System and method for an adaptive cloud conversation platform
An adaptive cloud conversation platform capable of making automated decisions regarding when and how to establish on-going communications with consumers so as to maximize the relationship between the consumer and a given brand. The system has a connection management services layer which determines what communications should be established and how they should be established, an initiation management services layer which determines when communications should be established, and a user management services layer which stores information about consumers and brands for determination of when and how communications should be established. Certain of these services have machine learning algorithms incorporated into them trained to perform analyses of the particular type of operation handled by that service. The outputs of each service can be used as inputs to other services, such that a network of machine learnings algorithms is created which determines when and how to establish on-going communications with consumers.
1. An adaptive cloud conversation platform, comprising:
a computing device comprising a memory, a processor, and a non-volatile data storage device;
a consumer profile database stored on the non-volatile data storage device, the consumer profile database comprising one or more consumer profiles;
a negotiation manager comprising a first plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive conversation data for a conversation with a consumer, the conversation data comprising current session information regarding an interaction between the consumer and a brand;
receive a determination that a callback to the consumer should be made; and
request and receive a recommended channel for the callback from a conversation manager;
request and receive a recommended time for the callback from a schedule manager;
send a callback offer to the consumer proposing that the callback be made at the recommended time using the recommended channel;
receive approval of the callback offer from the consumer; and
send the approved callback offer to a schedule manager to schedule the callback;
the conversation manager comprising a second plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the request for the recommended channel;
retrieve a consumer profile for the consumer from the consumer profile database, the consumer profile comprising a plurality of preferences of the consumer;
process the plurality of preferences through a first machine learning algorithm to obtain a recommended channel through which to conduct the survey with the consumer; and
send the recommended channel to the negotiation manager;
the schedule manager comprising a third plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the request for the recommended time;
retrieve the consumer profile;
process the plurality of preferences through a second machine learning algorithm to obtain a recommended time at which to conduct the callback with the consumer;
send the recommended time to the negotiation manager;
receive the approved callback offer and schedule a callback to be conducted with the consumer at the selected time through the selected channel; and
forward the callback schedule to a callback manager; and
the callback manager comprising a fourth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the callback schedule; and
execute the callback schedule by conducting the callback at the selected time through the selected channel as indicated in the callback schedule.
2. The platform of claim 1 , wherein the negotiation manager is further configured to:
retrieve the consumer profile;
process the plurality of preferences through a behavioral pairing artificial intelligence engine to obtain a recommended agent for conducting the callback with the consumer; and
include the recommended agent in the callback offer to the consumer.
3. The platform of claim 1 , further comprising a consumer context manager comprising a fifth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the conversation data;
retrieve the consumer profile, the consumer profile further comprising a plurality of behaviors of the consumer;
process the conversation data and the plurality of behaviors of the consumer through a third machine learning algorithm to determine whether a second callback to the consumer should be made; and
where the determination is that a second callback should be made, forward the determination to the conversation manager as the determination that a callback should be made to a consumer.
4. The platform of claim 3 , further comprising a session manager comprising a sixth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the conversation data;
process the conversation data through a fourth machine learning algorithm to determine a consumer sentiment; and
forward the determined sentiment to the consumer context manager as an additional input to the third machine learning algorithm's determination as to whether a callback to the consumer should be made.
5. The platform of claim 3 , wherein:
the conversation manager is further configured to:
process the conversation data through a fifth machine learning algorithm to determine a consumer goal, need, or intent; and
forward the determined goal, need, or intent to the consumer context manager as an additional input to the third machine learning algorithm's determination as to whether a callback to the consumer should be made.
6. The platform of claim 3 , further comprising:
an event rules database stored on the non-volatile data storage device, the event rules database comprising rules for triggering communications with consumers based on events occurring outside of a conversation; and
an event manager comprising a sixth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive notification of an event;
match the event to a rule in the event rules database; and
forward the matched event to the conversation manager as the determination that a callback should be made to the consumer.
7. The platform of claim 6 , wherein:
the event manager is further configured to:
retrieve the consumer profile;
process the consumer profile and one or more rules from the event rules database through an seventh machine learning algorithm to determine a new rule for triggering communications with the consumer; and
store the new rule in the event rules database.
8. The platform of claim 3 , further comprising:
a brand environment database stored on the non-volatile data storage device, the brand environment database comprising brand information related to conversations with consumers of the brand;
an environment manager comprising an eighth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
retrieve the consumer profile;
retrieve the brand information from the brand environment database;
process the consumer profile and the brand information through an eighth machine learning algorithm to determine whether a campaign of communications should be established with a plurality of consumers; and
forward the determination to the conversation manager as the determination that a callback should be made to the consumer.
9. The platform of claim 8 , further comprising:
a consumer manager comprising a ninth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
retrieve the consumer profile for the consumer from the consumer profile database;
receive a fitness parameter from the environment manager;
process the consumer profile and the fitness parameter through a ninth machine learning algorithm to identify opportunities for proactive conversations with the consumer; and
forward the identified to the consumer context manager as an additional input to the first machine learning algorithm's selection of the channel through which the callback should be made.
10. A method for operating an adaptive cloud conversation platform, comprising the steps of:
using a negotiation manager operating on a computing device comprising a memory, a processor, and a non-volatile data storage device to:
receive conversation data for a conversation with a consumer, the conversation data comprising current session information regarding an interaction between the consumer and a brand;
receive a determination that a callback to the consumer should be made; and
request and receive a recommended channel for the callback from a conversation manager;
request and receive a recommended time for the callback from a schedule manager;
send a callback offer to the consumer proposing that the callback be made at the recommended time using the recommended channel;
receive approval of the callback offer from the consumer; and
send the approved callback offer to the schedule manager to schedule the callback;
using a conversation manager operating on the computing device to:
receive the request for the recommended channel;
retrieve a consumer profile for the consumer from a consumer profile database stored on the non-volatile data storage device, the consumer profile database comprising one or more consumer profiles, and the consumer profile comprising a plurality of preferences of the consumer;
process the plurality of preferences through a first machine learning algorithm to obtain a recommended channel through which to conduct the survey with the consumer; and
send the recommended channel to the negotiation manager;
a schedule manager operating on the computing device to:
receive the request for the recommended time;
retrieve the consumer profile;
process the plurality of preferences through a second machine learning algorithm to obtain a recommended time at which to conduct the callback with the consumer;
send the recommended time to the negotiation manager;
receive the approved callback offer and schedule a callback to be conducted with the consumer at the selected time through the selected channel; and
forward the callback schedule to a callback manager; and
a callback manager comprising a fourth plurality of programming instructions stored in the memory which, when operating on the processor, causes the computing device to:
receive the callback schedule; and
execute the callback schedule by conducting the callback at the selected time through the selected channel as indicated in the callback schedule.
11. The method of claim 10 , further comprising the steps of using the negotiation manager to:
retrieve the consumer profile;
process the plurality of preferences through a behavioral pairing artificial intelligence engine to obtain a recommended agent for conducting the callback with the consumer; and
include the recommended agent in the callback offer to the consumer.
12. The method of claim 10 , further comprising the steps of using a consumer context manager operating on the computing device to:
receive the conversation data;
retrieve the consumer profile, the consumer profile further comprising a plurality of behaviors of the consumer;
process the conversation data and the plurality of behaviors of the consumer through a third machine learning algorithm to determine whether a second callback to the consumer should be made; and
where the determination is that a second callback should be made, forward the determination to the conversation manager as the determination that a callback should be made to a consumer.
13. The method of claim 12 , further comprising the steps of using a session manager operating on the computing device to:
receive the conversation data;
process the conversation data through a fourth machine learning algorithm to determine a consumer sentiment; and
forward the determined sentiment to the consumer context manager as an additional input to the third machine learning algorithm's determination as to whether a callback to the consumer should be made.
14. The method of claim 12 , further comprising the steps of:
using the conversation manager to:
process the conversation data through a fifth machine learning algorithm to determine a consumer goal, need, or intent; and
forward the determined goal, need, or intent to the consumer context manager as an additional input to the third machine learning algorithm's determination as to whether a callback to the consumer should be made.
15. The method of claim 12 , further comprising the steps of:
creating an event rules database on the non-volatile data storage device, the event rules database comprising rules for triggering communications with consumers based on events occurring outside of a conversation; and
using an event manager operating on the computing device to:
receive notification of an event;
match the event to a rule in the event rules database; and
forward the matched event to the conversation manager as the determination that a callback should be made to the consumer.
16. The method of claim 15 , further comprising the steps of:
using the event manager to:
retrieve the consumer profile;
process the consumer profile and one or more rules from the event rules database through an sixth machine learning algorithm to determine a new rule for triggering communications with the consumer; and
store the new rule in the event rules database.
17. The method of claim 12 , further comprising the steps of:
creating a brand environment database on the non-volatile data storage device, the brand environment database comprising brand information related to conversations with consumers of the brand;
using an environment manager operating on the computing device to:
retrieve the consumer profile;
retrieve the brand information from the brand environment database;
process the consumer profile and the brand information through a seventh machine learning algorithm to determine whether a campaign of communications should be established with a plurality of consumers; and
forward the determination to the conversation manager as the determination that a callback should be made to the consumer.
18. The method of claim 17 , further comprising the steps of:
using a consumer manager operating on the computing device to:
retrieve the consumer profile for the consumer from the consumer profile database;
receive a fitness parameter from the environment manager;
process the consumer profile and the fitness parameter through an eighth machine learning algorithm to identify opportunities for proactive conversations with the consumer; and
forward the identified to the consumer context manager as an additional input to the first machine learning algorithm's selection of the channel through which the callback should be made.