Personality-based intelligent personal assistant system and methods

Patent metadata

Field	Value
Publication number	US-9390706-B2
Application number	US-201414309728-A
Country	US
Kind code	B2
Filing date	Jun 19, 2014
Priority date	Jun 19, 2014
Publication date	Jul 12, 2016
Grant date	Jul 12, 2016

Abstract

The methods, apparatus, and systems described herein assist a user with a request. The methods include receiving at least one input from a user, entering the at least one input into an algorithm trained to output a personality type of the user, and tailoring an output based on the personality type.

First claim

What is claimed is:

1. A system adapted to assist a user, which comprises:
a node comprising a processor and a non-transitory computer readable medium operably couples thereto, the non-transitory computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, where the plurality of instructions comprises:
instructions that, when executed, receive a user request;
instructions that, when executed, retrieve or determine a personality type of the user from three or more personality types based on one or more user requests;
instructions that, when executed, determine a set of outputs, wherein the set of outputs comprises a plurality of different modalities of a device and physical actions to control the device, responsive to the received user request;
instructions that, when executed, rank the outputs in the set based on the determined personality type of the user;
instructions that, when executed, deliver a ranked output to the user request in a modality of the device, wherein the modality of the device is determined based on the personality type and type of the device configured to deliver the output to the user; and
instructions that, when executed, determine a distress level or engagement level of the user, or both, based on the ranked output delivered and the modality of delivery, and weight the ranked output for one or more future interactions with the user based on the determined distress level and/or engagement level.

2. The system of claim 1 , wherein the instructions to determine personality type of the user comprises instructions, that when executed, apply a linguistic-based algorithm to the user request.

3. The system of claim 1 , further comprising instructions that, when executed, extracts one or more communication attributes from the request.

4. The system of claim 3 , wherein each communication attribute comprises tone, tempo, pattern of speech, syntax, grammar, or any combination thereof.

5. The system of claim 1 , further comprising instructions that, when executed, predict user input.

6. The system of claim 1 , further comprising instructions that, when executed, rank the user request to prioritize requests for the user.

7. The system of claim 1 , further comprising instructions that, when executed, determine success of the output in addressing the user request.

8. A method for assisting a user, which comprises:
receiving, by one or more processors, at least one request from the user;
entering, by the one or more processors, the at least one request into an algorithm trained to output a personality type of the user from three or more personality types based on the at least one user request
generating, by the one more processors, a set of outputs, wherein the set of outputs comprises a plurality of different modalities of a device and physical actions to control the device, responsive to the at least one input;
ranking and selecting, by the one or more processors, an output from the set of outputs based on the one personality type;
delivering, by the one or more processors, the ranked and selected output to the user in a modality of the device, wherein the modality of the device is determined based on the personality type and type of the device configured to deliver the output to the user; and
determining a distress level or engagement level of the user, or both, based on the ranked and selected output and the modality of delivery, and weighting the ranked and selected output for one or more future interactions with the user based on the determined distress level and/or engagement level.

9. The method of claim 8 , which further comprises extracting one or more attributes from the request.

10. The method of claim 9 , wherein each attribute is a data attribute that comprises engagement, distress, mental state, or any combination thereof.

11. The method of claim 8 , Which further comprises updating the personality type based on additional input.

12. The method of claim 8 , which further comprises determining what the user may request in the future based at least in part on the personality type and success with determining previous output.

13. The method of claim 8 , wherein the output exhibits a personality type that is complementary to the user's personality type.

14. The method of claim 8 , which further comprises determining success of the output in meeting the user's request.

15. A non-transitory computer readable article comprising a plurality of instructions comprising:
instructions that, when executed, receive a request from a user;
instructions, that, when executed, identify a personality type of the user from three or more personality types based on the user request;
instructions that, when executed, determine a set of outputs, wherein the set of outputs comprises a plurality of different modalities of a device and physical actions to control the device, responsive to the received user request;
instructions that, when executed, rank the outputs in the set based on the identified personality type of the user;
instructions that, when executed, select a responsive ranked output from the set of ranked outputs responsive to the request and the personality type and deliver the responsive ranked output to the user in a modality of the device, wherein the modality of the device is determined based on the personality type and type of the device configured to deliver the responsive ranked output to the user; and
instructions that, when executed, determine a distress level or engagement level of the user, or both, based on the responsive ranked output delivered and the modality of delivery, and weight the respective ranked output for one or more future interactions with the user based on the determined distress level and/or engagement level.

16. The non-transitory computer readable article of claim 15 , wherein the instructions that identify a personality type of the user comprise instructions, that when executed, subject the request to a linguistic-based algorithm to yield a score.

17. The non-transitory computer readable article of claim 15 , wherein the at least one attribute is a data attribute that comprises engagement, distress, mental state, communication style, or any combination thereof.

18. The non-transitory computer readable article of claim 15 , further comprising instructions, that when executed, predict input from the user.

19. The non-transitory computer readable article of claim 15 , further comprising instructions that, when executed, update the personality type based on additional input from the user.

20. The non-transitory computer readable article of claim 15 , thither comprising instructions that, when executed, determine success of the output.

21. A system adapted to assist a user, which comprises:
a storage device storing a non-transitory computer readable program; and
a processor executing the non-transitory computer readable program comprising:
a communication module adapted to receive a user request;
a scoring module adapted to use the user request to determine a personality type of the user from the three or more personality types based on one or more user requests, wherein the scoring module is adapted to provide a set of ranked outputs, wherein the set of ranked outputs comprises a plurality of different modalities of a device and physical actions to control the device, based on the input according to the personality type of the user;
an interaction m

Assignees

• Mattersight Corp

Inventors

• Gustafson David
• Danson Christopher

Classifications

• G10L25/66

  for extracting parameters related to health condition (detecting or measuring for diagnostic purposes A61B5/00) · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L2015/088

  Word spotting · CPC title

• G10L25/63

  for estimating an emotional state · CPC title

• G10L25/51

  for comparison or discrimination · CPC title