Auto-Suggesting Response System for Social Media Customer Care

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional customer care systems in social media environments face challenges in providing instant and accurate solutions due to the manual and intensive nature of expert training, leading to increased response times and frustrated customers, as they struggle to effectively handle the contextual and noisy nature of social media conversations.

Innovation Solution

A method and system that automatically suggests responses by monitoring social media sites, extracting contextual information from conversational threads, and searching a database for relevant reference messages to generate customized and ranked responses, leveraging attributes like tags, slugs, categories, topics, sentiments, and user locations to improve response accuracy and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual expert training is used to handle social media customer queries, then response accuracy can be improved, but response time increases and customer satisfaction decreases

Engineering Contradiction:

Improveresponse accuracyVSAvoidresponse time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system enables self-service by automatically analyzing social media queries, extracting contextual information, and generating suggested responses without requiring manual expert intervention for each query. The handling expert only needs to review and approve the generated suggestions, significantly reducing response time while maintaining accuracy.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system introduces an intermediary automated response generation component that acts as a bridge between the customer query and the handling expert. This intermediary analyzes the query, searches historical data, and provides pre-prepared response suggestions, reducing the workload and response time for experts.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Reliability

If intensive expert training is provided to handle social media conversations, then service quality improves, but training costs and device complexity increase

Engineering Contradiction:

Improveservice qualityVSAvoidtraining system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system creates a virtual knowledge base by copying and storing historical successful interactions, conversational threads, and resolved issues from the database. This virtual repository serves as a trained knowledge source that guides response generation without requiring extensive human training programs.

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The system performs preliminary analysis of customer queries by extracting contextual information, identifying key attributes, and searching historical databases before presenting response suggestions to experts. This preliminary processing reduces the complexity of real-time decision-making and minimizes the training needed for experts.

Inventive Principle:

Principle #10Preliminary action

3Adaptability or versatility

If manual response generation is used in traditional call centers, then responses can be customized, but response time increases and productivity decreases

Engineering Contradiction:

Improveresponse customizationVSAvoidresponse throughput

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system automatically adjusts response parameters by extracting contextual information from social media queries, including customer location, sentiment, conversation history, and topic classification. These dynamic parameter adjustments enable customized responses to be generated automatically at scale, maintaining adaptability while increasing productivity.

Inventive Principle:

Principle #35Parameter changes

4Loss of information

If social media conversations are monitored and analyzed manually, then contextual understanding improves, but the volume of noise and informal content makes processing difficult and time-consuming

Engineering Contradiction:

Improvecontextual information retentionVSAvoidprocessing system complexity

Core Design Contradiction:

Loss of informationVSDevice complexity

Solution Approach 1:

The system extracts only the relevant contextual information from noisy social media conversations, such as customer location, sentiment, key topics, and conversation thread structure. By selectively extracting useful information and filtering out noise, the system simplifies processing while retaining essential contextual data.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS10162884B2System and method for auto-suggesting responses based on social conversational contents in customer care services

Publication Date: 2018.12.25 CONDUENT BUSINESS SERVICES LLC

AI summary

A first embodiment of the disclosure relates to a method for responding to a message posted in a social media stream. The method includes monitoring a social media site for at least one message including select subject matter. In response to identifying a message, the method includes collecting a series of exchanges that form a conversational thread including the message. The method includes determining at least one content attribute of the message. The method includes classifying the message using at least one key attribute. The method includes searching a database for a reference message using a combination of the at least one content and key attributes. The method includes determining a previous outcome of a reference thread including the reference message. The method includes using the previous outcome for determining a course of action.