System and method for categorization of social media conversation for response management

Patent metadata

Field	Value
Publication number	US-9824321-B2
Application number	US-201414490068-A
Country	US
Kind code	B2
Filing date	Sep 18, 2014
Priority date	Sep 20, 2013
Publication date	Nov 21, 2017
Grant date	Nov 21, 2017

Abstract

A computer implemented method for customer response management the method comprising the step of collecting information from social networking sites wherein the information is at least a post or comment for at least a brand or product; identifying customer among pluralities of authors of the information on the social networking sites; categorizing the information into at least a complaint, lead, service request, information request or feedback; analyzing the categorized information; prioritizing the analyzed information; and routing the prioritized information to at least a concerned personnel or a work flow of the Customer Relationship Management (CRM) system for response. The method further comprising identifying the influence of the customer wherein the influence is at least a global influence or local influence. The identification of customer is done by fetching information from at least the Customer Relationship Management (CRM) system or social profile aggregator service.

First claim

What is claimed is:

1. A computer implemented method executed by one or more computing devices for customer response management, the method comprising:
collecting, by at least one of the one or more computing devices, at least information from a first social networking site of a plurality of social networking sites, wherein the information comprises at least a post or comment by an individual for at least a brand or a product;
comparing at least one social networking site identity of the individual with customer profile information stored in a customer profile repository, the customer profile repository comprising one or more social networking site identities for each of a plurality of customers;
based on the comparing, determining that the individual is a customer;
categorizing by at least one of the one or more computing devices, the information into at least a complaint, lead, service request, information request or feedback by analyzing the information with a machine learning component trained to recognize at least one category, the at least one category comprising complaints, information requests, or feedback, the machine learning component being trained with a mathematical model of, and for, the at least one category;
analyzing, by at least one of the one or more computing devices, the categorized information by classifying the information using a taxonomy to link the categorized information to the at least a brand or product;
prioritizing, by at least one of the one or more computing devices, the analyzed information based at least in part on at least one of a reputation and relevancy weighting for the first social networking site, an influence score for the individual, and a category associated with the at least a post or comment; and
routing, by at least one of the one or more computing devices, the prioritized information to at least a concerned personnel or a work flow of a Customer Relationship Management (CRM) system for response, wherein routed information for a plurality of at least a post or a comment is displayed to the concerned personnel, or by CRM system, according to priorities associated with the plurality of at least a post or a comment.

2. The method of claim 1 , wherein the customer profile repository comprises information from at least the Customer Relationship Management (CRM) system or a social profile aggregator service.

3. The method of claim 1 , wherein the prioritizing is based at least in part on the influence score for the individual, the method further comprising:
calculating the influence score of the individual based on a weighting defined for the plurality of social networking sites, wherein the weighting is assigned at least in part based on reputation and relevancy of the plurality of social networking sites, a number of responses to the information, or profile information of the individual.

4. The method of claim 1 , wherein analyzing the categorized information further comprises identifying one or more key words in the categorized information, the one or more key words comprising a word describing an attribute of the at least a brand or a product.

5. The method of claim 1 wherein analyzing the categorized information further comprises identifying a sentiment in the categorized information by analyzing the categorized information using natural language processing and machine learning.

6. The method of claim 1 , the method further comprising:
determining a number of responses to the at least a post or comment;
wherein prioritizing the analyzed information is based at least in part on the number of responses.

7. The method of claim 1 , wherein the categorization is further done on at least the influence score of the individual or a sentiment of the post.

8. The method of claim 1 , wherein the influence score of the individual is at least a global influence or a local influence.

9. The method of claim 8 , wherein the global influence is the influence of the individual on the plurality of social networking sites, a plurality of internet forums, or a combination of the plurality of social networking sites and one or more internet forums.

10. The method of claim 8 , wherein the local influence of the individual is the influence of the individual on a social networking site of the plurality of social networking sites or an internet forum and is calculated at least in part based on one or more of a frequency of activity of the individual, a volume of posts by the individual, responses to the at least a post or comment by other users of the social networking site or internet forum, propagation of the at least a post or comment, a number of times the at least a post or comment was accessed, and an influence of other users of the social networking site or internet forum connected to the individual.

11. The method of claim 1 , further comprising:
responding to the individual at least on the first social networking site or through the CRM system.

12. A system for customer response management the system comprising:
one or more processors; and
one or more memories operatively coupled to at least one of the one or more processors and having instructions stored thereon that, when executed by at least one of the one or more processors, cause at least one of the one or more processors to perform operations comprising:
collecting at least information from a first social networking site of a plurality of social networking sites wherein the information is at least a post or comment by an individual;
comparing at least one social networking site identity of the individual with customer profile information stored in a customer profile repository, the customer profile repository comprising one or more social networking site identities for each of a plurality of customers;
based on the comparing, determining whether the individual is a customer;
categorizing the information into at least a complaint, information request or feedback by analyzing the information with a machine learning component trained to recognize at least one category;
analyzing the categorized information by classifying the information using a taxonomy to link the categorized information to at least a brand or product;
prioritizing the analyzed information; and
routing the prioritized information to at least a concerned personnel or a Customer Relationship Management (CRM) system for response.

13. The system of claim 12 , the operations further comprising:
aggregating a plurality of social media profiles of the individual.

14. The system of claim 12 , the operations further comprising:
mapping a social media site profile of the individual to an enterprise identity of the individual, wherein the mapping is based at least in part on an e-mail ID or a social networking profile name of the individual.

15. The system of claim 12 , the operations further comprising:
calculating the influence score of the individual, wherein the influence score is calculated based on a weightage defined for the plurality of social networking sites and the weightage is assigned based on at least reputation and relevancy of the plurality of social networking sites, a number of responses to the information, or profile information of the individual.

16. The system of claim 12 , the operations further comprising:
grouping a plurality of posts by users of the first social networking site into a conversation based at least in part on a keyword, the keyword being associated with the at least a post or comment.

17. The system of claim 12 , wherein an enterprise identity of the individual is stored

Assignees

• Infosys Ltd

Inventors

• Raghunathan Balaji
• Varghese Sivaram Thangam
• Teli Prasanna Nagesh

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G06Q10/0633 Primary

  Workflow analysis · CPC title

• H04L51/32

  Electricity · mapped topic

• G06Q50/01

  Physics · mapped topic

• H04L51/52

  for supporting social networking services · CPC title