Information Processing with Keyword-Guided Auxiliary Data Selection

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing techniques struggle to generate accurate response data due to the lack of auxiliary information when a first keyword is not included in a predetermined data set, leading to inaccurate results.

Innovation Solution

An information processing apparatus and method that includes a determination unit to identify the need for auxiliary information and an auxiliary information acquisition unit to extract and select relevant data from a subset based on input data and user feedback, enhancing the accuracy of response data generation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If a first keyword extracted from input data is not included in a predetermined data set, then the system cannot generate accurate response data, but adding all possible keywords to the data set increases device complexity

Engineering Contradiction:
Improveaccuracy of response dataVSAvoidcomplexity of data set
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent performs preliminary action by extracting multiple pieces of data corresponding to the first keyword from the data set before selecting auxiliary information. This pre-extraction and preparation of candidate data enables the system to handle keywords not directly in the data set, improving response accuracy without requiring all possible keywords to be pre-loaded into the data set.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces an intermediary mechanism by selecting one or more pieces of data from the extracted multiple pieces as auxiliary information based on the input data. This auxiliary information acts as a mediator between the input data and the response generation process, enabling accurate responses for keywords not directly present in the data set while maintaining a manageable data set size.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Measurement precision

If auxiliary information is selected based on user feedback information, then the accuracy of response data is improved, but the processing time and complexity increase

Engineering Contradiction:
Improveaccuracy of response dataVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements feedback by extracting a second keyword from user feedback information and using it to refine the selection of auxiliary information. The system generates prompt information based on the input data and the second keyword, then selects auxiliary information that aligns with user feedback. This feedback mechanism improves response accuracy by incorporating user preferences and corrections.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent applies partial action by selectively processing only the necessary portions of user feedback information. Instead of processing all feedback data comprehensively, the system extracts the second keyword and uses it to guide auxiliary information selection, achieving improved accuracy with reduced processing overhead compared to comprehensive feedback analysis.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP4617906A1Information processing apparatus, information processing method, and computer-readable storage medium
Publication Date: 2025.09.17 FUJITSU LTD
  • EP4617906A1 patent drawingFigure 1
  • EP4617906A1 patent drawingFigure 2
  • EP4617906A1 patent drawingFigure 3A~3B

AI summary

Disclosed are an information processing apparatus, an information processing method and a computer-readable storage medium. The information processing apparatus may include: a determination unit, configured to determine that auxiliary information for input data is required, in a case where a first keyword extracted from the input data is not included in a first subset corresponding to the first keyword in a predetermined data set; and an auxiliary information acquisition unit, configured to, in a case where the determination unit determines that the auxiliary information is required, extract, from the first subset, multiple pieces of data corresponding to the first keyword, and select, based on the input data, one or more pieces of data from the extracted multiple pieces of data, as the auxiliary information for generating response data.