Voice Recognition Sales Analysis Automation

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for analyzing sales conversations rely heavily on human resources, leading to inefficiencies and reduced accuracy, especially as the complexity of sales conversations increases in B2B models.

Innovation Solution

A sales conversation analysis method and apparatus that utilizes voice recognition to convert sales conversations into text, extracts relevant keywords and sentences related to business items, calculates evaluation scores, and generates recommendation queries to enhance sales success probabilities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If human resources are used to directly analyze voice files, then analysis accuracy may be maintained, but labor consumption increases and efficiency decreases

Engineering Contradiction:

Improveanalysis efficiencyVSAvoidtime consumption

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The patent replaces manual human analysis of voice files with an automated voice recognition system that converts speech to text and extracts business information automatically. This substitution of mechanical/human labor with automated technological systems directly resolves the contradiction by eliminating the need for human resources to directly analyze voice files, thereby improving productivity while reducing time consumption.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of manufacture

If simple voice-to-text conversion is used, then implementation is simple, but analysis quality for sales conversations deteriorates

Engineering Contradiction:

Improveimplementation simplicityVSAvoidanalysis accuracy

Core Design Contradiction:

Ease of manufactureVSMeasurement precision

Solution Approach 1:

The patent segments the analysis process into distinct stages: voice recognition for basic conversion, keyword extraction for identifying business items, sentence extraction for detailed analysis, and evaluation scoring for quality assessment. This segmentation allows the system to build complexity progressively, maintaining implementation simplicity in early stages while achieving high analysis accuracy through the combined effect of multiple processing layers.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent introduces an intermediary analysis platform that sits between the simple voice-to-text conversion and the final analysis requirements. This intermediary layer includes keyword extraction modules, sentence extraction modules, and evaluation scoring modules that bridge the gap between basic conversion and high-quality analysis, enabling the system to achieve both implementation simplicity and analysis accuracy.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If more factors are considered in sales conversation analysis, then analysis comprehensiveness improves, but information missed or unrecognized increases

Engineering Contradiction:

Improveanalysis comprehensivenessVSAvoidinformation recognition accuracy

Core Design Contradiction:

Adaptability or versatilityVSLoss of information

Solution Approach 1:

The patent performs preliminary actions by pre-defining multiple business item categories (budget, authority, needs, purchase time, competitor) and their corresponding extraction criteria before analyzing the actual sales conversation. This preliminary preparation ensures that the system is ready to recognize and extract all relevant factors systematically, preventing information loss while maintaining high comprehensiveness across diverse sales scenarios.

Inventive Principle:

Principle #10Preliminary action

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach automates the analysis process, reducing labor and time requirements while providing accurate and systematic analysis, leading to improved sales success probabilities and optimized sales strategies.

Implementation Method 1

converting the voice information into text

Methodology Applied

Scientific EffectVoice recognition:

Data Source

PatentUS12282928B2Method and apparatus for analyzing sales conversation based on voice recognition

Publication Date: 2025.04.22 VODABI CO LTD

AI summary

There is disclosed a method for analyzing a sales conversation based on voice recognition. The disclosed method comprises obtaining voice information about a sales conversation between a sales representative and a customer, converting the voice information into text, extracting at least one of a keyword and a sentence corresponding to each of a plurality of business items from the text, extracting analysis information for each of the plurality of business items based on at least one of the keyword and the sentence, and calculating an evaluation score for each of the plurality of business items based on the analysis information for each of the plurality of business items.