Topic-Based Book Recommendation for Faster E-Reading Discovery

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

In e-reading platforms, users face inefficiency in finding books of interest beyond their current selection, as they can only preview book descriptions or contents, leading to a low efficiency in discovering relevant books.

Innovation Solution

A topic recommendation method that determines a target book based on preset display conditions, acquires a matching target recommended topic, and displays recommended books and topics to enhance the discovery of books of interest.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If users preview book descriptions or contents to find books of interest, then they can discover relevant books, but the efficiency of finding books is low

Engineering Contradiction:
Improveefficiency of finding booksVSAvoidtime spent previewing books
Core Design Contradiction:
ProductivityVSLoss of time

Solution Approach 1:

The patent introduces a topic recommendation system as an intermediary between users and books. Instead of directly browsing book descriptions, users receive topic-based recommendations that guide them to relevant books. The system extracts topics from book content and matches them with user preferences, serving as a mediator that accelerates the book discovery process without requiring extensive previewing

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The system performs preliminary analysis of book content to extract topics and characteristics before users need to search. By pre-processing book data and organizing it by topics, the system prepares recommendation information in advance, allowing users to quickly find relevant books without having to manually preview multiple book descriptions

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If the system provides detailed book information for recommendation, then recommendation accuracy improves, but information processing complexity increases

Engineering Contradiction:
Improverecommendation accuracyVSAvoidinformation processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments book information into distinct topics rather than processing entire book descriptions as single units. By dividing content into discrete topical elements, the system can efficiently match user preferences with relevant book topics without processing all book information in detail, thereby maintaining recommendation accuracy while reducing processing complexity

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system extracts key topics from book content, separating essential recommendation information from redundant details. By taking out only the relevant topic elements needed for matching user preferences, the system achieves accurate recommendations while minimizing the amount of information that needs to be processed and stored

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS12505139B2Topic recommendation method, computer device, and storage medium
Publication Date: 2025.12.23 DOUYIN VISION CO LTD
  • US12505139B2 patent drawing
  • US12505139B2 patent drawing
  • US12505139B2 patent drawing

AI summary

The present disclosure provides a topic recommendation method and apparatus, a computer device, and a storage medium, and the method includes: in response to satisfying a preset display condition, determining a target book to be displayed under the preset display condition; acquiring a target recommended topic matching the target book; and displaying recommended books and the target recommended topic according to a display manner matching the preset display condition, in which the recommended books at least include the target book.