Granted Patent B2

US 12,361,932 · App. 18/333,573 · Granted Jul 15, 2025

Inventors: Irene Lizeth Manotas Gutiérrez (White Plains, NY); Ra'eesa Kabir (Birmingham, GB); Jonathan D. Dunne (Dungarvan, IE)

Assignee: International Business Machines Corporation

G10L15/1815G10L15/22

Abstract

Claims (61)

1. A processor-implemented method for human-machine interfacing, the method comprising:

receiving, by a processor, a personality corpus associated with a personality typology comprising multiple personality types;

extracting, by a processor, a plurality of utterances from a user;

selecting, by a personality model, a personality type associated with the user based on the utterances and the personality corpus;

identifying, by a processor, a compatible personality type of the selected personality type;

constructing, by a processor, one or more natural language scripts from a word graph associated with the compatible personality type; and

transmitting, by a processor, the one or more natural language scripts to the user.

2. The method of claim 1 , wherein the personality model is selected from a plurality of specialized personality models based on the personality typology.

3. The method of claim 1 , wherein the generated natural language script exceeds an alignment threshold according to a Cohen's Kappa hypothesis test.

4. The method of claim 1 , further comprising: updating the word graph with the plurality of chat utterances, the linguistic data, and/or the personality information.

5. The method of claim 1 , wherein the selecting comprises scoring a plurality of items of linguistics data based on an alignment with a personality type of the multiple personality types.

6. The method of claim 5 , wherein the selecting further comprises selecting a personality type based on the collective scoring of the plurality of items of linguistics data.

7. The method of claim 1 , wherein the identified compatible personality type has a highest compatibility level of a plurality of compatible personality types of the selected personality type.

8. A computer system for human-machine interfacing, the computer system comprising:

one or more processors, one or more computer-readable memories, one or more computer-readable tangible storage medium, and program instructions stored on at least one of the one or more tangible storage medium for execution by at least one of the one or more processors via at least one of the one or more memories, wherein the computer system is capable of performing a method comprising:

receiving a personality corpus associated with a personality typology comprising multiple personality types;

extracting a plurality of utterances from a user;

selecting, by a personality model, a personality type associated with the user based on the utterances and the personality corpus;

identifying a compatible personality type of the selected personality type;

constructing one or more natural language scripts from a word graph associated with the compatible personality type; and

transmitting the one or more natural language scripts to the user.

9. The computer system of claim 8 , wherein the personality model is selected from a plurality of specialized personality models based on the personality typology.

10. The computer system of claim 8 , wherein the generated natural language script exceeds an alignment threshold according to a Cohen's Kappa hypothesis test.

11. The computer system of claim 8 , further comprising: updating the word graph with the plurality of chat utterances, the linguistic data, and/or the personality information.

12. The computer system of claim 8 , wherein the selecting comprises scoring a plurality of items of linguistics data based on an alignment with a personality type of the multiple personality types.

13. The computer system of claim 12 , wherein the selecting further comprises selecting a personality type based on the collective scoring of the plurality of items of linguistics data.

14. The computer system of claim 8 , wherein the identified compatible personality type has a highest compatibility level of a plurality of compatible personality types of the selected personality type.

15. A computer program product for human-machine interfacing, the computer program product comprising:

one or more computer-readable tangible storage medium and program instructions stored on at least one of the one or more tangible storage medium, the program instructions executable by a processor to cause the processor to perform a method comprising:

receiving a personality corpus associated with a personality typology comprising multiple personality types;

extracting a plurality of utterances from a user;

selecting, by a personality model, a personality type associated with the user based on the utterances and the personality corpus;

identifying a compatible personality type of the selected personality type;

constructing one or more natural language scripts from a word graph associated with the compatible personality type; and

transmitting the one or more natural language scripts to the user.

16. The computer program product of claim 15 , wherein the personality model is selected from a plurality of specialized personality models based on the personality typology.

17. The computer program product of claim 15 , wherein the generated natural language script exceeds an alignment threshold according to a Cohen's Kappa hypothesis test.

18. The computer program product of claim 15 , further comprising: updating the word graph with the plurality of chat utterances, the linguistic data, and/or the personality information.

19. The computer program product of claim 15 , wherein the selecting comprises scoring a plurality of items of linguistics data based on an alignment with a personality type of the multiple personality types.

20. The computer program product of claim 19 , wherein the selecting further comprises selecting a personality type based on the collective scoring of the plurality of items of linguistics data.

21. A processor-implemented method for human-machine interfacing, the method comprising:

receiving a personality corpus associated with a personality typology comprising multiple personality types;

receiving a plurality of utterances from a user;

receiving a plurality of context information;

selecting a personality type associated with the user based on the personality corpus and the utterances;

selecting a chatbot of a plurality of chatbots associated with a personality type compatible with the selected personality type based on the context information;

constructing, by the selected chatbot, one or more natural language scripts; and

transmitting the one or more natural language scripts to the user.

22. The method of claim 21 , wherein the plurality of chatbots are associated with both a personality type of the multiple personality types and a domain inferred from the context information.

23. The method of claim 21 , wherein the selecting is further based on an interface method associated with the chatbot of the plurality of chatbots.

24. The method of claim 23 , wherein the one or more natural language scripts consist of a plurality of elements comprising the plurality of word graphs that passed a Cohen's Kappa hypothesis test.

25. A processor-implemented method for human-machine interfacing, the method comprising:

receiving a personality corpus;

receiving a plurality of context data;

receiving a plurality of chat utterances from a user;

extracting a plurality of linguistics data from the plurality of chat utterances;

inferring a plurality of personality information from the linguistics data;

selecting a personality type associated with the user;

choosing one or more compatible personality type to the selected personality type;

constructing one or more natural language scripts from a word graph associated with at least the chosen personality type and a word graph associated with a domain inferred from the context data; and

transmitting the one or more natural language scripts to the user.

Assignments (1)

Continuity (1)

References Cited (21)