Dynamic Keyword Dictionary for Call Data Analysis Accuracy

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional CTI systems face challenges in achieving high accuracy in analyzing client-contact center interactions, particularly in recognizing and interpreting product-related information from call data.

Innovation Solution

A system that acquires call data, performs sound recognition using a keyword dictionary, extracts relevant keywords, and registers new keywords from a product information database to enhance analysis accuracy, incorporating natural language processing and AI for improved keyword detection and weighting.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional CTI systems are used for call data analysis, then basic call recording and analysis can be performed, but the accuracy of analyzing product-related information is insufficient

Engineering Contradiction:

Improveanalysis accuracyVSAvoidproduct information recognition

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The system implements a feedback mechanism where sound recognition results are continuously registered into the dictionary data. The registration unit adds newly recognized keywords and product information back into the system, creating a self-improving loop that enhances analysis accuracy over time through accumulated learning from call data

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs self-service by automatically registering sound recognition results into the dictionary data without requiring manual intervention. The registration unit autonomously processes recognized keywords and product information, enabling the system to self-enhance its analysis capabilities through continuous operation

Inventive Principle:

Principle #25Self-service

2Adaptability or versatility

If a fixed keyword dictionary is used for sound recognition, then the system structure remains simple, but the system cannot adapt to new product information or evolving customer queries

Engineering Contradiction:

Improvekeyword recognition adaptabilityVSAvoiddictionary data structure

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The dictionary data structure is made dynamic through automatic registration of sound recognition results. The system transitions from a static keyword list to a dynamically evolving database that automatically incorporates new keywords and product information, enabling adaptation to changing customer needs and product catalogs

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system performs preliminary registration of sound recognition results into the dictionary data, preparing the system in advance for future recognition tasks. By continuously pre-loading new keywords and product information, the system ensures it is ready to handle evolving customer queries and product variations

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS11532311B2System, method, program, and recording medium for improving accuracy of call data analysis

Publication Date: 2022.12.20 YOKOGAWA ELECTRIC CORP

AI summary

Recently, there has been a demand for further improvement of accuracy of analysis. A system is provided that includes an acquisition unit that acquires call data which is a record of a call between a client and a contact center, a sound recognition unit that performs sound recognition on the call data by using a keyword registered in dictionary data, an analysis unit that performs analysis using a keyword included in a result of the sound recognition, and a registration unit that registers in the dictionary data, a keyword included in a product information database among a plurality of the keywords included in the result of the sound recognition, the product information database storing product information about each of a plurality of products.