Predictive customer service environment
A mechanism for facilitating customer interactions within a customer service environment provides prompt and accurate answers to customer questions. A smart chat facility for use in a customer service environment to predict a customer problem examines a customer chat transcript to identify customer statements that set forth a customer issue and, responsive to this, can route the customer to an agent, an appropriate FAQ, or can implement a problem specific widget in the customer UI. Customer queries are matched with most correct responses and accumulated knowledge is used to predict a best response to future customer queries. The iterative system thus learns from each customer interaction and can adapt to customer responses over time to improve the accuracy of problem prediction.
1. An apparatus for event-driven, customizable action execution to facilitate contextual interactions, comprising:
a processor and a memory configured as part of a predictive service platform for building and provisioning real time interaction management solutions over a network;
said processor configured to capture information representative of a user's journey across said network, said journey representing said user's interactions with a website window of a browser associated with said network including any of data accessed on said website, actions performed on said website and time on pages of the website;
said memory configured as a persistent local storage of said browser to store said information of said journey such that said information stored in said memory is capable of being shared locally across a plurality of windows of said browser;
said processor configured to send updates of said stored information over a network to a server during non-persistent interactions to facilitate generation of a model of said journey as a finite state machine including distinct states and conditional transitions thereby making said server stateless, said model representing said user's interactions with the website, a chat transcript representing the user's prior interaction with the predictive service platform, and customer relationship management (CRM) records associated with said user, the model being a hierarchical category model generated using a machine learning algorithm;
said processor configured to predict an issue of the user having a highest probability score identified in the model representing said user's interactions with the website, the chat transcript representing the user's prior interaction with the predictive service platform, and the CRM records associated with said user; and
said processor performing a specific action correlating to the issue of the user as predicted using the model, the specific action causing a state transition or display of an interface representing an interaction opportunity to resolve said issue of said user.
2. The apparatus of claim 1 , wherein the interactions with the website include a page loading results.
3. The apparatus of claim 1 , wherein the interactions with the website includes any of data, actions, and time on all pages.
4. The apparatus of claim 1 , wherein said interface includes any of:
an interaction popup;
a self-service wizard;
a customized interaction interface to the user; and
and a chat conversation.
5. The apparatus of claim 1 , wherein the interactions with the website include any of chat, self-service, emails, social media, and click to call.
6. The apparatus of claim 1 further comprising:
said processor configured to generate one or more sessions to identify any of a visitor, a logical browsing session of the user, and a logical interaction with the user.
7. The apparatus of claim 1 , said processor configured to send periodical and on-demand update of tracked information to said server.
8. An apparatus for event-driven, customizable action execution to facilitate contextual interactions, comprising:
a processor and a memory configured as part of a predictive service platform for building and provisioning real time interaction management solutions over a network;
said processor configured to capture information stored in a persistent local storage of a client device, said stored information representative of a user's journey across said network, said journey representing said user's interactions with a website window of a browser associated with said network including any of data accessed on said website, actions performed on said website, and time on pages of the website;
said processor configured to receive updates of said stored information over a network from said client device during non-persistent interactions to facilitate generation of a model of said journey as a finite state machine including distinct states and conditional transitions thereby making said apparatus stateless, said model representing said user's interactions with the website, a chat transcript representing the user's prior interaction with the predictive service platform, and customer relationship management (CRM) records associated with said user, the model generated using a machine learning algorithm;
said processor configured to predict an issue of the user having a highest probability score identified in the model representing said user's interactions with the website, the chat transcript representing the user's prior interaction with the predictive service platform, and the CRM records associated with said user; and
said processor causing the client device to perform a specific action correlating to said issue of the user as predicted using the model, the specific action including a state transition or display of an interface representing interaction opportunities to resolve said issue of said user during a lifecycle of said journey responsive to captured information.
9. The apparatus of claim 8 , wherein said apparatus is a server comprising:
a rules engine configured to divide decision making into three phases to predict said issue, comprising:
client side data collection and client side condition evaluation;
server side data collection from third party integrations; and
server side condition evaluation based on client, as well as server side, data.
10. The apparatus of claim 8 , said processor configured to allow other system components to subscribe for, and take appropriate actions.
11. The apparatus of claim 9 , wherein client side data comprises any of:
time on a page;
geography;
cookies;
DOM data;
client side persistent storage; and
data obtained anywhere during a journey.
12. The apparatus of claim 9 , wherein server side data comprises any of:
a page visitor's profile; and
past history and any third party data coming from a backend.
13. The apparatus of claim 1 , wherein the issue of the user is predicted by identifying a query type having the highest probability score in a probability matrix associated with the hierarchical category model.
14. The apparatus of claim 8 , wherein the issue of the user is predicted by identifying a query type having the highest probability score in a probability matrix associated with the model.