Information Pushing System Using Neural Network Models

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing methods for pushing information to users are not personalized, as they provide all information to all users without considering individual user preferences or interests, leading to irrelevant content being displayed.

Innovation Solution

A method and apparatus that determine target information based on user information and object information using a pre-established information determination model, such as an artificial neural network or deep learning model, to represent corresponding relationships and push relevant information to the user's terminal.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If all information is provided to all users without personalization, then the completeness of information coverage is improved, but the relevance of content to individual users deteriorates

Engineering Contradiction:
Improveinformation coverageVSAvoidcontent relevance
Core Design Contradiction:
Quantity of substanceVSManufacturing precision

Solution Approach 1:

The patent segments information push services into two distinct modes: a first mode that provides comprehensive information coverage to all users, and a second mode that delivers personalized content based on user profiles and preferences. This segmentation allows the system to simultaneously achieve complete information coverage and high content relevance by directing different users to appropriate modes based on their individual characteristics

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by customizing information content according to specific user characteristics. User profiles store individual preferences, behavior patterns, and interest tags, allowing the system to tailor information delivery to each user's local needs and preferences rather than applying a uniform approach to all users

Inventive Principle:
Principle #3Local quality

2Manufacturing precision

If personalized information pushing is implemented using machine learning models, then the relevance of content to users is improved, but the system complexity deteriorates

Engineering Contradiction:
Improvecontent relevanceVSAvoidsystem complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent implements preliminary action by pre-establishing user profiles that store user information, preferences, and behavior patterns before actual information pushing occurs. The system pre-processes user data and creates structured profiles that can be quickly queried and matched with information content, avoiding the need for complex real-time analysis during information delivery

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces user profiles as an intermediary layer between the information source and the user. These profiles act as a mediator that stores and organizes user characteristics, enabling the system to match information with users without requiring direct complex interactions between the information pushing mechanism and user preferences

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentUS11962662B2Method and apparatus for pushing information
Publication Date: 2024.04.16 BEIJING WODONG TIANJUN INFORMATION TECH CO LTD
  • US11962662B2 patent drawing
  • US11962662B2 patent drawing
  • US11962662B2 patent drawing

AI summary

Embodiments of the present application disclose a method and an apparatus for pushing information. One embodiment of the method comprises: in response to the receipt of an information push request sent by a user by means of a terminal, determining object information about at least one object associated with user information included in the information push request; determining target push information according to the user information, the object information, and a pre-established information determination model, the information determination model being used for characterizing a correlation between user information, object information, and target push information; and pushing the target push information to the terminal for the user to view by means of the terminal.