System and method for mobile device active callback prioritization with predictive outcome scoring
A system and methods for mobile device active callback prioritization with predictive outcome scoring, utilizing an enhanced callback prioritization engine operating on a user's mobile device for integration through the operating system and software applications operating on the device, wherein the enhanced callback prioritization engine receives intercepted data or voice messages sent to the mobile device, retrieves and aggregates data related to the assigned messages, inputs the assigned data message and aggregate data into prioritization model wherein the prioritization model may analyze the input data, the results of the analysis may be used to compute a priority score for the assigned data message. An outcome model may be present and configured to produce outcome scores for a callback recipient based on the context of the data or voice message. System generates a callback list from the computed prioritization score and outcome score.
1. A mobile device with active callback prioritization, comprising:
a processor, a memory, and a plurality of programming instructions stored in the memory and operable on the processor;
a callback integration engine comprising a subset of the plurality of programming instructions that, when operating on the processor, cause the processor to:
receive a data or voice message, the data or voice message comprising at least one characteristic;
produce a callback object in memory comprising information associated with the data or voice message received; and
send the callback object to an enhanced callback prioritization engine; and
the enhanced callback prioritization engine comprising a subset of the plurality of programming instructions that, when operating on the processor, cause the processor to:
receive the callback object from the callback integration engine;
retrieve and aggregate application data related to the data or voice message;
retrieve callback recipient data for a plurality of callback recipients;
use the callback object and the aggregated application data as inputs into a prioritization model, wherein the prioritization model analyzes the callback object's information and the aggregated application data to determine the context and urgency associated with the data or voice message;
for each callback object, compute a priority score based at least upon the results of the analysis;
use the determined context and urgency and the retrieved callback recipient data as inputs into one or more machine learning algorithms, wherein the machine learning algorithms analyze the context and urgency and the retrieved callback recipient data to determine an interaction outcome associated with the data or voice message;
for each callback recipient, compute an outcome score based at least upon the results of the analysis;
assign a callback recipient to the callback object based at least upon the outcome score; and
use the computed priority score, the callback object data, and the data or voice message to generate a callback list.
2. The mobile device of claim 1 , wherein the enhanced callback prioritization engine is further configured to:
retrieve and aggregate requestor-specific data;
use the aggregated requestor-specific data as an additional input into the one or more machine learning algorithms, wherein the machine learning algorithms analyze the context and urgency data, the retrieved callback recipient data, and the aggregated requestor-specific data to determine a requestor-specific outcome associated with the data or voice message;
for each callback recipient, compute a requestor-specific outcome score based at least upon the results of the analysis; and
assign a callback recipient to and the callback object based at least upon the requestor-specific outcome score.
3. The mobile device of claim 1 , wherein the callback recipient data comprises agents skills, quality assurance scores, scheduling information, historical interactions, spoken languages, certifications, interaction outcomes, and location information.
4. The mobile device of claim 2 , wherein the requestor-specific data comprises requestor preferences.
5. The mobile device of claim 4 , wherein the requestor preferences comprise preferred agents or agent qualities.
6. The mobile device of claim 1 , wherein the application data is retrieved using application programming interfaces.
7. The mobile device of claim 1 , wherein the callback list comprises a smart reply message.
8. The mobile device of claim 1 , wherein the callback integration engine receives a user confirmed callback list and executes the confirmed callback items on the list.
9. The mobile device of claim 1 , wherein the application data comprises data from communication, social media, financial, gaming, and productivity applications.
10. The mobile device of claim 1 , wherein the machine learning algorithms comprise natural language processing.
11. A method for active callback prioritization, comprising the steps of:
receiving a data or voice message, the data or voice message comprising at least one characteristic;
producing a callback object in memory comprising information associated with the data or voice message received;
sending the callback object to an enhanced callback prioritization engine;
receiving the callback object from the callback integration engine;
retrieving and aggregate application data related to the data or voice message;
retrieving callback recipient data for a plurality of callback recipients;
using the callback object and the aggregated application data as inputs into a prioritization model, wherein the prioritization model analyzes the callback object's information and the aggregated application data to determine the context and urgency associated with the data or voice message;
for each callback object, computing a priority score based at least upon the results of the analysis;
using the determined context and urgency and the retrieved callback recipient data as inputs into one or more machine learning algorithms, wherein the machine learning algorithms analyze the context and urgency and the retrieved callback recipient data to determine an interaction outcome associated with the data or voice message;
for each callback recipient, computing an outcome score based at least upon the results of the analysis;
assigning a callback recipient to the callback object based at least upon the outcome score; and
using the computed priority score, the callback object data, and the data or voice message to generate a callback list.
12. The method device of claim 11 , further comprising the steps of:
retrieving and aggregate requestor-specific data;
using the aggregated requestor-specific data as an additional input into the one or more machine learning algorithms, wherein the machine learning algorithms analyze the context and urgency data, the retrieved callback recipient data, and the aggregated requestor-specific data to determine an requestor-specific outcome associated with the data or voice message;
for each callback recipient, computing a requestor-specific outcome score based at least upon the results of the analysis; and
assigning a callback recipient to and the callback object based at least upon the requestor-specific outcome score.
13. The method of claim 11 , wherein the callback recipient data comprises agents skills, quality assurance scores, scheduling information, historical interactions, spoken languages, certifications, interaction outcomes, and location information.
14. The method of claim 12 , wherein the requestor-specific data comprises requestor preferences.
15. The method of claim 14 , wherein the requestor preferences comprise preferred agents or agent qualities.
16. The method of claim 11 , wherein the application data is retrieved using application programming interfaces.
17. The method of claim 11 , wherein the callback list comprises a smart reply message.
18. The method of claim 11 , wherein the callback integration engine receives a user confirmed callback list and executes the confirmed callback items on the list.
19. The method of claim 11 , wherein the application data comprises data from communication, social media, financial, gaming, and productivity applications.
20. The method of claim 11 , wherein the machine learning algorithms comprise natural language processing.