Facilitating pharmacy customer orders through natural language processing
A computer-implemented method includes receiving a message of a pharmacy customer wherein the message includes a text string, and generating a set of one or more intents corresponding to the pharmacy customer by analyzing the text string using a trained machine learning model, wherein each of the one or more intents correspond to a respective desired action pertaining to the pharmacy order. The machine learning model may be a classification model. The method further includes generating at least one response message based on the set of intents corresponding to the pharmacy customer and transmitting the at least one response message to a mobile device associated with the pharmacy customer. The set of one or more intents may be chosen from a list of commonplace pharmacy customer intents.
1. A computer-implemented method of facilitating a pharmacy order, comprising:
receiving, in an application server, a message of a pharmacy customer, the message including a text string;
training a machine learning model using training data including a set of messages each having a respective intent label specifying an objective of a pharmacy customer;
generating, by analyzing the text string using the trained machine learning model, a set of one or more intents of the pharmacy customer, each of the one or more intents corresponding to a respective desired action pertaining to the pharmacy order;
generating, based on the set of intents corresponding to the pharmacy customer, at least one response message; and
transmitting the at least one response message to a mobile device associated with the pharmacy customer.
2. The computer-implemented method of claim 1 , wherein receiving the message of the pharmacy customer includes receiving a text message via a mobile telephone carrier.
3. The computer-implemented method of claim 1 , wherein analyzing the text string using the trained machine learning model includes analyzing the text string using a classifier model.
4. The computer-implemented method of claim 1 , wherein generating the at least one response message includes generating a confirmation based on an intent of the customer.
5. The computer-implemented method of claim 1 , wherein generating the at least one response message includes generating a message deferral timeout.
6. The computer-implemented method of claim 5 , wherein transmitting the at least one response message to the mobile device associated with the pharmacy customer includes delaying the transmission of the at least one response message until the message deferral timeout has elapsed.
7. The computer-implemented method of claim 5 , wherein generating the message deferral timeout is based on the set of intents corresponding to the pharmacy customer including an intent indicating that the pharmacy customer is driving.
8. The computer-implemented method of claim 1 , wherein transmitting the at least one response message to the mobile device associated with the pharmacy customer includes transmitting a text message to the mobile device.
9. The computer-implemented method of claim 1 , wherein:
generating the set of one or more intents includes generating an intent corresponding to a prescription refill request;
generating the at least one response message includes generating a refill confirmation message based on the intent corresponding to a prescription refill request; and
transmitting the at least one response message to the mobile device associated with the pharmacy customer includes transmitting the refill confirmation message to the mobile device.
10. A computing system comprising:
one or more processors; and
memory storing instructions that, when executed by the one or more processors, cause the computing system to:
receive, in an application server, a message of a pharmacy customer, the message including a text string;
train a machine learning model using training data including a set of messages each having a respective intent label specifying an objective of a pharmacy customer;
select, from a set of one or more trained machine learning models, the trained machine learning model;
generate, by analyzing the text string using the trained machine learning model, a set of one or more intents of the pharmacy customer, each of the one or more intents corresponding to a respective desired action pertaining to the pharmacy order;
generate, based on the set of intents corresponding to the pharmacy customer, at least one response message;
transmit the at least one response message to a mobile device associated with the pharmacy customer; and
cause the at least one response message to be displayed in a display device of the mobile device.
11. The computing system of claim 10 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
receive a text message via a mobile telephone carrier.
12. The computing system of claim 10 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
analyze the text string using a classifier model.
13. The computing system of claim 10 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
generate a confirmation based on an intent of the customer.
14. The computing system of claim 10 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
generate a message deferral timeout.
15. The computing system of claim 10 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
transmit a text message to the mobile device.
16. The computing system of claim 14 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
delay and/or defer the transmission of the at least one response message until the message deferral timeout has elapsed.
17. The computing system of claim 10 , wherein the memory stores further instructions that, when executed by the one or more processors, cause the computing system to:
initiate a pharmacy prescription refill of a prescription associated with the pharmacy customer based on the set of intents corresponding to the pharmacy customer.
18. A computing system comprising:
a mobile device configured to execute an application that causes an inbound message to be transmitted via a carrier network;
a server device configured to execute an application that causes the inbound message to be received via the carrier network, wherein the server device is configured to, after receiving the inbound message via the carrier network;
train a machine learning model using training data including a set of messages each having a respective intent label specifying an objective of a pharmacy customer;
analyze the inbound message using the trained machine learning model;
identify a customer intent corresponding to the inbound message;
based on the customer intent, perform an action with respect to a pharmacy order corresponding to the customer;
generate an outbound text message addressed to the mobile device; and
transmit the outbound text message to the mobile device via the carrier network.
19. The computing system of claim 18 , wherein the customer intent corresponding to the inbound message pertains to the status of a pharmacy order.
20. The computing system of claim 18 , wherein the server device is configured to query an electronic database to look up information related to a customer based on metadata associated with the inbound message.