Keyword discovery method and system based on information monitoring and electronic equipment

Abstract

The invention discloses a keyword discovery method and system based on information monitoring and electronic equipment. The method comprises the following steps: monitoring, scheduling and setting a monitoring task, and setting a timing task and related task parameters, wherein the monitoring target obtaining includes obtaining the first N search results of the monitoring vocabulary in the searchengine set by the task after reaching the task monitoring time point, and removing duplication according to a result domain name; the monitoring content collection is to obtain the content of a website under a specified domain name and the content of a website externally linked with the website by using a crawler; the content analysis processing comprises the steps of performing word segmentationon the website content, and establishing a word set; processing vocabularies in the word set by using a keyword recommendation algorithm to obtain a recommendation result; and displaying the recommendation result to auditors through manual auditing. According to the method, the keyword list can be automatically generated, the new keywords are found according to the latest development trend of thecurrent bad information, the original method of manually collecting and inputting the keywords is replaced, and the website content monitoring efficiency and accuracy are effectively improved.

Description

technical field [0001] The invention relates to the technical field of self-information identification, in particular to a keyword discovery method, system and electronic equipment based on information monitoring. Background technique [0002] The virtual online world is equal to the real world. In the real world, there are beauty and ugliness, good and evil, and in the online world there are also beauty and ugliness, good and evil. In the era when the Internet was just emerging, people went online mainly to search for materials and information, and bad information was still very limited at that time. However, with the continuous development of the Internet, people began to pursue entertainment, find business opportunities, and read news on the Internet. At this time, bad information began to gradually spread. In recent years, bad information has even developed into an industry, and has begun to transform from purely "knowledge-based" information to "profit-seeking" informa...

AI Technical Summary

Problems solved by technology

[0004] 1) The list of keywords used to monitor the content of the website still needs to be manually collected and input by the user, which is low in work efficiency and consumes a lot of human resources

Moreover, manual review also has the risk of misjudgment and misoperation;

[0005] 2) The scope of keywords is limited, and the keyword list cannot be updated in time according to the current development trend of bad information. The amount of information is insufficient, resulting in low detection accuracy of the system

Images