FAQ Response Processing System Keyword Classification

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

In FAQ systems using chatbots, users face difficulty in narrowing down answer candidates when the number of retrieval results exceeds the maximum display number, especially when irrelevant keywords are displayed, making it hard for users to select relevant keywords related to their queries.

Innovation Solution

A response processing method that automatically classifies keywords or key phrases extracted from answer candidate data, allowing users to select and narrow down answer candidates based on classified options, thereby facilitating the retrieval of relevant FAQs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple answer candidate data are retrieved and displayed, then the completeness of information is improved, but the difficulty of selecting relevant keywords increases

Engineering Contradiction:

Improvenumber of answer candidatesVSAvoidease of keyword selection

Core Design Contradiction:

Quantity of substanceVSEase of operation

Solution Approach 1:

The patent segments the large set of retrieved answer candidates into smaller groups based on extracted keywords. Each keyword becomes a category header that organizes related answer candidates, transforming one overwhelming list into multiple manageable sections that users can navigate efficiently.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces keywords as intermediary elements between the user's query and the answer candidates. These keywords act as mediators that bridge the gap by providing intermediate classification layers, allowing users to filter and select answer candidates through keyword-based navigation rather than browsing all candidates directly.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If keywords are extracted from answer candidate data, then the relevance of displayed information is improved, but the processing time increases

Engineering Contradiction:

Improveprecision of keyword relevanceVSAvoidprocessing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent extracts only the most relevant keywords from answer candidate data rather than processing all possible information. By selecting a limited set of key terms that capture the essence of each answer, the system achieves sufficient relevance precision while minimizing processing time through selective extraction.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent changes the parameter of keyword extraction by focusing on specific critical terms rather than comprehensive text analysis. This parameter change in the extraction approach allows the system to maintain high relevance precision while reducing the computational burden and processing time required.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS11709872B2Computer-readable recording medium storing response processing program, response processing method, and information processing apparatus

Publication Date: 2023.07.25 FUJITSU LTD

AI summary

A non-transitory computer-readable recording medium stores a response processing program for causing a computer to execute processing including: receiving a question from a user input to a terminal; extracting, in a case where a plurality of pieces of answer candidate data that corresponds to the received question is retrieved, keywords or key phrases from the plurality of pieces of answer candidate data; classifying the extracted keywords or key phrases on the basis of words included in the keywords or key phrases; and outputting a classification result of the keywords or key phrases to the terminal in a state selectable by a user, together with a response text to the question.