Digital financial service pushing method and system based on artificial intelligence

Through real-time data collection through multi-channel, deep neural networks are constructed, and financial product feature vectors are generated through natural language processing. The collaborative filtering and matching method is used to solve the problems of inaccurate user portraits and poor recommendation results, and more accurate user demand capture and personalized recommendations are achieved.

CN120146961AInactive Publication Date: 2025-06-13SOUTH CHINA UNIV OF TECH
View PDF 6 Cites 1 Cited by

Patent Information

Application Number
CN202510272597.3
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-10
Publication Date
2025-06-13
Estimated Expiration
Not applicable · inactive patent

Smart Images

  • Figure CN120146961A_ABST
    Figure CN120146961A_ABST
Patent Text Reader

Abstract

The invention discloses a digital financial service pushing method and system based on artificial intelligence, and relates to the field of artificial intelligence and financial science and technology, and the method comprises the steps: collecting user multi-source data and financial product text data in real time through multiple channels, carrying out the preprocessing, and generating a user multi-source data set and a standardized word set of the financial product text data; constructing a user portrait model by using a machine learning algorithm, inputting the user multi-source data set into the user portrait model, and generating a user portrait vector; processing the normalized word set of the financial product text data through a natural language processing model BERT to generate a feature vector of the financial product; the multi-source data of the user and the financial product text data are collected in real time through multiple channels and preprocessed, comprehensiveness, accuracy and integrity of the data are ensured, the user portrait model is constructed through the deep neural network DNN, user requirements and behavior characteristics can be accurately captured, and therefore the precision of a recommendation system is improved.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Video recommendation method and device

    CN110717069A

  • Natural language processing method and system based on machine learning

    CN117493491A

  • Product recommendation method and device, computer equipment and storage medium

    CN117557331A

  • Method for constructing intelligent recommendation platform based on artificial intelligence portrait system

    CN119106184A

  • Financial information recommendation method and system based on multi-channel distribution

    CN119149827A

Cited By

  • Urban merchant access cloud platform information management method and device, and medium

    CN121544349A