Method for identifying financial advertisements in text advertisements
An advertising and financial technology, applied in the field of advertising recognition, can solve the problem that the advertising analysis model cannot effectively identify financial advertisements, and achieve the effects of preventing over-fitting, improving accuracy, and good classification effects
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Example Embodiment
[0022] Example 1: Such as figure 1 What is shown is a schematic diagram of the overall functional structure of this embodiment. The method for identifying financial advertisements in text advertisements disclosed in this embodiment includes the following steps:
[0023] (1) Obtain the crawled advertisement text data from the database; the advertisement text data mainly comes from search engines, Baidu Post Bar, financial portals, news portals and other sites.
[0024] (2) Preprocess the text data, perform word segmentation and remove useless information, so that the text can better represent semantic information. The data preprocessing mainly includes the following steps:
[0025] i. Word segmentation: In Chinese, a word is the smallest unit that constitutes a language, and it is the smallest unit with semantics, and a word cannot better represent the semantic information it carries. Therefore, it is necessary to convert the uninterrupted text data into continuous phrases;
[0026] i...
Example Embodiment
[0040] Example 2:
[0041] This embodiment takes the identification of financial advertisements in text advertisements in Baidu search engine as an example to describe technical solutions and steps. A method for identifying financial advertisements in text advertisements in Baidu search engine includes the following steps:
[0042] Step 1: Get 1000 advertisement texts of Baidu search engine that have been crawled from the database, and the ratio of training set to test set is 3:1;
[0043] Step 2: Use the jieba word segmentation tool to segment the text content of the training set:
[0044] jiaba word segmentation tool: is a python package for natural language processing, which can be downloaded and used directly through pip.
[0045] Step 3: Filter the phrase obtained after the word segmentation in step 2 through the stop vocabulary list published by the Harbin Engineering Natural Language Processing Laboratory, and remove the words in the stop word list. https: / / github.com / goto456 / st...
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