A system and method for marketing audit analysis based on artificial intelligence
A technology of artificial intelligence and analysis methods, applied in the field of artificial intelligence, can solve the problems of low efficiency of manual screening of audit data, inflexible marketing audit rules, and low accuracy, so as to achieve precise risk control, reduce manual workload, and improve accuracy high effect
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0044] Such as figure 1 As shown, this embodiment provides a system for marketing audit analysis based on artificial intelligence.
[0045] The system includes a big data platform, an AI model and an artificial intelligence-based customer volume fee business risk analysis system;
[0046] The AI model includes a data preprocessing module, an input graph processing module and a graph convolutional network;
[0047] The data preprocessing module uses the CA knowledge graph to construct the adjacency matrix structure, and the input graph module labels the certain points in the graph;
[0048] Graph convolutional network includes SVM / SOFTMAX classifier, self-developed graph convolutional layer, and optimization module;
[0049] The artificial intelligence-based customer volume fee business risk analysis system includes a preprocessing layer, a neural network layer and a view layer;
[0050] The functions of the preprocessing layer include knowledge graph construction and inpu...
Embodiment 2
[0054] This embodiment provides a method for marketing audit analysis based on artificial intelligence.
[0055] Such as figure 2 As shown, the method includes the following steps:
[0056] S1: Sorting out the original "quantity fee" business audit related data, establishing a complete "quantity fee" audit business semantic system, using the above semantic system to build a knowledge graph based on the CA model (Core-Attachment), and setting demand adaptive rules / parameter pairs The user points are connected to generate an adjacency matrix input graph to ensure the versatility of the model;
[0057] S2: By building a graph model with a multi-level structure, the relationship between different objects is established on the basis of considering the primary and secondary levels, and the correlation between objects is more accurately measured;
[0058] S3: Using a convolutional neural network-based representation learning algorithm to implement a convolutional neural network en...
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, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com