Presentation Evaluation Device Sentence Proportion Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing presentation evaluation devices cannot accurately determine if key explanations have been uttered during a conversation, leading to potential over-evaluation when only related keywords are mentioned.

Innovation Solution

A presentation evaluation device that analyzes speech to determine the proportion of uttered sentences or keywords, evaluating the presentation based on the proportion of provided explanations and displaying required explanations that have not been uttered.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If evaluation is based on keywords alone, then evaluation speed is improved, but evaluation accuracy deteriorates because explanations may be omitted even when related keywords are uttered

Engineering Contradiction:
Improveevaluation speedVSAvoidevaluation accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent divides the explanation into multiple sentences and evaluates each sentence's utterance proportion separately. This segmentation allows the system to determine whether the explanation has been adequately covered by checking if a predetermined proportion of sentences have been uttered, rather than relying solely on keyword matching. This resolves the contradiction by maintaining evaluation speed through automated sentence-level analysis while improving accuracy through proportional coverage assessment.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces a new evaluation parameter - the proportion of uttered sentences within an explanation - to replace simple keyword presence/absence checking. By changing from binary keyword matching to proportional sentence coverage assessment, the system can accurately determine whether explanations have been provided while maintaining efficient automated evaluation. This parameter change resolves the contradiction by enabling both speed and accuracy.

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If all sentences in explanations are checked for utterance, then evaluation accuracy is improved, but device complexity increases

Engineering Contradiction:
Improveevaluation accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent applies partial action by checking only whether a predetermined proportion of sentences in each explanation have been uttered, rather than requiring 100% coverage or checking every possible sentence variation. This partial coverage approach (e.g., requiring at least 50% of sentences to be uttered) provides sufficient accuracy to determine explanation coverage while significantly reducing the complexity of sentence-by-sentence verification. The system achieves this by storing explanations and their sentences and performing proportional matching against speech transcriptions.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20240412725A1Presentation evaluation device
Publication Date: 2024.12.12 INTERACTIVE SOLUTIONS CORP
  • US20240412725A1 patent drawing

AI summary

[Problem] To provide a presentation evaluation device for evaluating a presentation using the proportion of spoken notes among explanatory notes. [Solution] A presentation evaluation device having a speech analysis unit 3 for analyzing speech, a presentation-material-related information storage unit 5, a sentence storage unit 19, and a presentation evaluation unit 9. The presentation evaluation unit 9 reads one or a plurality of sentences for each of one or a plurality of explanatory notes from the sentence storage unit 19, determines whether or not one or a plurality of sentences for each of the one or plurality of explanatory notes is included and whether or not one or a plurality of explanatory notes are spoken by using spoken terms acquired by the speech analysis unit 3, and evaluates an inputted presentation on the basis of information pertaining to spoken notes among explanatory notes in presentation material stored in the presentation-material-related information storage unit 5.