Method for routing electronic correspondence based on the level and type of emotion contained therein

• US 8,600,734 B2
• Filed: 12/18/2006
• Issued: 12/03/2013
• Est. Priority Date: 10/07/2002
• Status: Active Grant

• Current Assignee: Oracle OTC Subsidiary LLC (Oracle Corporation)
• Original Assignee: Oracle OTC Subsidiary LLC (Oracle Corporation)
• Inventors: Warner, Douglas K., Richter, James Neal, Durbin, Stephen D., Gianforte, Greg
• Primary Examiner(s): SPOONER, LAMONT M
• Application Number:
  US11/612,206
• Publication Number:
  US 20070100603A1
• Time in Patent Office: 2,542 Days
• Field of Search: 704/9, 704/231, 704/251, 704/257, 704/256, 707 2- 6, 707706-708
• US Class Current: 704/9
• CPC Class Codes: G06F 40/284 Lexical analysis, e.g. tokenisation or collocates
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A system, method, and computer program product for determining the emotional content of an electronic correspondence to route or prioritize the information, to set the expectations of a customer support worker, to flag those workers who are using inappropriate language with the customer, or to determine another best course to send the correspondence. In a preferred embodiment, a customer sends an electronic correspondence to a company via email. Emotionally charged words or symbols in each sentence are detected. The message is then given an emotional ranking which is used to determine what future action is most appropriate for the correspondence.

Claims

1. A multi-language method for routing electronic correspondence to personnel or entity having a potential interest in the emotional content of at least one or more words or symbols within said electronic correspondence, said method comprising:

receiving said electronic correspondence;

analyzing said electronic correspondence to determine an emotional ranking for said correspondence including;

determining from a plurality of languages a language used in said electronic correspondence,

applying language specific tagging to each word of said electronic correspondence with their respective parts-of-speech for said language,

applying language specific parsing of said electronic correspondence into noun phrases and verb phrases for said language based on the tagging of each word of said electronic correspondence,

applying transformation rules to said parsed electronic correspondence to produce an emotional ranking for said electronic correspondence, wherein producing the emotional ranking for the electronic correspondence includes assigning to each phrase and one or more symbols in the electronic communication an emotion value, wherein the one or more symbols comprise punctuation strings of one or more characters which together with the phrases denote emotion, and wherein the emotional ranking comprises a time-scaled weighted average of the emotional values, and

assigning a priority to the electronic correspondence based on the emotional ranking; and

workflow routing said electronic correspondence to one of said personnel or entity more likely having said potential interest in the contents thereof for further action based on said emotional ranking and the assigned priority.

2. The method of claim 1, wherein said emotional ranking is determined by a customer'"'"'s satisfaction with a company'"'"'s products or services.

3. The method of claim 1, wherein said further action comprises at least one of the following actions:

routing said electronic correspondence to an appropriate person based on said emotional ranking;

setting the expectations of one or more recipients;

flagging said one or more recipients who are using inappropriate language with said customer;

or

determining another best course to send said electronic correspondence.

4. The method of claim 3, wherein the electronic correspondence is from a customer service representative to a customer.

5. The method of claim 1, further comprising the steps of:

storing a collection of said emotional rankings;

performing mathematical calculations on an individual or a collection of said emotional rankings to generate statistics; and

generating one or more of a plurality of reports based on said statistics.

6. The method of claim 1 wherein said emotional ranking is conveyed in a numeric range.

7. The method of claim 1 including the steps of:

responding to said electronic correspondence in a manner related to said emotional ranking; and

rerouting said response if said emotional ranking of said response has a negative emotional value.

8. The method of claim 1, including the step of assigning an emotional value to said electronic correspondence using a reference data structure.

9. The method of claim 8 wherein said emotion value is in a range that spans from a negative value to a positive value.

10. The method of claim 8, wherein said referenced data structure is a table, spreadsheet, or database having said emotional values associated with predetermined words of emotional content.

11. The method of claim 8, wherein said step of assigning an emotional value to said electronic correspondence using a referenced data structure, further comprises:

determining whether one or more words, phrases, or symbols of said electronic correspondence is located within said referenced data structure; and

retrieving said emotional value based on said one or more words, phrases, or symbols having a match within said referenced data structure.

12. The method of claim 8 wherein said emotion value is reflective of both positive and negative emotions.

13. A method as recited in claim 12 further comprising routing the electronic correspondence as a result of said emotional ranking.

14. A method as recited in claim 12 wherein said emotional ranking is derived by a fuzzy logic reduction process, which reduces the non-linearity of individual work ratings and simplifies the conveyance of information to a user.

15. The method of claim 1, wherein the electronic correspondence is from a customer to a customer service representative.

16. A multi-language method in a computing environment for routing an electronic correspondence based on the level and type of information contained within the electronic correspondence, the method comprising:

determining from a plurality of languages a language used in said electronic correspondence;

applying language specific tagging to each word of said electronic correspondence;

applying language specific parsing of said electronic correspondence based on said tagging to parse the electronic correspondence into a plurality of words and phrases;

assigning one or more values to each of the words or phrases and one or more symbols in the electronic correspondence, wherein the one or more symbols each comprise a punctuation string of one or more characters which together with the phrases denote emotion;

utilizing said one or more values to provide an emotional ranking and priority for said electronic correspondence, wherein the emotional ranking comprises a time-scaled weighted average of the emotional values; and

workflow routing said electronic correspondence to personnel having an interest in taking action based on said correspondence as a result of said priority and emotional ranking of the contents thereof.

17. A method as recited in claim 16 further comprising utilizing said emotional ranking to prioritize said electronic correspondence.

18. A method as recited in claim 16 wherein said emotional ranking is derived by a fuzzy logic reduction process, which reduces the non-linearity of individual word ratings and simplifies the conveyance of information to a user.