Personalizing computerized customer service

• US 8,615,070 B2
• Filed: 09/05/2012
• Issued: 12/24/2013
• Est. Priority Date: 06/26/2003
• Status: Active Grant

• Current Assignee: Kyndryl Incorporated
• Original Assignee: International Business Machines Corporation
• Inventors: Hughes, Nathan Raymond, Rao, Nishant Srinath, Uretsky, Michelle Ann
• Primary Examiner(s): Gauthier, Gerald
• Application Number:
  US13/604,112
• Publication Number:
  US 20120328086A1
• Time in Patent Office: 475 Days
• Field of Search: 379/88.01, 379/88.05, 379/88.06, 379/114.2, 379/265.12, 379/29.01, 434/308, 455/411, 455/566, 704/8, 705/37, 705/43, 705/26.1, 709/219, 715/205, 715/700, 370/352, 713/1, 725/153
• US Class Current: 379/88.01
• CPC Class Codes: G06F 40/56 Natural language generation

Abstract

A method and system for improving user satisfaction with a computer system that includes a computer. The computer prompts a user at a user machine to select a language usage pattern preference from at least two language usage pattern preference choices respectively including at least two text passages, each text passage expressing different text. After the prompting, the computer receives from the user machine a language usage pattern preference selected by the user from the at least two language usage pattern preference choices. The computer stores, in a user profile of the user located in a database accessible to the computer, a flag indicative of the selected language usage pattern preference.

Claims

1. A method for improving user satisfaction of a user at a user machine, said method comprising:

prompting, by a computer, a user at the user machine to select a language usage pattern preference from a plurality of language usage pattern preference choices respectively comprising a plurality of text passages, each text passage expressing different text;

after said prompting, said computer receiving from the user machine a language usage pattern preference selected by the user from the plurality of language usage pattern preference choices; and

said computer storing, in a user profile of the user located in a database accessible to the computer, a flag indicative of the selected language usage pattern preference.

2. The method of claim 1, wherein each text passage comprises a different one or more personal pronouns not comprised by any other text passage of the plurality of text passages.

3. The method of claim 1, wherein the plurality of language usage pattern preference choices consist of three language usage pattern preference choices respectively comprising three text passages.

4. The method of claim 1, wherein the method further comprises:

after said storing the flag, said computer ascertaining, from the stored flag, the selected language usage pattern preference.

5. The method of claim 1, wherein the computer is located at a web site, wherein the user machine is separated from the web site by a web network, and wherein the method further comprises:

said computer detecting an attempt by the user machine to access the web site via the web network, wherein said prompting is in response to said detecting.

6. The method of claim 5, wherein the method further comprises:

after said storing the flag, said computer ascertaining, from the stored flag, the selected language usage pattern preference;

after said ascertaining, said computer modifying text content to be presented to the user, said modifying comprising applying grammatical rules to the ascertained language usage pattern preference; and

said computer providing the modified text content to the user computer for presentation to the user.

7. The method of claim 1, wherein the user machine is a telephone, and wherein the method further comprises:

said computer querying the user at the telephone to determine preferred voice qualities while the computer is engaged in telephone communication with the user via the telephone;

said computer receiving, from the user at the telephone, responses to said querying;

said computer determining from the responses received from the user, using voice recognition functions of the telephonic response system, the preferred voice qualities; and

said computer storing, in the user profile, the preferred voice qualities determined from the responses received from the user.

8. The method of claim 7, wherein the method further comprises:

after said storing the preferred voice qualities, said computer accessing the stored preferred voice qualities;

after said accessing the stored preferred voice qualities, said computer modifying responses to the user to be presented to the user, said modifying comprising generating the modified responses, using voice generation functions of the telephonic response system, such that voice qualities in the generated modified responses match the accessed preferred voice qualities; and

said computer providing the modified responses to the user at the telephone.

9. The method of claim 7, wherein said storing the preferred voice qualities comprises storing voice qualities comprising pacing of speech expressed as a time rate of speech text, volume of speech expressed as speech loudness, and gender of speech expressed as male or female, and wherein the method comprises determining the gender of speech from a range of sound wave frequency of the responses received from the user to said querying.

10. The method of claim 9, wherein the method further comprises:

after said storing the preferred voice qualities, said computer accessing the stored preferred voice qualities;

after said accessing the stored preferred voice qualities, said computer modifying responses to the user to be presented to the user, said modifying comprising generating the modified responses, using voice generation functions of the telephonic response system, such that voice qualities in the generated modified responses match the accessed preferred voice qualities; and

said computer providing the modified responses to the user at the telephone.

11. A computer system, said computer system comprising a computer, said computer configured to perform a method for improving satisfaction of a user at a user machine, said method comprising:

said computer prompting a user at the user machine to select a language usage pattern preference from a plurality of language usage pattern preference choices respectively comprising a plurality of text passages, each text passage expressing different text;

after said prompting, said computer receiving from the user machine a language usage pattern preference selected by the user from the plurality of language usage pattern preference choices; and

said computer storing, in a user profile of the user located in a database accessible to the computer, a flag indicative of the selected language usage pattern preference.

12. The computer system of claim 11, wherein each text passage comprises a different one or more personal pronouns not comprised by any other text passage of the plurality of text passages.

13. The computer system of claim 11, wherein the plurality of language usage pattern preference choices consist of three language usage pattern preference choices respectively comprising three text passages.

14. The computer system of claim 11, wherein the method further comprises:

after said storing the flag, said computer ascertaining, from the stored flag, the selected language usage pattern preference.

15. The computer system of claim 11, wherein the computer is located at a web site, wherein the user machine is separated from the web site by a web network, and wherein the method further comprises:

said computer detecting an attempt by the user machine to access the web site via the web network, wherein said prompting is in response to said detecting.

16. The computer system of claim 15, wherein the method further comprises:

after said storing the flag, said computer ascertaining, from the stored flag, the selected language usage pattern preference;

after said ascertaining, said computer modifying text content to be presented to the user, said modifying comprising applying grammatical rules to the ascertained language usage pattern preference; and

said computer providing the modified text content to the user computer for presentation to the user.

17. The computer system of claim 11, wherein the user machine is a telephone, and wherein the method further comprises:

said computer querying the user at the telephone to determine preferred voice qualities while the computer is engaged in telephone communication with the user via the telephone;

said computer receiving, from the user at the telephone, responses to said querying;

said computer determining from the responses received from the user, using voice recognition functions of the telephonic response system, the preferred voice qualities; and

said computer storing, in the user profile, the preferred voice qualities determined from the responses received from the user.

18. The computer system of claim 17, wherein the method further comprises:

after said storing the preferred voice qualities, said computer accessing the stored preferred voice qualities;

after said accessing the stored preferred voice qualities, said computer modifying responses to the user to be presented to the user, said modifying comprising generating the modified responses, using voice generation functions of the telephonic response system, such that voice qualities in the generated modified responses match the accessed preferred voice qualities; and

said computer providing the modified responses to the user at the telephone.

19. The computer system of claim 17, wherein said storing the preferred voice qualities comprises storing voice qualities comprising pacing of speech expressed as a time rate of speech text, volume of speech expressed as speech loudness, and gender of speech expressed as male or female, and wherein the method comprises determining the gender of speech from a range of sound wave frequency of the responses received from the user to said querying.

20. The computer system of claim 19, wherein the method further comprises:

after said storing the preferred voice qualities, said computer accessing the stored preferred voice qualities;

after said accessing the stored preferred voice qualities, said computer modifying responses to the user to be presented to the user, said modifying comprising generating the modified responses, using voice generation functions of the telephonic response system, such that voice qualities in the generated modified responses match the accessed preferred voice qualities; and

said computer providing the modified responses to the user at the telephone.