an independent Tag label, for example, the room is clean (ratio: 70%, word frequency: 10), sound insulation is poor (ratio: 80%, word frequency: 8), the room is large (ratio: 60%, word frequency: 5), small bathroom (ratio: 70%, word frequency: 3), etc., lack of readability, and cannot directly provide the evaluation information required by users

Images