Persona-based conversational interface personalization using social network preferences

• US 10,339,931 B2
• Filed: 10/04/2017
• Issued: 07/02/2019
• Est. Priority Date: 10/04/2017
• Status: Active Grant

• Current Assignee: Toronto-Dominion Bank
• Original Assignee: Toronto-Dominion Bank
• Inventors: Tseretopoulos, Dean C. N., McCarter, Robert Alexander, Walia, Sarabjit Singh, Lalka, Vipul Kishore, Moretti, Nadia, Dickie, Paige Elyse, Kuruvilla, Denny Devasia, Dunjic, Milos, D'Agostino, Dino Paul, Jagga, Arun Victor, Lee, John Jong-Suk, Jethwa, Rakesh Thomas
• Primary Examiner(s): Pullias, Jesse S
• Application Number:
  US15/725,060
• Publication Number:
  US 20190103102A1
• Time in Patent Office: 636 Days
• Field of Search: 704 1, 704 9, 704 10, 704257, 704270-275
• CPC Class Codes: G06F 40/35 Discourse or dialogue representation
• CPC Class Codes: G06F 40/56 Natural language generation
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 40/00 Finance; Insurance; Tax strategies; Processing of corporate or income taxes
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: G10L 15/1807 using prosody or stress
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

The present disclosure involves systems, software, and computer implemented methods for personalizing interactions within a conversational interface based on an input context. One example system performs operations including receiving a conversational input via a conversational interface associated with a particular user profile. The input is analyzed via a natural language processing engine to determine an intent and a personality input type. A persona response type associated with the determined personality input type is identified, and responsive content is determined. A particular persona associated with the particular user profile based on a related set of social network activity information associated with the user profile and that corresponds to the identified persona response type is identified. The responsive content is modified by applying persona-related content associated with the identified particular persona to generate a persona-associated response, and the persona-associated response is transmitted to a device associated with the particular user profile.

Claims

1. A system comprising:

a communications module;

at least one memory storing instructions, a plurality of user profiles, and a repository of persona-related contextual content associated with a plurality of personas, the persona-related contextual content for use in personalizing at least one response generated in response to a conversational contextual input; and

at least one hardware processor interoperably coupled with the at least one memory and the communications module, wherein the instructions instruct the at least one hardware processor to;

receive, via the communications module, a first signal including a conversational input received via interactions with a conversational interface, the conversational input associated with a particular user profile, wherein the particular user profile is associated with a set of social network activity information;

analyze the received conversational input via a natural language processing engine to determine an intent of the received conversational input and to determine a personality input type of the received conversational input;

identify a persona response type associated with the determined personality input type;

determine a set of response content responsive to the determined intent of the received conversational input;

identify a particular persona associated with the particular user profile based on the set of social network activity information, the identified particular persona corresponding to the identified persona response type, where the particular persona is associated with a set of persona-related content;

modify the set of response content using at least a portion of the persona-related content to generate a persona-associated response; and

transmit, via the communications module, a second signal including the persona-associated response to a device associated with the particular user profile for presentation in response to the received conversational input.

2. The system of claim 1, wherein the determined personality input type is one of a plurality of predefined personality input types, wherein each predefined personality input type is mapped to a persona response type.

3. The system of claim 1, wherein identifying a particular persona associated with the particular user profile is further based on at least one of a current context of the particular user profile, a financial history of the particular user profile, and a financial analysis associated with the particular user profile.

4. The system of claim 1, wherein the determined intent associated with the received conversational input is associated with a question, and wherein determining the set of response content responsive to the determined intent of the received conversational input comprises determining a responsive answer to the question.

5. The system of claim 4, wherein the responsive answer to the question is associated with a preferred action to be performed by the user associated with the particular user profile, and wherein identifying the particular persona associated with the particular user profile based on the associated set of social network activity includes identifying the particular persona based on the preferred action to be performed by the user.

6. The system of claim 1, wherein the set of social network activity information is stored remotely from the particular user profile, wherein the particular user profile is associated with at least one social network account, and wherein the set of social network activity is accessed in response to the conversational input and prior to identifying the particular persona associated with the particular user profile.

7. The system of claim 1, wherein the set of social network activity information identifies at least one social network account followed by, liked, or subscribed to by the particular user profile, and wherein identifying the particular persona associated with the particular user profile comprises identifying a particular persona from the plurality of personas corresponding to the at least one social network account followed by, liked, or subscribed to by the particular user profile.

8. The system of claim 1, wherein the set of social network activity information identifies at least one social network account with which the particular user profile has previously had a positive interaction, and wherein identifying the particular persona associated with the particular user profile comprises identifying a particular persona from the plurality of personas corresponding to the at least one social network account with which the particular user profile has had the positive interaction.

9. The system of claim 1, wherein, for each of the personas, the persona-related contextual content includes a set of common phrases or words associated with the particular persona, and wherein modifying the set of response content using at least a portion of the persona-related contextual content to generate a persona-associated response for the particular user comprises incorporating at least one common phrase or word associated with the identified particular persona into the set of response content.

10. The system of claim 9, wherein incorporating the at least one common phrase or word associated with the identified particular persona into the set of response content comprises replacing at a portion of the set of response content with at least one common phrase or word associated with the identified particular persona.

11. The system of claim 1, wherein, for at least some of the personas, the persona-related contextual content includes a voice associated with the persona, and wherein modifying the set of response content using at least a portion of the persona-related contextual content to generate a persona-associated response for the particular user comprises generating an audio file for use in presenting the set of response content spoken in the voice associated with the identified particular persona.

12. A non-transitory, computer-readable medium storing computer-readable instructions executable by a computer and configured to:

receive, via a communications module, a first signal including a conversational input received via interactions with a conversational interface, the conversational input associated with a particular user profile, wherein the particular user profile is associated with a set of social network activity information;

analyze the received conversational input via a natural language processing engine to determine an intent of the received conversational input and to determine a personality input type of the received conversational input;

identify a persona response type associated with the determined personality input type;

determine a set of response content responsive to the determined intent of the received conversational input;

identify a particular persona from a plurality of personas associated with the particular user profile based on the set of social network activity information, the identified particular persona corresponding to the identified persona response type, where each of the plurality of personas are associated with persona-related contextual content for use in personalizing at least one response generated in response to a conversational contextual input, and wherein the particular persona is associated with a set of persona-related content;

modify the set of response content using at least a portion of the persona-related content associated with the identified particular persona to generate a persona-associated response; and

transmit, via the communications module, a second signal including the persona-associated response to a device associated with the particular user profile for presentation in response to the received conversational input.

13. The computer-readable medium of claim 12, wherein the determined personality input type is one of a plurality of predefined personality input types, wherein each predefined personality input type is mapped to a persona response type.

14. The computer-readable medium of claim 12, wherein identifying a particular persona associated with the particular user profile is further based on at least one of a current context of the particular user profile, a financial history of the particular user profile, and a financial analysis associated with the particular user profile.

15. The computer-readable medium of claim 12, wherein the determined intent associated with the received conversational input is associated with a question, and wherein determining the set of response content responsive to the determined intent of the received conversational input comprises determining a responsive answer to the question, wherein the responsive answer to the question is associated with a preferred action to be performed by the user associated with the particular user profile, and wherein identifying the particular persona associated with the particular user profile based on the associated set of social network activity includes identifying the particular persona based on the preferred action to be performed by the user.

16. The computer-readable medium of claim 12, wherein the set of social network activity information is stored remotely from the particular user profile, wherein the particular user profile is associated with at least one social network account, and wherein the set of social network activity is accessed in response to the conversational input and prior to identifying the particular persona associated with the particular user profile.

17. The computer-readable medium of claim 12, wherein the set of social network activity information identifies at least one social network account followed by, liked, or subscribed to by the particular user profile, and wherein identifying the particular persona associated with the particular user profile comprises identifying a particular persona from the plurality of personas corresponding to the at least one social network account followed by, liked, or subscribed to by the particular user profile.

18. The computer-readable medium of claim 12, wherein, for each of the personas, the persona-related contextual content includes a set of common phrases or words associated with the particular persona, and wherein modifying the set of response content using at least a portion of the persona-related contextual content to generate a persona-associated response for the particular user comprises incorporating at least one common phrase or word associated with the identified particular persona into the set of response content.

19. The computer-readable medium of claim 18, wherein incorporating the at least one common phrase or word associated with the identified particular persona into the set of response content comprises replacing at a portion of the set of response content with at least one common phrase or word associated with the identified particular persona.

20. A computerized method performed by one or more processors, the method comprising:

receiving, via a communications module, a first signal including a conversational input received via interactions with a conversational interface, the conversational input associated with a particular user profile, wherein the particular user profile is associated with a set of social network activity information;

analyzing the received conversational input via a natural language processing engine to determine an intent of the received conversational input and to determine a personality input type of the received conversational input;

identifying a persona response type associated with the determined personality input type;

determining a set of response content responsive to the determined intent of the received conversational input;

identifying a particular persona from a plurality of personas associated with the particular user profile based on the set of social network activity information, the identified particular persona corresponding to the identified persona response type, where each of the plurality of personas are associated with persona-related contextual content for use in personalizing at least one response generated in response to a conversational contextual input, and wherein the particular persona is associated with a set of persona-related content;

modifying the set of response content using at least a portion of the persona-related content associated with the identified particular persona to generate a persona-associated response; and

transmitting, via the communications module, a second signal including the persona-associated response to a device associated with the particular user profile for presentation in response to the received conversational input.