Rumor recognition method
A method for identifying rumors and a technology for rumors, applied in the fields of the Internet and artificial intelligence, can solve problems such as inability to identify rumors, achieve the advantages of strong timeliness, reduce computational complexity, and improve the degree of adaptation.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0066] Example two
[0067] Reference image 3 As shown, there are still some shortcomings in judging the text to be tested by the rumor discrimination model alone. In this embodiment, a user classification and weighting system is introduced, which is essentially based on users with specific marks (users of a certain level in a certain field). "Text to be tested" is scored for rumor determination.
[0068] The users in the user classification and weighting system include initial users and non-initial users.
[0069] (1) User classification initialization
[0070] New users can choose whether they are willing to become volunteers and select areas of interest or expertise through a simple process. This part of the selection is used as the initial classification of the user, and the initial weight of the user is 0.
[0071] (2) Initialize user weight adjustment
[0072] Because there may be differences between the user's self-assessment and the objective facts, we need to evaluate the use...
Example Embodiment
[0082] Example three
[0083] The rumor recognition feedback model based on human-computer collaboration uses the "user weighted judgment" as the standard to compare the scores of the "rumor discrimination model", save the wrong annotation data, and iterate into the model.
[0084] In this embodiment, the user accesses the rumor discrimination model in two ways. One is to access the API interface and call the predict function shown in the "model effect test" code in the rumor discrimination model (5). The content of the evaluation is input as a variable; the other is through the test page, and the text to be tested is input into the page.
[0085] After collecting the rumor text to be tested entered by the user, it can be a link or text data, and then the prediction function in the rumor judgment model is also called to obtain the judgment result. At the same time, both the pre-evaluation result and the text content are recorded in the database.
[0086] After the text is classified i...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap