Systems and method for intent messaging
Disclosed embodiments provide a framework to assist customers in obtaining relevant responses from brands and other users to the intents communicated by these customers. In response to obtaining an intent, an intent messaging service identifies one or more users that can be provided with the intent to solicit responses to the intent. The one or more users are selected based on characteristics of the intent. The intent messaging service evaluates the responses to the intent from the one or more users to identify relevant responses that can be presented to the customer. The intent messaging service provides the relevant responses to the intent to the customer, which can determine which users to interact with to address the intent.
1. A computer-implemented method comprising:
obtaining an intent, wherein the intent corresponds to a request that is to be addressed, and wherein the intent is associated with a customer;
identifying one or more users to which to provide the intent, wherein the one or more users are identified based on a set of characteristics of the intent;
providing the intent, wherein the intent is provided to the one or more users to solicit responses to the intent;
obtaining a set of responses to the intent;
evaluating the set of responses to identify relevant responses to the intent, wherein irrelevant responses from the set of responses are discarded; and
providing the relevant responses to cause the relevant responses to be presented to the customer in response to the intent.
2. The computer-implemented method of claim 1 , further comprising:
receiving a request to initiate a communications channel with a particular user, wherein the request to initiate the communications channel is associated with the intent and a response of the particular user to the intent; and
establishing the communications channel to allow the particular user to transmit communications responsive to the intent over the communications channel.
3. The computer-implemented method of claim 1 , wherein the set of responses are evaluated using a classification model, and wherein the classification model is updated using sample intents, known relevant responses to the sample intents, and known irrelevant responses to the sample intents.
4. The computer-implemented method of claim 1 , wherein the one or more users are identified using a machine learning model, and wherein the machine learning model is updated using sample intents and sample outputs corresponding to features of the one or more users.
5. The computer-implemented method of claim 1 , further comprising:
transmitting instructions to an application to cause the application to prohibit creation of new responses to the intent, wherein the instructions are transmitted in response to obtaining the set of responses.
6. The computer-implemented method of claim 1 , wherein the intent is extracted from the request based on a semantic analysis of the request.
7. The computer-implemented method of claim 1 , wherein the set of characteristics of the intent are obtained in response to a query for additional information associated with the intent.
8. The computer-implemented method of claim 1 , further comprising:
utilizing natural language processing to solicit information associated with the intent, wherein the information associated with the intent is used to extract the intent from the request.
9. A system, comprising:
one or more processors; and
memory storing thereon instructions that, as a result of being executed by the one or more processors, cause the system to:
obtain an intent, wherein the intent corresponds to a request that is to be addressed, and wherein the intent is associated with a customer;
identify one or more users to which to provide the intent, wherein the one or more users are identified based on a set of characteristics of the intent;
provide the intent, wherein the intent is provided to the one or more users to solicit responses to the intent;
obtain a set of responses to the intent;
evaluate the set of responses to identify relevant responses to the intent, wherein irrelevant responses from the set of responses are discarded; and
provide the relevant responses to cause the relevant responses to be presented to the customer in response to the intent.
10. The system of claim 9 , wherein the instructions, as a result of being executed by the one or more processors, further cause the system to:
obtain a request to establish a communications channel between a first computing system of the customer and a second computing system of a particular user, wherein the request to establish the communications channel is obtained in response to a determination that a response from the particular user satisfies the intent; and
establish the communications channel in response to the request to establish the communications channel.
11. The system of claim 9 , wherein the relevant responses are identified using a classification model, and wherein the classification model is generated using sample intents, known relevant responses to the sample intents, and known irrelevant responses to the sample intents.
12. The system of claim 9 , wherein the one or more users are identified using a machine learning model, and wherein the machine learning model is generated using sample intents and sample outputs corresponding to features of the one or more users.
13. The system of claim 9 , wherein the instructions, as a result of being executed by the one or more processors, further cause the system to:
transmit particular instructions to an application to cause the application to prohibit further responses to the intent from being generated, and wherein the particular instructions are transmitted in response to obtaining the set of responses.
14. The system of claim 9 , wherein the instructions, as a result of being executed by the one or more processors, further cause the system to:
perform a semantic analysis of the request to extract the intent from the request.
15. The system of claim 9 , wherein the set of characteristics of the intent are obtained in response to a query for additional information associated with the intent.
16. The system of claim 9 , wherein the instructions, as a result of being executed by the one or more processors, further cause the system to:
utilize natural language processing to solicit information associated with the intent, wherein the information associated with the intent is used to extract the intent from the request.
17. A non-transitory, computer-readable storage medium storing thereon executable instructions that, as a result of being executed by one or more processors of a computer system, cause the computer system to:
obtain an intent, wherein the intent corresponds to a request that is to be addressed, and wherein the intent is associated with a customer;
identify one or more users to which to provide the intent, wherein the one or more users are identified based on a set of characteristics of the intent;
provide the intent, wherein the intent is provided to the one or more users to solicit responses to the intent;
obtain a set of responses to the intent;
evaluate the set of responses to identify relevant responses to the intent, wherein irrelevant responses from the set of responses are discarded; and
provide the relevant responses to cause the relevant responses to be presented to the customer in response to the intent.
18. The non-transitory, computer-readable medium of claim 17 , wherein the executable instructions, as a result of being executed by the one or more processors, further cause the computer system to:
obtain a request to establish a communications channel between a first computing device of the customer and a second computing device of a particular user that provided a relevant response; and
establish the communications channel between the first computing device of the customer and the second computing device of the particular user to cause interactions between the customer and the particular user over the communications channel with regard to the intent.
19. The non-transitory, computer-readable storage medium of claim 17 , wherein the executable instructions, as a result of being executed by the one or more processors, further cause the computer system to:
use a classification model to evaluate the set of responses, wherein the classification model is updated using sample intents, known relevant responses to the sample intents, and known irrelevant responses to the sample intents.
20. The non-transitory, computer-readable storage medium of claim 17 , wherein the one or more users are identified using a machine learning model, and wherein the machine learning model is generated using sample intents and sample outputs corresponding to features of the one or more users.
21. The non-transitory, computer-readable storage medium of claim 17 , wherein the executable instructions, as a result of being executed by the one or more processors, further cause the computer system to:
transmit particular instructions to an application to cause the application to prohibit creation of new responses to the intent, wherein the particular instructions are transmitted in response to obtaining the set of responses.
22. The non-transitory, computer-readable storage medium of claim 17 , wherein the executable instructions, as a result of being executed by the one or more processors, further cause the computer system to:
perform a semantic analysis of the request to obtain the intent.
23. The non-transitory, computer-readable storage medium of claim 17 , wherein the set of characteristics of the intent are obtained in response to a query for additional information associated with the intent.
24. The non-transitory, computer-readable storage medium of claim 17 , wherein the executable instructions, as a result of being executed by the one or more processors, further cause the computer system to:
utilize natural language processing to solicit information associated with the intent, wherein the information associated with the intent is used to extract the intent from the request.