Artificial intelligence (AI)-based robotic process automation (RPA) for independent insurance sales agent
Methods and systems are provided for AI-based robotic automation for persuasive references. In one novel aspect, a robotic persuasive reference is generated based on a prospect product-service (P_PS) matrix, which is generated based on predictive analysis using DNN model and dynamically obtained feedbacks. In one embodiment, the DNN model is trained with customer personal profiles against associated PS revenues for each customer data set. In one embodiment, the predictive analysis uses a decision tree classifier. In one embodiment, the computer system detects one or more predefined triggering events comprising feedback information for the robotic persuasive reference and one or more predefined lifetime events, updates the P_PS matrix based and the robotic persuasive reference accordingly. In one embodiment, the feedback information is a sentiment analysis on responses from the prospect. In another embodiment, a recency, frequency, and page browsing analysis is performed based on the one or more detected lifetime events.
1. A method, comprising:
obtaining, by an independent insurance sales agent (USA) Bot computer system with one or more processors coupled with at least one memory unit, one or more prospect input data sets for one or more corresponding prospects, wherein each prospect input data set includes a plurality of predefined prospect attributes;
performing a predictive analysis on the one or more prospect input data sets using a deep neural network (DNN) model, wherein the DNN model is trained by a preexisting Big Data set containing a plurality of customer data sets;
generating a prospect product-service (P_PS) matrix of the prospect based on the predictive analysis and feedback attributes, wherein the feedback attributes are obtained from responses of corresponding prospects;
generating a robotic persuasive reference identifying one or more matching PSs for the prospect based on the P_PS matrix;
detecting one or more predefined triggering events comprising feedback information for the robotic persuasive reference and one or more predefined lifetime events;
updating the P_PS matrix based on the one or more detected predefined triggering events; and
updating the robotic persuasive reference based on the updated P_PS matrix.
2. The method of claim 1 , wherein the DNN model is trained with customer personal profiles against associated product and service (PS) revenues for each customer data set.
3. The method of claim 1 , wherein the predictive analysis further uses one or more decision tree classifiers.
4. The method of claim 3 , wherein the predictive analysis is further based on a PS knowledgebase and one or more agent profiles.
5. The method of claim 3 , wherein one or more prospect input data sets is an augmented data set each including one or more related data sets based on one or more predefined relationship rules.
6. The method of claim 1 , wherein the feedback information for the robotic persuasive reference is a sentiment analysis on responses from the prospect.
7. The method of claim 6 , wherein the sentiment analysis is based on an audio input analysis using a sentiment classifier.
8. The method of claim 6 , wherein the sentiment analysis is based on obtained textual inputs from the prospect using a set of predefined sentiment classifiers.
9. The method of claim 1 , wherein the feedback information for the robotic persuasive reference is an overt behavior analysis based one or more detected overt actions of the prospect.
10. The method of claim 1 , wherein a recency and frequency, (RF) analysis is performed based on one or more triggers comprising one or more detected overt actions, and the one or more detected lifetime events.
11. An independent insurance sales agent (USA) Bot system, comprising:
one or more network interfaces that connect the system with a network;
a memory; and
one or more processors coupled to one or more memory units, the one or more processors configured to
obtain one or more prospect input data sets for one or more corresponding prospects, wherein each prospect input data set includes a plurality of predefined prospect attributes;
perform a predictive analysis on the one or more prospect input data sets using a deep neural network (DNN) model, wherein the DNN model is trained by a preexisting Big Data set containing a plurality of customer data sets;
generate prospect product-service (P_PS) matrix of the prospect based on the predictive analysis and feedback attributes, wherein the feedback attributes are obtained from responses of corresponding prospects;
generate a robotic persuasive reference identifying one or more matching PSs for the prospect based on the P_PS matrix;
detect one or more predefined triggering events comprising feedback information for the robotic persuasive reference and one or more predefined lifetime events; update the P_PS matrix based on the one or more detected predefined triggering events; and update the robotic persuasive reference based on the updated P_PS matrix.
12. The IISA Bot system of claim 11 , wherein the DNN model is trained with personal customer profiles against associated product and service (PS) revenues for each customer data set.
13. The IISA Bot system of claim 11 , wherein the predictive analysis further uses one or more decision tree classifiers.
14. The IISA Bot system of claim 13 , wherein the predictive analysis is further based on a PS knowledgebase and one or more agent profiles.
15. The IISA Bot system of claim 13 , wherein one or more prospect input data sets is an augmented data set each including one or more related data sets based on one or more predefined relationship rules.
16. The IISA Bot system of claim 11 , wherein the feedback information for the robotic persuasive reference is a sentiment analysis on responses from the prospect.
17. The IISS Bot system of claim 11 , wherein the feedback information for the robotic persuasive reference is an overt behavior analysis based one or more detected overt actions of the prospect.
18. The IISA Bot system of claim 11 , wherein a recency and frequency, (RF) analysis is performed based on one or more triggers comprising one or more detected overt actions, and the one or more detected lifetime events.
19. The method of claim 16 , wherein the sentiment analysis is based on an audio input analysis using a sentiment classifier.
20. The method of claim 16 , wherein the sentiment analysis is based on obtained textual inputs from the prospect using a set of predefined sentiment classifiers.