Personalized Book Generation via Reading History Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional book-making methods fail to effectively utilize personalized information from children, limiting their interest in reading by not tailoring content to their specific interests, and are time-consuming in offline services.
Innovation Solution
A system and method that analyze a user's reading history to generate personalized books with customized content and illustrations, using a service server that collects, analyzes, and processes reading data to create books with varying difficulty levels and vocabulary, allowing users to edit and add illustrations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional book making applies information about a child to existing stories and illustrations, then the book making process is simple, but it fails to properly utilize personalized information such as interested matters of children, showing limitations in increasing interest in reading
Solution Approach 1:
The system segments the book-making process into distinct functional modules: a reading history collection module that gathers data from multiple sources (online reading records, offline reading logs, surveys), a reading history analysis module that processes the collected data to identify interested matters, and a book generation module that creates personalized content. This segmentation allows complex personalization to be achieved through coordinated simple modules, resolving the contradiction between personalization capability and system complexity.
Solution Approach 2:
The system introduces a reading history analysis module as an intermediary between data collection and book generation. This intermediary processes raw reading history data to extract meaningful interested matters, then passes structured information to the book generation module. This intermediary layer enables sophisticated personalization while keeping the overall system architecture manageable and modular.
2Productivity
If offline reading service produces personalized book contents by synthesizing user's name and photo with set template, then some personalization is achieved, but the contents that can be produced is limited and a lot of time is required to produce the contents
Solution Approach 1:
The system enables automated self-service book generation by collecting reading history data automatically from multiple sources (online reading platforms, offline reading logs, survey results) without manual intervention. The reading history analysis module automatically processes this data to identify interested matters, and the book generation module automatically creates personalized content based on these insights. This automation dramatically improves productivity while maintaining high content variety, eliminating the time-consuming manual template synthesis of conventional methods.
Solution Approach 2:
The system changes the fundamental parameters of book generation from fixed template-based synthesis to dynamic content creation based on analyzed reading history. Instead of merely inserting user name and photo into predetermined templates, the system generates story content, selects illustrations, and structures the book based on the user's identified interested matters. This parameter change enables both high productivity through automation and high content variety through data-driven personalization.
3Loss of information
If reading history is collected from multiple sources including online reading records, offline reading logs, and survey results, then comprehensive personalized information is obtained, but the data collection and processing becomes more complex
Solution Approach 1:
The reading history collection module is designed with multi-functionality to gather data from diverse sources (online reading records from multiple platforms, offline reading logs from various devices, survey results from different formats) through a unified interface. This universal collection capability obtains comprehensive personalized information while maintaining a single, manageable data collection system that handles all sources consistently, resolving the contradiction between information completeness and system complexity.
Data Source
AI summary
This disclosure presents a system and a method for providing a personalized book in which an interested matter is analyzed based on reading history, and a personalized book is generated which includes personalized contents and illustrations based on the interested matter. The presented system for providing a personalized book includes a reading history database which stores a reading history associating a user identifier and a book identifier with each other, a book information database which stores book information including a book identifier, text data, and image data, and a service server configured to deduce an interested matter of a user based on the reading history of the user stored in the reading history database in response to a personalized book generation request from a user terminal, and to generate a personalized book based on the interested matter and the book information stored in the book information database.