Short message auditing system and method, and method for constructing short message auditing model

Abstract

The invention provides a short message auditing system and method, and a method for constructing a short message auditing model. The auditing system includes a URL detection module, an error correction matching module, a URL blacklist and white list module, a URL content module, a real-time capture module, an auditing model, a model training module and a background management module. The auditingmethod comprises the following steps: capturing the URL in a short message by using the crawler technology in real time, modeling by combining the contents of the short message with webpage contents,and classifying the properties of to-be-audited short message contents via a machine learning algorithm, and finally determining to release or intercept the short message. Compared with the traditional auditing method according to the short message contents and the URL, the auditing method has the advantages of greatly improving the accuracy, shortening the URL by short URL service during the auditing, an performing personalized auditing according to different URL after skipping instead of single manner just like that in the traditional manner.

Description

Technical field [0001] The present invention relates to the field of information review, and in particular to a short message review system and method and a method for constructing a short message review model, that is, a review system and method for including jumpable information such as URL links in a piece of information, and a method for constructing a short message review model . Background technique [0002] In recent years, the number of users of smart mobile phones in my country has grown at an unimaginable rate, and some essential characteristics of smart phones have caused huge changes in people’s habits. For example, when using non-smart phones before, if business users need Sending a website address to a personal mobile phone for users to click to open it can only use WAPPUSH technology. If SMS technology is used, the user who receives the text message can only copy the link address to the browser and open it. [0003] Due to WAP PUSH's own habits and device support, al...

AI Technical Summary

Problems solved by technology

[0006] 2. Send the activity address in the member marketing SMS, such as: Dear XXXX users, the 2017 GL82.0T Automatic Deluxe Edition is not yet on the market, and the official guide price has not yet been announced

[0009] The above are just some typical applications. In fact, there are more and more SMS applications with URLs, and the content is also varied. With the popularity of this application, it also brings a severe test to the current information review management: due to the existence of URLs Certain concealment, the webpage address pointed behind the specific URL cannot be known in the content of the SMS, and even due to the character limit of the SMS, most of the URLs appearing in the SMS are short addresses, which are shortened by professional short URL services Yes, and even if the content is the same, the URL sent in each text message can be different, such as t.cn in the example, resulting in the inability to check the URL address library

These problems have brought difficulties to information review, resulting in a greatly increased risk of information review

[0010] In the traditional information review method, the URL or part of the information in the URL is often put into the address library, and when the text message content includes the information in the URL address library, it will be released or blocked according to the results recorded in the library, but This audit method is almost impossible to work properly due to the emergence of short URL services, such as the short URLs such as http: / / t.cn / ZtG0V2G and http: / / 2bai.co / 969644 in the above example, The domain name itself does not have characteristic elements, and the latter part is randomly generated, so in the traditional information review system, these short messages are either all intercepted or all are released, and finally the URL review module is useless

[0011] Another most stupid method is that the SMS gateway with a manual review module will send the SMS containing URL keywords to the letter review personnel for manual review. The way to achieve it requires a lot of manpower and material resources, and at the same time greatly increases the delay of SMS messages and increases the company's operating costs

Images