Customized communications for network systems
View Patent ↗A network system customizes communications and communication channels for delivery to candidate providers registering with the network system. Candidate providers progress through steps of a network registration process by providing input data at the various steps. The network system provides communications to request the input data and facilitate the candidate providers' progress. The network system can use a machine learning model to predict particular types of communications and communication channels (e.g., online messages, phone calls, physical mail, etc.) that are likely to be well-received by candidate providers. Thus, the network system is able to increase the expected number of candidate providers that successfully register to provide services to other users of the network system.
1. A method for customizing communication channels of a network system, comprising:
determining, based on input data from a client device, that a candidate provider has progressed to a step of a sequence of steps to register for a service of the network system;
selecting a first communication channel that the candidate provider is likely to use to respond to a communication;
providing, by the network system to the client device, the communication via the first communication channel for presentation to the candidate provider;
progressing the candidate provider from the step to a subsequent step of the sequence of steps in response to determining that the candidate provider completed at least one action indicated by the communication; and
providing, by the network system to the client device, a subsequent communication for the subsequent step via a second communication channel for presentation to the candidate provider, the second communication channel different than the first communication channel.
2. The method of claim 1 , further comprising:
determining, by a machine learning model, that the candidate provider is likely to use the first communication channel to respond to the communication, the machine learning model trained using historical actions performed by one or more candidate providers and registered providers of the network system.
3. The method of claim 2 , wherein machine learning model determines that the candidate provider is likely to use the first communication channel to respond to the communication based on at least one of: the step of the sequence of steps, a type of the service, or the at least one action indicated by the communication.
4. The method of claim 2 , wherein machine learning model determines that the candidate provider is likely to use the first communication channel to respond to the communication using information from the one or more candidate providers and registered providers having at least one characteristic in common with the candidate provider, the at least one characteristic based on demographics or geographical region.
5. The method of claim 1 , further comprising:
determining that the candidate provider is likely to use the first communication channel to respond to the communication using actions performed in response to a plurality of historical communications by the candidate provider.
6. The method of claim 5 , wherein the actions include one or more of: scrolling through content of a message, opening an email, or responding to a phone call.
7. The method of claim 1 , wherein the first communication channel and the second communication channel are selected from a plurality of communication channels including one or more of text message, email, phone, physical mail, or chatbot.
8. The method of claim 1 , wherein the service is transportation service, the method further comprising:
selecting the communication from a plurality of communications each requesting information for a different one of: driver license, vehicle insurance, and vehicle inspection.
9. The method of claim 1 , further comprising:
receiving a scanned copy or photo of a driver license of the candidate provider; and
wherein progressing the candidate provider from the step to the subsequent step of the sequence of steps is further in response to determining that the scanned copy or photo of the driver license is legible and valid.
10. A computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by one or more processors, cause the one or more processors to:
determine, based on input data from a client device, that a candidate provider has progressed to a step of a sequence of steps to register for a service of a network system;
select a first communication channel that the candidate provider is likely to use to respond to a communication;
provide, by the network system to the client device, the communication via the first communication channel for presentation to the candidate provider;
progress the candidate provider from the step to a subsequent step of the sequence of steps in response to determining that the candidate provider completed at least one action indicated by the communication; and
provide, by the network system to the client device, a subsequent communication for the subsequent step via a second communication channel for presentation to the candidate provider, the second communication channel different than the first communication channel.
11. The non-transitory computer readable storage medium of claim 10 , having further instructions that when executed by the one or more processors cause the one or more processors to:
determine, by a machine learning model, that the candidate provider is likely to use the first communication channel to respond to the communication, the machine learning model trained using historical actions performed by one or more candidate providers and registered providers of the network system.
12. The non-transitory computer readable storage medium of claim 11 , wherein machine learning model determines that the candidate provider is likely to use the first communication channel to respond to the communication based on at least one of: the step of the sequence of steps, a type of the service, or the at least one action indicated by the communication.
13. The non-transitory computer readable storage medium of claim 11 , wherein machine learning model determines that the candidate provider is likely to use the first communication channel to respond to the communication using information from the one or more candidate providers and registered providers having at least one characteristic in common with the candidate provider, the at least one characteristic based on demographics or geographical region.
14. The non-transitory computer readable storage medium of claim 10 , having further instructions that when executed by the one or more processors cause the one or more processors to:
determine that the candidate provider is likely to use the first communication channel to respond to the communication using actions performed in response to a plurality of historical communications by the candidate provider.
15. The non-transitory computer readable storage medium of claim 14 , wherein the actions include one or more of: scrolling through content of a message, opening an email, or responding to a phone call.
16. The non-transitory computer readable storage medium of claim 10 , wherein the first communication channel and the second communication channel are selected from a plurality of communication channels including one or more of text message, email, phone, physical mail, or chatbot.
17. The non-transitory computer readable storage medium of claim 10 , having further instructions that when executed by the one or more processors cause the one or more processors to:
select the communication from a plurality of communications each requesting information for a different one of: driver license, vehicle insurance, and vehicle inspection, wherein the service is transportation service.
18. The non-transitory computer readable storage medium of claim 10 , having further instructions that when executed by the one or more processors cause the one or more processors to:
receive a scanned copy or photo of a driver license of the candidate provider; and
wherein progressing the candidate provider from the step to the subsequent step of the sequence of steps is further in response to determining that the scanned copy or photo of the driver license is legible and valid.
19. A system comprising:
one or more processors; and
a computer program product comprising a non-transitory computer readable storage medium having instructions encoded thereon that, when executed by the one or more processors, cause the one or more processors to:
determine, based on input data from a client device, that a candidate provider has progressed to a step of a sequence of steps to register for a service of a network system;
select a first communication channel that the candidate provider is likely to use to respond to a communication;
provide, by the network system to the client device, the communication via the first communication channel for presentation to the candidate provider;
progress the candidate provider from the step to a subsequent step of the sequence of steps in response to determining that the candidate provider completed at least one action indicated by the communication; and
provide, by the network system to the client device, a subsequent communication for the subsequent step via a second communication channel for presentation to the candidate provider, the second communication channel different than the first communication channel.
20. The system of claim 19 , wherein the non-transitory computer readable storage medium includes further instructions that when executed by the one or more processors cause the one or more processors to:
determine, by a machine learning model, that the candidate provider is likely to use the first communication channel to respond to the communication, the machine learning model trained using historical actions performed by one or more candidate providers and registered providers of the network system.