Method and apparatus for optimizing customer service across multiple channels

Abstract

A method and apparatus for a computer-implemented technique for maximizing customer satisfaction and first call resolution, including converting telephone calls into online chats, while minimizing cost is provided. Techniques for incorporating analytics as applied to customer data into particular strategies for call deflection, targeting particular individuals to increase chat acceptance rate, and computing a customer's wait time are also provided.

I/We claim: 
     
         1 . A computer-implemented method comprising:
 monitoring a behavioral attribute of an individual who has accessed a website in an attempt to resolve an issue,
 wherein the behavioral attribute is based on click activities performed by the individual, hover activities performed by the individual, or any combination thereof; 
   determining, based on the behavioral attribute, that the individual is unable to find a solution to the issue on the website; and   executing a containment strategy designed to retain the individual on the website rather than initiate an interaction with a live agent associated with a call center,
 wherein said retaining is effected by proactively:
 inviting the individual to a chat channel having an automated feature that is accessible via the website; 
 presenting a self-service opportunity to the individual on a self-service channel that is accessible via the website; or 
 presenting an assisted self-service opportunity to the individual on an assisted self-service channel that is accessible via the website. 
 
   
     
     
         2 . The computer-implemented method of  claim 1 , further comprising:
 identifying a particular website associated with a top call driver,
 wherein the top call driver represents a particular issue responsible for driving a highest number of calls to the call center; and 
   identifying one or more web journeys that correspond to the particular website,
 wherein each web journey represents a web traversal footprint associated with at least one visitor to the particular website. 
   
     
     
         3 . The computer-implemented method of  claim 2 , further comprising:
 computing traffic on the particular website and each website included in each web journey; and   estimating expected chat volume based on the traffic.   
     
     
         4 . The computer-implemented method of  claim 1 , further comprising:
 executing a targeting strategy designed to indicate a likelihood of the individual interacting via chat,
 wherein said executing includes
 applying a statistical model to compute a chat acceptance score for the individual, 
 determining whether the chat acceptance score exceeds a particular threshold, and 
 responsive to a determination that the chat acceptance score exceeds the particular threshold,
 causing display of an offer to interact with the individual on the chat channel. 
 
 
   
     
     
         5 . The computer-implemented method of  claim 1 , further comprising:
 examining customer relationship management (CRM) data to identify at least one call driver,
 wherein each call driver represents a separate issue responsive for causing at least one individual to call the call center; 
   determining an amenability of each call driver to be resolved on the website; and   targeting one or more issues for application of the containment strategy,
 wherein each issue of the one or more issues is associated with an amenability that exceeds a particular threshold. 
   
     
     
         6 . The computer-implemented method of  claim 5 , further comprising:
 identifying a web journey that corresponds to the website,
 wherein the web journey represents a web traversal footprint associated with at least one visitor to the website; 
   identifying one or more uniform resource locators (URLs) corresponding to the web journey;   determining a hot lead rate for each URL,
 wherein the hot lead rate represents a percentage of individuals who access the corresponding URL to be targeted for retainment by the containment strategy. 
   
     
     
         7 . The computer-implemented method of  claim 6 , wherein the hot lead rate is based on a hierarchical level of the corresponding URL, behavioral attributes, and journey attributes. 
     
     
         8 . The computer-implemented method of  claim 1 , further comprising:
 determining an acceptance rate from a multivariate model; and   determining, based on the acceptance rate, when to present the individual with an invitation to the chat channel.   
     
     
         9 . The computer-implemented method of  claim 1 , further comprising:
 servicing an optical segment of URLs based on exit rates of the URLs, user ratings of the URLs, or any combination thereof.   
     
     
         10 . The computer-implemented method of  claim 1 , further comprising:
 mining transcripts of chat sessions between individuals and live agents of the call center to identify a call driver; and   identifying websites associated with the call driver to target for deployment of the containment strategy.   
     
     
         11 . An electronic device comprising:
 a memory that includes instructions for effecting containment of individuals to a website,   wherein the instructions, when executed by a processor, cause the processor to:
 monitor a behavior attribute of an individual who has accessed a website in an attempt to resolve an issue; 
 determining, based on the behavioral attribute, that the individual is unable to find a solution to the issue on the website; and 
 execute a containment strategy designed to retain the individual on the website rather than initiate an interaction with a live agent associated with a call center,
 wherein said retaining is effected by: 
 applying a multivariate model to determine a likelihood of the individual accepting an invitation to a chat channel; 
 determine, based on the likelihood, when to present the individual with the invitation to the chat channel; and 
 inviting the individual to the chat channel that has an automated feature that is accessible via the website. 
 
   
     
     
         12 . The electronic device of  claim 11 , wherein the behavioral attribute is based on click activities performed by the individual, hover activities performed by the individual, or any combination thereof. 
     
     
         13 . The electronic device of  claim 11 , wherein the instructions further cause the processor to:
 identify a particular website associated with a call driver,
 wherein the call driver represents a particular issue responsible for driving a number of calls to the call center; and 
   identify one or more web journeys that correspond to the particular website,
 wherein each web journey represents a web traversal footprint associated with at least one visitor to the particular website. 
   
     
     
         14 . The electronic device of  claim 13 , wherein the instructions further cause the processor to:
 compute traffic on the particular website and each website included in each web journey; and   estimate expected chat volume based on the traffic.   
     
     
         15 . The electronic device of  claim 11 , wherein the instructions further cause the processor to:
 examine customer relationship management (CRM) data to identify at least one call driver,
 wherein each call driver represents a separate issue responsive for causing at least one individual to call the call center; 
   determine an amenability of each call driver to be resolved on the website; and   target one or more issues for application of the containment strategy,
 wherein each issue of the one or more issues is associated with an amenability that exceeds a particular threshold. 
   
     
     
         16 . The electronic device of  claim 11 , wherein the instructions further cause the processor to:
 identify a web journey that corresponds to the particular website,
 wherein the web journey represents a web traversal footprint associated with visitors to the particular website; 
   identify one or more uniform resource locators (URLs) corresponding to the web journey; and   determine a hot lead rate for each URL,
 wherein the hot lead rate represents a percentage of individuals who access the corresponding URL to be targeted for retainment by the containment strategy. 
   
     
     
         17 . The electronic device of  claim 16 , wherein the hot lead rate is based on a hierarchical level of the corresponding URL, behavioral attributes, and journey attributes. 
     
     
         18 . The electronic device of  claim 11 , wherein the instructions further cause the processor to:
 service an optical segment of URLs based on exit rates of the URLs, user ratings of the URLs, or any combination thereof.   
     
     
         19 . The electronic device of  claim 11 , wherein the instructions further cause the processor to:
 mine transcripts of chat sessions between individuals and live agents of the call center to identify a call driver; and   identify websites associated with the call driver to target for deployment of the containment strategy.   
     
     
         20 . A computer-implemented method comprising:
 acquiring call data associated with voice calls placed to a call center,
 wherein the call data specifies, for each call, a duration, a date, a total handling time, a live agent, an issue type, a caller attribute, an agent attribute, or any combination thereof; 
   identifying a call driver from the call data,
 wherein the call driver represents an issue responsible for driving at least a specified volume of calls to the call center; 
   identifying a web journey corresponding to the call driver,
 wherein the web journey is representative of electronic footprints left by visitors to a particular website seeking to resolve the issue, and 
 wherein each electronic footprint specifies a referral website, a landing website, an exit website, a clickstream of visited websites, a wait time for each visited website, a count of visited websites, or any combination thereof; 
   computing traffic on a website related to the call driver and websites related to the web journey;   analyzing a behavioral attribute of each visitor to the website related to the call driver; and   for each visitor,
 performing, based on the corresponding behavioral attribute, an action to retain the visitor on the website rather than initiate an interaction with a live agent associated with the call center. 
   
     
     
         21 . The computer-implemented method of  claim 20 , wherein said performing comprises performing at least one of:
 inviting the visitor to a chat channel having an automated feature that is accessible via the website;   presenting a self-service opportunity to the visitor on a self-service channel that is accessible via the website; and   presenting an assisted self-service opportunity to the visitor on an assisted self-service channel that is accessible via the website.