Intelligent conversational messaging

• US 9,761,222 B1
• Filed: 06/10/2015
• Issued: 09/12/2017
• Est. Priority Date: 06/11/2014
• Status: Active Grant

• Current Assignee: Albert Scarasso
• Original Assignee: Albert Scarasso
• Inventors: Scarasso, Albert, Alda, Enzo
• Primary Examiner(s): Sharma, Neeraj
• Application Number:
  US14/736,140
• Time in Patent Office: 825 Days
• Field of Search: 704240, 704257, 704258, 704270, 704201, 704236, 704 9, 707769, 707694, 707737, 726 1, 726 26, 726 23, 705 35, 715706, 706 47, 706 46, 434236, 709219, 711147
• CPC Class Codes: G06F 40/20 Natural language analysis semantic analysis of natural language G06F40/30
• CPC Class Codes: G06F 40/30 Semantic analysis
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection
• CPC Class Codes: G10L 15/07 to the speaker
• 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 51/00 User-to-user messaging in packet-switching networks, transmitted according to store-and-forward or real-time protocols, e.g. e-mail
• CPC Class Codes: H04L 51/02 using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages

Abstract

A system for implementing a computer-based assistance in a conversation can comprise determining an identification indication associated with a first participant in a conversation. The system can also comprise accessing, within a database, user information associated with the identification indication. The user information can comprise data relating to the first participant. Based upon the user information and one or more words communicated in the conversation, the system can include calculating one or more probabilities that the conversation is associated with one or more respective conversation types. Based upon a determined conversation type, the system can activate an expert agent in the conversation. The expert agent can comprise a virtual conversation participant that is associated with a goal. The system can also comprise executing a sequential lists of actions that are associated with the goal, wherein the list of actions comprises interactions with the first participant.

Claims

1. A computer system, comprising:

one or more processors;

system memory; and

one or more computer-readable media storing computer-executable instructions that, when executed by the one or more processors, cause the computer system to implement a method for a goal-driven computer-based assistant in a conversation, the method comprising;

determining an identification indication associated with a first participant in a conversation;

accessing, within a database, user information associated with the identification indication, wherein the user information comprises data relating to the first participant;

receiving through a conversation bridge one or more words communicated from a user;

mapping the one or more words to a repository of predefined conversation types, wherein each predefined conversation type is associated with a goal process that comprises a finite state network that moves through a plurality of states to reach a particular end state that is associated with the respective predefined conversation type;

based upon the user information and the mapping of the one or more words to the predefined conversation types, calculating one or more probabilities that the conversation is associated with one or more predefined conversation types;

causing a digital display screen to display a list of suggested conversation types, wherein the list is periodically reordered based upon updates regarding probabilities that the conversation is associated with the one or more predefined conversation types;

receiving an indication that the conversation is a particular type of conversation, wherein the received indication comprises a selection of the particular type of conversation from the display list;

based upon the selected particular conversation type, activating an expert agent in the conversation, wherein the expert agent comprises a virtual conversation participant that is associated with the goal process, wherein;

each state within the plurality of states is associated with business rules; and

executing actions that are associated with the goal process, wherein the actions comprise communicating to the first participant through the conversation bridge.

2. The system as recited in claim 1, wherein the identification indication is a messaging system identification.

3. The system as recited in claim 1, wherein the expert agent communicates with one or more participants in the conversation.

4. The system as recited in claim 3, wherein the expert agent communicates with a participant in the conversation without one or more other participants being aware of the communication.

5. The system as recited in claim 1, further comprising:

requesting, through the expert agent, participant information from the first participant; and

based upon an analysis of the participant information, determining a subsequent action for the expert agent.

6. The system as recited in claim 1, further comprising:

identifying the occurrence of a particular event, wherein the particular event is associated with the goal process; and

initiating an action from the sequential list of actions based upon the occurrence of a particular event.

7. The system as recited in claim 6, wherein the particular event occurs after the conversation is completed.

8. The system as recited in claim 6, wherein the particular event comprises an equity fund reaching a particular value.

9. The system as recited in claim 1, further comprising:

identifying, with the expert agent, a particular conversation component; and

in response to the conversation component, connecting a second participant to the conversation.

10. The system as recited in claim 9, wherein the particular conversation component comprises a breach of compliance rules.

11. The system as recited in claim 9, wherein the second participant comprises a human compliance officer.

18. The system as recited in claim 10, further comprising:

identifying, with the expert agent, a particular conversation component; and

in response to the conversation component, connecting a second participant to the conversation.

19. The system as recited in claim 18, wherein the particular conversation component comprises a breach of compliance rules.

12. A computer-implemented method for automating a computer assistant within a conversation, the method comprising:

determining an identification indication associated with a first participant in a conversation;

accessing, within a database, user information associated with the identification indication, wherein the user information comprises data relating to the first participant;

receiving through a conversation bridge one or more words communicated from a user;

mapping the one or more words to a repository of predefined conversation types, wherein each predefined conversation type is associated with a goal process that comprises a finite state network that moves through a plurality of states to reach a particular end state that is associated with the respective predefined conversation type;

based upon the user information and the mapping of the one or more words to the predefined conversation types, calculating one or more probabilities that the conversation is associated with one or more predefined conversation types;

causing a digital display screen to display a list of suggested conversation types, wherein the list is periodically reordered based upon updates regarding probabilities that the conversation is associated with the one or more predefined conversation types;

receiving an indication that the conversation is a particular type of conversation, wherein the received indication comprises a selection of the particular type of conversation from the display list;

based upon the selected particular conversation type, activating an expert agent in the conversation, wherein the expert agent comprises a virtual conversation participant that is associated with the goal process, wherein;

the goal process comprises a finite state network that moves through a plurality of states to reach a particular end state, and

each state within the plurality of states is associated with business rules; and

executing actions that are associated with the goal process, wherein the actions comprise communicating to the first participant through the conversation bridge.

13. The method as recited in claim 12, wherein the expert agent communicates with one or more participants in the conversation.

14. The method as recited in claim 13, wherein the expert agent communicates with a participant in the conversation without one or more other participants being aware of the communication.

15. The method as recited in claim 12, further comprising:

requesting, through the expert agent, participant information from the first participant; and

based upon an analysis of the participant information, determining a subsequent action for the expert agent.

16. The method as recited in claim 12, further comprising:

identifying the occurrence of a particular event, wherein the particular event is associated with the goal process; and

initiating an action from the sequential list of actions based upon the occurrence of a particular event.

17. The system as recited in claim 16, wherein the particular event occurs after the conversation is completed.

20. One or more computer storage devices having stored thereon computer-executable instructions that, when executed at a processor, cause the computer system to perform a method for automating a computer assistant within a conversation, the method comprising:

determining an identification indication associated with a first participant in a conversation;

accessing, within a database, user information associated with the identification indication, wherein the user information comprises data relating to the first participant;

receiving through a conversation bridge one or more words communicated from a user;

mapping the one or more words to a repository of predefined conversation types, wherein each predefined conversation type is associated with a goal process that comprises a finite state network that moves through a plurality of states to reach a particular end state that is associated with the respective predefined conversation type;

based upon the user information and the mapping of the one or more words to the predefined conversation types, calculating one or more probabilities that the conversation is associated with one or more predefined conversation types;

causing a digital display screen to display a list of suggested conversation types, wherein the list is periodically reordered based upon updates regarding probabilities that the conversation is associated with the one or more predefined conversation types;

receiving an indication that the conversation is a particular type of conversation, wherein the received indication comprises a selection of the particular type of conversation from the display list;

based upon the selected particular conversation type, activating an expert agent in the conversation, wherein the expert agent comprises a virtual conversation participant that is associated with the goal process, wherein;

the goal process comprises a finite state network that moves through a plurality of states to reach a particular end state, and

each state within the plurality of states is associated with business rules; and

executing actions that are associated with the goal process, wherein the actions comprise communicating to the first participant through the conversation bridge.