Learned-Model Vocabulary Test Generation From Search Histories

Solution Overview

Problem

Existing electronic dictionaries lack an effective mechanism to create personalized and contextually relevant test questions based on user search histories, limiting their ability to enhance vocabulary learning effectively.

Innovation Solution

An information processing apparatus and method that utilizes a learned model, such as a recurrent neural network (RNN), to analyze user search histories and generate test questions by predicting correlations between character strings, allowing for the creation of contextually relevant vocabulary exercises.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If a learned model is used to analyze user search histories and generate test questions, then the personalization and contextual relevance of vocabulary exercises are improved, but the device complexity increases

Engineering Contradiction:

Improvepersonalization of test questionsVSAvoidcomplexity of information processing apparatus

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system performs preliminary learning of user search history patterns before actual test generation. The learned model is trained in advance on aggregated search history data to establish correlation relationships between character strings, so that when a user's search history is input, the model can quickly generate personalized test questions without requiring complex real-time processing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent introduces a learned model as an intermediary component between the user's search history input and the test question generation. This model acts as a mediator that has pre-learned correlation patterns, simplifying the overall system architecture by encapsulating the complex analysis logic within the model rather than requiring complex rule-based processing throughout the system.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Productivity

If test questions are generated based on user search histories, then user engagement and vocabulary learning effectiveness are improved, but the loss of time for processing and generating questions increases

Engineering Contradiction:

Improvevocabulary learning effectivenessVSAvoidtime for generating test questions

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary learning of user search history patterns before actual test generation. The learned model is trained in advance on aggregated search history data to establish correlation relationships between character strings, so that when a user's search history is input, the model can quickly generate personalized test questions without requiring complex real-time processing.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces traditional mechanical rule-based question generation with a learned model that automatically identifies patterns and correlations in search history data. This substitution enables faster processing by leveraging the model's pre-learned knowledge rather than requiring step-by-step rule evaluation, significantly reducing the time required to generate personalized test questions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS12411892B2Information processing apparatus, information processing method, and recording medium

Publication Date: 2025.09.09 CASIO COMPUTER CO LTD

AI summary

An information processing apparatus includes a memory and at least one processor. The memory stores a learned model having learned correlation between character strings included in a search history of words and/or phrases. The processor inputs information of a search history of words and/or phrases by a target user to the learned model. The processor creates a word and/or a phrase for learning by the target user.