Personality-based chatbot and methods

• US 9,847,084 B2
• Filed: 06/20/2016
• Issued: 12/19/2017
• Est. Priority Date: 06/19/2014
• Status: Active Grant

• Current Assignee: Mattersight Corporation (Nice Ltd)
• Original Assignee: Mattersight Corporation (Nice Ltd)
• Inventors: Gustafson, David, Danson, Christopher
• Primary Examiner(s): Shah, Paras D
• Application Number:
  US15/187,521
• Publication Number:
  US 20160300570A1
• Time in Patent Office: 547 Days
• Field of Search: 704270, 7042701, 704275, 704 9, 379 8801, 379 8816
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 15/19 Grammatical context, e.g. disambiguation of the recognition hypotheses based on word sequence rules
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 25/51 for comparison or discrimination
• CPC Class Codes: G10L 25/63 for estimating an emotional state
• CPC Class Codes: G10L 25/66 for extracting parameters related to health condition detecting or measuring for diagnostic purposes A61B5/00
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

The methods, apparatus, and systems described herein assist a user with a request. The methods in part retrieve or determine a personality type of the user from three or more personality types based on one or more user communications, determine a set of outputs based on the user communication, rank outputs based on the user'"'"'s personality, engage with an external service to perform an action based on the communication, and determine a distress level or engagement level of the user, or both, based on the ranked and selected output and the modality of delivery, and weight the ranked and selected outputs for one or more future interactions with the user.

Claims

1. A system adapted to communicate with a user, which comprises:

a node comprising a processor and a non-transitory computer readable medium operably coupled 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 voice communication from a client device;

instructions that, when executed, convert the voice communication to text;

instructions that, when executed, apply a linguistic-based algorithm to the text to determine a personality type of the user or retrieve the personality type of the user, the retrieved personality type determined by application of the linguistic-based algorithm to a prior text converted from a prior voice communication of the user, from three or more personality types;

instructions that, when executed, determine a set of outputs based on the personality type of the user;

instructions that, when executed, rank the outputs from the set of outputs based on the personality type of the user;

instructions that, when executed, engage with an external service to perform, on the client device, an action from one of the ranked outputs;

instructions that, when executed, determine a distress level or engagement level of the user, or both, based on the determined and ranked outputs and a modality of delivery of the action;

instructions that, when executed, predict user input based on the received voice communication;

instructions that, when executed, select an output from the determined and ranked outputs to address the predicted user input;

instructions that, when executed, determine that the selected output addressing the predicted user input is a success;

instructions that, when executed, aggregate determined successes based on repeated user communications; and

instructions that, when executed, prioritize future ranked outputs for the user based on the determined distress level or engagement level of the user and the aggregated determined successes.

2. The system of claim 1, further comprising instructions that, when executed, extract one or more communication attributes from the text.

3. The system of claim 2, wherein each communication attribute comprises tone, tempo, pattern of speech, syntax, grammar, or any combination thereof.

4. The system of claim 1, further comprising instructions that, when executed, rank user input to prioritize inputs for the user.

5. The system of claim 1, wherein the personality type is retrieved from a pre-existing user profile.

6. The system of claim 1, wherein the instructions that apply a linguistic-based algorithm to the text to determine a personality type of the user, or retrieve the personality type of the user, are based on four or more personality types.

7. The system of claim 1, wherein the linguistic-based algorithm searches for keywords in the text and a density of those keywords in the text to determine the personality type of the user.

18. The system of claim 1, wherein the determined successes are based on a response of the user to the output.

8. A method for communicating with a user, which comprises:

receiving a user voice communication from a client device;

converting the voice communication to text;

applying a linguistic-based algorithm to the text to determine a personality type of the user, or retrieving the personality type of the user, the retrieved personality type determined by application of the linguistic-based algorithm to a prior text converted from a prior voice communication of the user, from three or more personality types;

determining a set of outputs based on the personality type of the user;

ranking the outputs from the set of outputs based on the personality type of the user;

engaging with an external service to perform, on the client device, an action from one of the ranked outputs;

determining a distress level or engagement level of the user, or both, based on the determined and ranked set of outputs and a modality of delivery of the action;

predicting user input based on the received voice communication;

selecting an output from the determined and ranked outputs to address the predicted user input;

determining that the selected output addressing the predicted user input is a success;

aggregating determined successes based on repeated user communications; and

prioritizing future ranked outputs for the user based on the determined distress level or engagement level of the user and the aggregated determined successes.

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

10. The method of claim 9, wherein each communication attribute is select comprise tone, tempo, pattern of speech, syntax, grammar, or any combination thereof.

11. The method of claim 8, which further comprises ranking user input to prioritize inputs for the user.

12. The method of claim 8, wherein the personality type is retrieved from a pre-existing user profile.

13. The method of claim 8, wherein the applying a linguistic-based algorithm to the text to determine a personality type of the user, or retrieving the personality type of the user, is based on four or more personality types.

14. The method of claim 8, wherein the linguistic-based algorithm searches for keywords in the text and a density of those keywords in the text to determine the personality type of the user.

15. The method of claim 8, wherein the success determination is based on a response of the user to the output.

16. A method for assisting a user;

which comprises;

receiving, by one or more processors, at least one input from the user on a client device;

applying, by one or more processors, a linguistic-based algorithm to the at least one input to determine a personality type of the user, or retrieving, by one or more processors, the personality type of the user, the retrieved personality type determined by application of the linguistic-based algorithm to a prior input from the user;

determining, by one or more processors, a set of outputs based on the at least one input from the user;

ranking, by one or more processors, the outputs from the set of outputs based on the personality type of the user;

engaging with an external service to perform, on the client device, an action from one of the ranked outputs;

determining a distress level or engagement level of the user, or both, based on the determined and ranked outputs and a modality of delivery of the action;

predicting user input based on the received at least one input;

selecting an output from the determined and ranked outputs to address the predicted user input;

determining that the selected output addressing the predicted user input is a success;

aggregating determined successes based on repeated user communications; and

prioritizing future ranked outputs for the user based on the determined distress level or engagement level of the user and the aggregated determined successes.

19. The method of claim 16, wherein the linguistic-based algorithm searches for keywords in the at least one input and a density of those keywords in the at least one input to determine the personality type of the user.

17. A non-transitory computer readable medium comprising a plurality of instructions comprising:

instructions that;

when executed, receive input from a user on a client device;

instructions that;

when executed, apply a linguistic-based algorithm to a text of the user input to determine a personality type of the user or retrieve the personality type of the user, the retrieved personality type determined by application of the linguistic-based algorithm to a prior text of the user input;

instructions that;

when executed, extract at least one attribute from the input;

instructions that, when executed, engage with an external service to perform, on the client device;

an action from outputs based on the input from the user;

instructions that, when executed, determine a distress level or engagement level of the user, or both, based on the determined personality type and the at least one attribute and a modality of delivery of the action;

instructions that, when executed, predict user input based on the received input;

instructions that, when executed, select an output from the outputs to address the predicted user input;

instructions that, when executed, determine that the selected output addressing the predicted user input is a success;

instructions that, when executed, aggregate determined successes based on repeated user communications; and

instructions that;

when executed, prioritize future ranked outputs for the user based on the determined distress level or engagement level and the aggregated determined successes.