Abstract Generation Apparatus for ICT Service SDG Contribution Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The causal relationship between ICT services and the Sustainable Development Goals (SDGs) is difficult to clarify using keyword extraction methods, making it challenging to determine the specific goal that an ICT service contributes to, as the meaning of the targets is not easily grasped.
Innovation Solution
A summary generation device that extracts feature information from ICT services and SDG targets, calculates similarity, and generates summaries through cluster analysis to reflect the causal relationship, facilitating decision-making on the contribution of ICT services to SDGs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If keyword extraction method is used to summarize SDG targets, then the summarization process is simple, but the causal relationship between ICT services and SDG goals cannot be clarified
Solution Approach 1:
The patent segments the summarization process into multiple stages: first extracting keywords from SDG targets, then extracting components related to those keywords from ICT service descriptions, and finally generating summaries that preserve causal relationships. This segmentation allows the system to maintain both simplicity and information completeness.
Solution Approach 2:
The patent introduces an intermediary component extraction stage that acts as a mediator between keyword extraction and final summarization. This intermediary process identifies and preserves causal relationship components, ensuring that the transition from simple keywords to meaningful summaries does not lose critical information about how ICT services contribute to SDG goals.
2Measurement precision
If dependency analysis summarization is used, then some target components are extracted, but the meaning of the sentence and contribution of ICT service cannot be grasped easily
Solution Approach 1:
The patent merges dependency analysis with component extraction by integrating both approaches. The system not only extracts target components through dependency analysis but also extracts additional components from ICT service descriptions that are related to those targets, combining the strengths of both methods to produce summaries that are both precise and easy to understand.
Solution Approach 2:
The patent adds another dimension to the summarization process by extracting components from both the SDG target side and the ICT service description side. This dual-dimensional approach ensures that summaries capture not only the target components but also the specific ways ICT services contribute to achieving those targets, making the meaning and contribution easily graspable.
3Loss of information
If cluster analysis is performed on all target components, then comprehensive summarization is achieved, but processing complexity and time increase
Solution Approach 1:
The patent extracts only the necessary components for summarization by first identifying keywords from SDG targets and then selectively extracting components related to those keywords from ICT service descriptions. This extraction approach avoids the need to perform cluster analysis on all possible target components, significantly reducing processing time while maintaining summarization completeness.
Solution Approach 2:
The patent applies partial action by performing cluster analysis only on the extracted components that are directly related to SDG targets, rather than analyzing all possible components. This partial analysis approach achieves comprehensive summarization for the relevant aspects while avoiding the excessive processing time that would result from analyzing all target components in full detail.
Data Source
AI summary
A summary generation unit includes a processor and a memory storing program instructions that cause the processor to: extract, based on components of text data regarding an Information and Communication Technology (ICT) service, one or more pieces of first feature information from the text data; a extract, based on components of a target belonging to a goal of sustainable development goals (SDGs), one or more pieces of second feature information from the target; determine a degree of similarity between the first feature information and each of the one or more pieces of second feature information; and generate a result of a cluster analysis of a set of the components that correspond to a piece of second feature information having the similarity equal to or more than a threshold among the one or more pieces of second feature information, the result of the cluster analysis being a summary of the goal.