Method and apparatus for analyzing and applying data related to customer interactions with social media

• US 9,536,269 B2
• Filed: 01/13/2012
• Issued: 01/03/2017
• Est. Priority Date: 01/19/2011
• Status: Active Grant

• Current Assignee: [24]7.ai, Inc.
• Original Assignee: 24/7 Customer Incorporated
• Inventors: Chang, Andrew, KANNAN, PALLIPURAM V., Vijayaraghavan, Ravi
• Primary Examiner(s): Coulter, Kenneth R
• Application Number:
  US13/349,807
• Publication Number:
  US 20120185544A1
• Time in Patent Office: 1,817 Days
• Field of Search: 709204-206, 709/224, 709/223, 715751-759
• US Class Current: 1/1
• CPC Class Codes: G06F 16/2465 Query processing support for facilitating data mining operations in structured databases
• CPC Class Codes: G06Q 10/0637 Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 50/01 Social networking

Abstract

Embodiments of the invention provide techniques that quantize community interactions with social media to understand and influence consumer experiences. Embodiments include a customer predictive experience platform. The platform can include an outcome engine configured for information mining and applying rules and analytics to the information, and an ops module configured for providing agent performance management, average handling time analytics, workflow management, and voice of the customer facilities. The platform can also include a chat module, a social media dialog engine, and a solution client configured for effecting predictive self-service, active auto sentiment management and rapid response to counteract negative sentiment, a customer experience ticker, a pre- and post-launch pulse, enhanced brand ambassadors, integration into corporate messaging and marketing, a social media dashboard, and a live portal configured for social media engagement and feedback.

Claims

1. A customer predictive experience platform, comprising:

a processor and memory, cooperating to function as;

an outcome engine configured for information mining and for applying rules and analytics to said information;

an ops module configured for providing agent performance management, average handling time (AHT) analytics, workflow management (WFM), and voice of the customer (VoC) facilities;

a chat module;

a social media dialog engine; and

a solution client, interactive with said outcome engine, configured for effecting;

predictive self-service by automatically serving curated contents and chat to implement any of social media brand improvement;

active auto sentiment management and rapid response by identifying and counteracting negative sentiment, identifying and reinforcing positive sentiment, and building authority;

a customer experience ticker;

a pre- and post-launch pulse;

enhanced brand ambassadors;

integration into corporate messaging and marketing, including two-way information exchange and synergy, by leveraging information flow across channels and providing a unified view of content and state;

a social media dashboard; and

a live portal configured for social media engagement and feedback.

2. The platform of claim 1, the solution client further configured for:

extracting a real time customer satisfaction value from a real-time survey score from any of customers receiving services, general and/or issue specific;

friends activities, updates, and comments;

real time sentiment comparison;

live feed with regard to social media tweets, marketing;

live feed with regard to a customer experience ticker that provides real feedback in real time; and

live feed with regard to positive blogs.

3. A computer implemented method for developing a social media strategy, comprising:

providing, by a processor, a first stage comprising try/participate, test, and prototype activities;

providing, by a processor, second stage comprising interaction with company and brand specific, dedicated brand ambassadors for effecting reactive, standalone reporting and how to build a relationship with a social audience with regard to rent vs. buy;

sales vs. service;

rent on other sites; and

buy, build vs. collect and automatic ability to identify and counteract negative sentiment, identify and reinforce positive sentiment, and build authority; and

providing, by a processor, a third stage comprising;

relationship deepening;

creating measurable business value with associated metrics, including sales activities comprising acquisition, lead generation, marketing, and service;

first call resolution (FCR) and CSAT;

providing automation in parallel and enhancing brand ambassadors;

integration into corporate messaging and marketing, including two-way information exchange and synergy;

leveraging information flow between/across channels and communication networks;

providing a unified view of content and state through a live portal configured for social media engagement and feedback;

actively managing and driving brand presence and value;

providing integrated reporting; and

determining what is fit for social media and what is not fit to actively predict, direct, and integrate customer actions;

manage, guide and shape customer sentiment and allocation of authority to the business'"'"' choosing and priority; and

bring customers to online portal(s) and destination website(s) of the business'"'"' choosing.

4. A customer predictive experience platform, comprising:

a processor;

a memory with instructions executable by the processor,

the processor configured both for identifying, building, and reinforcing positive sentiment, and for specifically responding to negative sentiment by;

generating an alert in a new thread;

using text mining and targeting an issue;

containing, limiting, and focused responding to the issue, and actively managing and recovering in the case of negative sentiment;

amplifying positive sentiment, volume and building authority in the case of positive sentiment, and

driving customer education and feedback learning and action;

the processor configured for providing automation enhancing brand ambassadors;

integration into corporate messaging and marketing, including two-way information exchange and synergy; and

the processor configured for providing a live portal to manage social media engagement and feedback.

5. The platform of claim 4, said processor configured for:

identifying negativity and triggering an alert for threads that are negative and identifying positivity and triggering an alert for threads that are positive;

both using a text mining engine configured to identify a topic of the thread and a key cause of the negativity or positivity as expressed by an original writer; and

identifying best examples of feedback and real customer text from a database of positive recent customer transactions that are used to counteract the negative comments of the original writer and reinforce and build authority for positive comments of the original writer or other positive writers.

6. The platform of claim 4, said processor configured for:

effecting negativity identification and for providing a corresponding alert in connection with access to a database of words and phrases, including context of said words and phrases, that indicates a negative reaction by an author of a text thread, and prioritizing and being further selective in providing alerts based on the author'"'"'s influencer score, wherein said text stream is continuously scanned by a monitor to look for words and phrases from the database; and

providing a set of trigger thresholds which are set initially based on historical data, and then adjusted by real-time results and learning;

wherein if an amount of negativity in a text thread exceeds the threshold settings, then an alert is triggered; and

wherein structured data is integrated into threshold scoring.

7. The platform of claim 6, wherein said word and phrase database is continuously renewed and actual results are fed back to enable said platform to learn about an indicative power of each word and each phrase.

8. The platform of claim 4, said processor configured for:

effecting positivity identification and for providing a corresponding alert in connection with access to a database of words and phrases, including context of said words and phrases, that indicates a positive reaction by an author of a text thread, and prioritizing and being further selective in providing alerts based on the author'"'"'s influencer score, wherein said text stream is continuously scanned by a monitor to look for words and phrases from the database; and

providing a set of trigger thresholds which are set initially based on historical data and then adjusted by real-time results and learning;

wherein if an amount of positivity in a text thread exceeds the threshold settings, then an alert is triggered; and

wherein structured data is integrated into threshold scoring.

9. The platform of claim 8, wherein said word and phrase database is continuously renewed and actual results are fed back to enable said platform to learn about an indicative power of each word and each phrase.

10. The platform of claim 4, said processor configured for:

providing a database of real customer transcripts which have positive experiences;

updating said database continuously and categorizing information therein in detail by topic;

presenting a large number of real examples from actual customer transcripts that are specifically matched to a topic in a negative thread that is targeted for counteraction or a topic in a positive thread that is targeted for amplification and reinforcement and increase in authority; and

either counteracting and overturning opinions expressed in an original negative thread by a volume of positive opinions and experiences for a same issue, or amplifying and increasing prominence/authority/reach of opinions expressed in an original positive thread by a volume of positive opinions and experiences.

11. The platform of claim 4, said processor configured for:

for a customer having a Web presence, capturing said customer'"'"'s social media experiences by any of leveraging and/or activating a social media login session;

leveraging and/or activating a social media ID;

capturing a social media name and social media ID; and

collecting information through an active campaign.

12. The platform of claim 4, said processor configured for:

performing text mining to find positive outcomes for similar issues, which are then used in social media;

said text mining incorporating a full range of automated text analysis techniques, including any of word spotting, key word and phrase, semantic context, subject and phrase categorization, and frequency distributions;

wherein said text mining techniques are applied to determine an intent and subject of each sample of text and to organize resulting data into specific recommendation and insights.

13. The platform of claim 4, said processor configured for:

triggering social media threads directly from a chat exit survey.

14. The platform of claim 13, said processor configured for:

setting pre-filter criteria based upon configurable selection and prioritization of target topics and/or influencer scores;

wherein key criteria are established specifically by an end user based on current business priorities and/or automatically by monitoring different social media threads combined with positive score levels;

wherein said criteria comprise any of sessions, topics, and situations that match a key topic that a user wants to emphasize and/or specific feedback that is impactful;

obtaining one or more chat transcripts; and

performing real time text mining to find/alert positive outcomes with similar issues.

15. The platform of claim 14, said processor configured for:

receiving positive feedback and inputting said positive feedback into a survey which feeds a real time sentiment ticker;

extracting real time scores from real time live customer service interaction with a filter;

tracking and accumulating each score; and

posting said scores to said real time sentiment ticker.