System for automatic classification and routing

One or more non-transitory computer-readable media storing instructions, which, when processed by one or more processors, cause:

• a request classifier service, executing on a server computer, receiving an input request from a client device;
• in response to the request classifier service receiving the input request from the client device, the request classifier service:
• accessing classification data from a knowledge repository, where the classification data comprises one or more defined input requests mapped to one or more classification types;
• determining confidence values for each of the one or more defined input requests mapped to the one or more classification types, where the confidence value represents a relative match score between the input request from the client device and each of the one or more defined input requests mapped to the one or more classification types;
• in response to the request classifier service determining the confidence values for each of the one or more defined input requests mapped to the one or more classification types, sending one or more classification types from the one or more defined input requests mapped to the one or more classification types to a processing service on the server computer;
• the processing service, determining a process response type, based upon the one or more classification types from the one or more defined input requests mapped to the one or more classification types received from the request classifier service;
• the processing service, routing the process response type, determined by the processing service, and the input request from the client device to a destination mapped to the process response type.

A computer-implemented method comprising:

• a request classifier service, executing on a server computer, receiving an input request from a client device;
• in response to the request classifier service receiving the input request from the client device, the request classifier service:
• accessing classification data from a knowledge repository, where the classification data comprises one or more defined input requests mapped to one or more classification types;
• determining confidence values for each of the one or more defined input requests mapped to the one or more classification types, where the confidence value represents a relative match score between the input request from the client device and each of the one or more defined input requests mapped to the one or more classification types;
• in response to the request classifier service determining the confidence values for each of the one or more defined input requests mapped to the one or more classification types, sending one or more classification types from the one or more defined input requests mapped to the one or more classification types to a processing service on the server computer;
• the processing service, determining a process response type, based upon the one or more classification types from the one or more defined input requests mapped to the one or more classification types received from the request classifier service;
• the processing service, routing the process response type, determined by the processing service, and the input request from the client device to a destination mapped to the process response type.