Systems and methods for configurable messaging response-action engine
Systems and methods for a configurable response-action engine are provided. Actions are generated for a conversation when an insight is received from a natural language processing system. Industry, segment, client specific instructions, third party data, a state for the lead and lead historical patterns are also received. A decision making action model is tuned using this information. An objective for the conversation may be extracted from the state information for the lead. The tuned model is then applied to the insight and objective to output an action. A response message may be generated for the action. The action is directed to cause a state transition of the lead to a preferred state. In another embodiment, systems and methods are presented for feature extraction from one or more messages. In yet other embodiments, systems and methods for message cadence optimization are provided.
1. A computer implemented method for generating actions to a message comprising:
receiving at least one insight regarding a message from a natural language processing machine learning model;
receiving a plurality of objectives;
receiving a set of completed objectives;
generating a set of outstanding objectives by comparing the plurality of objectives with the set of completed objectives;
receiving client specific instructions, and lead historical patterns, wherein the client specific instructions indicates how aggressive the language to be used is, and where the client specific instructions includes message wait length, and order of objective completion, and wherein the lead historical patterns includes response time and effective persuasion techniques;
tuning a decision making action model using the client specific instructions and lead historical patterns to modify at least one of response time, message content and order of completing the set of outstanding objectives
applying the tuned model to the insight to generate an action.
2. The method of claim 1 , further comprising generating a response message using the generated action.
3. The method of claim 1 , further comprising receiving a state for the lead.
4. The method of claim 3 , further comprising extracting an objective from the state information for the lead.
5. The method of claim 4 , wherein the tuned model is applied to the insight and objective to generate the action.
6. The method of claim 5 , wherein the action is directed to cause a state transition of the lead to a preferred state.
7. The method of claim 1 , wherein the decision making action model is independent from the natural language processing machine learning model.
8. The method of claim 1 , wherein the decision making action model is a machine learning model.
9. The method of claim 8 , wherein the decision making action model is trained by annotating the message with actions.
10. The method of claim 9 , wherein the annotation is performed in the client domain.