AUTOMATED ASSISTANT CONTEXT AND PROTOCOL

• US 20200133629A1
• Filed: 10/25/2018
• Published: 04/30/2020
• Est. Priority Date: 10/25/2018
• Status: Active Grant

• Current Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Original Assignee: AT&T Intellectual Property I LP (AT&T, Inc.)
• Inventors: Pratt, James, Huet, Miranda, Knotts, William, Zavesky, Eric
• Granted Patent: US 11,481,186 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: H04L 67/01 Protocols
• CPC Class Codes: H04L 67/12 specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Virtual assistants (VAs) can be managed in interactions with communication devices (and associated users) or other VAs. A communication management component (CMC) can track an interaction between a VA and a communication device of a user or another VA with regard to an event. The CMC can analyze information relating to the interaction to determine a context of the interaction. The CMC can manage the VA, the involvement of the communication device in the interaction, or the other VA based on the context. When indicated by the context, the CMC can modify characteristics associated with the VA to enhance the interaction. When another communication device or another VA enter the interaction in progress, the CMC can determine interaction update information, based on the tracking of the interaction, and can communicate the interaction update information to the other communication device (and associated user) or other VA.

Claims

1. A method, comprising:

analyzing, by a system comprising a processor, information relating an interaction between a virtual assistant device and a device associated with a user identity to determine a context of the interaction; and

managing, by the system, the virtual assistant device based on the context of the interaction, wherein the managing comprises managing a speed of a presentation of audible words by the virtual assistant device to the device associated with the user identity based on the context.

2. The method of claim 1, wherein the virtual assistant device is a first virtual assistant device, and wherein the method further comprises:

determining, by the system, that a second virtual assistant device is to communicate event information relating to an event associated with the user identity, wherein the second virtual assistant device is remote from the first virtual assistant device and is associated with the user identity; and

in response to determining that the second virtual assistant device is to communicate the event information, determining, by the system, that a portion of the event information is to be communicated, in a non-verbal form, between the second virtual assistant device and the first virtual assistance device.

3. The method of claim 2, wherein the determining that the second virtual assistant device is to communicate the event information comprises determining that the second virtual assistant device is to communicate the event information based on at least one attribute associated with the second virtual assistant device, and wherein the at least one attribute is from a group of attributes comprising a performance attribute associated with the second virtual assistant device, a network attribute associated with the second virtual assistant device, an identifier presented by the second virtual assistant device, and an attribute associated with the context.

4. The method of claim 2, further comprising:

managing, by the system, a communication speed of the communicating of the portion of the event information between the second virtual assistant device and the first virtual assistance device to communicate the portion of the event information between the second virtual assistant device and the first virtual assistance device at a faster speed than the speed of the presentation of the audible words by the first virtual assistant device to the device.

5. The method of claim 2, wherein the portion of the event information is a first portion of the event information, wherein the first portion of the event information comprises a second portion of the event information, and wherein the method further comprises:

initiating, by the system, presenting the second portion of the event information via an interface associated with the second virtual assistant device.

6. The method of claim 1, wherein the information relating the interaction is first information relating to the interaction, wherein the context is a first context, and wherein the method further comprises:

determining, by the system, a second context of the interaction based on the first information and second information relating to the interaction.

7. The method of claim 6, wherein the device is a first device, wherein the user identity is a first user identity, and wherein the method further comprises:

based on the second context;

determining, by the system, that the virtual assistant device is to suspend the presentation of the audible words to the device, wherein the audible words relate to an event; and

determining, by the system, that event information relating to the event is to be communicated between the first device associated with the first user identity and a second device associated with a second user identity.

8. The method of claim 7, wherein the event information comprises a first portion of the event information and a second portion of the event information, and wherein the method further comprises:

during a first time period, tracking, by the system, communication of the first portion of the event information between the virtual assistant device and the device associated with the user identity, wherein the first portion of the event information comprises the audible words relating to the event;

during a second time period, in response to determining that the second portion of the event information is to be communicated between the first device and the second device, communicating, by the system, a third portion of the event information to the second device or an interface associated with the second identity to facilitate providing a status of the interaction to the second device or the interface, wherein the third portion of the event information is determined based on the tracking of the communication of the first portion of the event information between the virtual assistant device and the device.

9. The method of claim 6, wherein the virtual assistant device is a first virtual assistant device, wherein the audible words relate to an event, wherein a second virtual assistant device is remote from the first virtual assistant device and is associated with the device that is associated with the user identity, and wherein the method further comprises:

based on the second context;

determining, by the system, that a portion of event information relating to the event is to be communicated, in a non-verbal form, between the second virtual assistant device and the first virtual assistance device simultaneously with the presentation of the audible words by the first virtual assistant device to the device.

10. The method of claim 6, wherein the second context occurs at a second time subsequent to a first time associated with the first context, wherein the second context relates to at least one circumstance of a group of circumstances comprising a consent is to be obtained from the device associated with the user identity, a length of time that has transpired since receiving a response to an inquiry from the device, a number of times that the inquiry has been communicated to the device without the response being received by the virtual assistant device from the device, a first portion of event information relating to an event associated with the user identity is to be obtained in audible word form from the device, and a second portion of the event information is able to be communicated in a non-verbal form between virtual assistant devices, comprising the virtual assistant device, and

wherein the managing of the virtual assistant device comprises, at the second time, managing the virtual assistant device based on the second context.

11. The method of claim 1, further comprising:

based on the context, modifying, by the system, at least one parameter relating to the presentation of the audible words by the virtual assistant device to the device to modify at least one characteristic of the presentation of the audible words.

12. The method of claim 11, wherein the at least one characteristic is selected from a group of characteristics comprising the speed of the presentation of the audible words by the virtual assistant device to the device, a tone of an emulated voice of the virtual assistant device in connection with the presentation of the audible words, an inflection of the emulated voice of the virtual assistant device in connection with the presentation of the audible words, and a cadence of the emulated voice of the virtual assistant device in connection with the presentation of the audible words.

13. A system, comprising:

a processor; and

a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising;

analyzing information relating an interaction between a virtual assistant device and a device associated with a user identity to determine a context of the interaction; and

controlling operation of the virtual assistant device based on the context of the interaction, wherein the controlling comprises controlling, based on the context, a rate of a presentation of verbal words by the virtual assistant device to the device.

14. The system of claim 13, wherein the virtual assistant device is a first virtual assistant device, and wherein the operations comprise:

determining that a second virtual assistant device is to communicate event data relating to an event associated with the user identity, wherein the second virtual assistant device is remote from the first virtual assistant device and is associated with the user identity; and

in response to determining that the second virtual assistant device is to communicate the event data, determining that a portion of the event data is to be communicated, in a non-verbal form, between the second virtual assistant device and the first virtual assistance device.

15. The system of claim 14, wherein the rate is a first rate, and wherein the operations comprise:

controlling a second rate of the communication of the portion of the event data between the second virtual assistant device and the first virtual assistance device to communicate the portion of the event data between the second virtual assistant device and the first virtual assistance device at a higher rate than the first rate of the presentation of the verbal words by the first virtual assistant device to the device.

16. The system of claim 13, wherein the information relating the interaction is first information relating to the interaction, wherein the context is a first context, and wherein the operations comprise:

determining a second context of the interaction based on the first information and second information relating to the interaction.

17. The system of claim 16, wherein the device is a first device and the user identity is a first user identity, and wherein the operations comprise:

based on the second context;

determining that the virtual assistant device is to discontinue the presentation of the verbal words to the device, wherein the verbal words relate to an event; and

determining that event data relating to the event is to be communicated between the first device associated with the first user identity and a second device associated with a second user identity, wherein at least a portion of the event data is communicated, in verbal word form, between the first device and the second device.

18. The system of claim 13, wherein the operations comprise:

based on the context, adjusting at least one parameter relating to the presentation of the verbal words by the virtual assistant device to the device to adjust at least one attribute of the presentation of the verbal words, wherein the at least one attribute is selected from a group of attributes comprising the rate of the presentation of the verbal words by the virtual assistant device to the device, a tone of a virtual voice of the virtual assistant device in connection with the presentation of the verbal words, an inflection of the virtual voice of the virtual assistant device in connection with the presentation of the verbal words, and a cadence of the virtual voice of the virtual assistant device in connection with the presentation of the verbal words.

19. A machine-readable storage medium, comprising executable instructions that, when executed by a processor, facilitate performance of operations, comprising:

analyzing data relating an interaction between a virtual assistant device and a device associated with a user identity to determine a context of the interaction; and

managing operation of the virtual assistant device based on the context of the interaction, wherein the managing comprises managing, based on the context, a speed of a presentation of verbal words by the virtual assistant device to the device.

20. The machine-readable storage medium of claim 19, wherein the operations further comprise:

based on the context, modifying at least one parameter relating to the presentation of the verbal words by the virtual assistant device to the device to modify at least one characteristic of the presentation of the verbal words, wherein the at least one characteristic is selected from a group of characteristics comprising the speed of the presentation of the verbal words by the virtual assistant device to the device, a tone of a virtual voice of the virtual assistant device in connection with the presentation of the verbal words, an inflection of the virtual voice of the virtual assistant device in connection with the presentation of the verbal words, and a cadence of the virtual voice of the virtual assistant device in connection with the presentation of the verbal words.