Method and system for personalising responses to customer communications
In one embodiment, the invention provides a method for personalizing a response to an incoming customer communication. The method includes identifying a customer based on an incoming customer communication; selecting a rule applicable to the incoming customer communication, the rule having a destination associated therewith; preparing data to facilitate processing of the incoming customer communication; and routing the call to the destination associated with the selected rule and sending the prepared data to the destination.
1. A method, comprising:
generating, by a processor, personalization data comprising at least one tag: value pair;
associating, by the processor, the personalization data with an incoming customer communication;
matching, by the processor, the personalization data against a set of rules in a rule database to determine a rule that most closely matches the personalization data; and
selecting, by the processor, a destination for the incoming customer communication based on the matching of the personalization data, wherein
the value pair comprises a customer name, a service level of the customer, satisfaction level of the customer, status of service, or a combination thereof, and
the matching of the personalization data against the set of rules further comprises
calculating a vector dot product between the value pair and each of the set of rules in the rule database, and
selecting a rule of from the set of rules closest to the value pair based on the calculated vector dot product.
2. The method of claim 1 , wherein the incoming customer communication comprises a telephone call and the personalization data is generated during the telephone call.
3. The method of claim 1 , wherein the personalization data is based on explicitly-received information from the customer.
4. The method of claim 1 , wherein the personalization data is based on implicitly-collected information.
5. The method of claim 1 , wherein the matching comprises applying a statistical matching technique.
6. The method of claim 1 , wherein the matching comprises using a statistical approach to determine the most closely matching rule.
7. A system comprising a processor and a memory coupled to the processor, the memory storing instructions that, when executed by the processor, are configured to cause the system to:
receive an incoming customer communication;
retrieve a customer profile associated with the incoming customer communication;
match the customer profile comprising at least one tag against a plurality of rules to select a rule that best fits data in the customer profile; and
route the call to a destination associated with the selected rule, wherein
the at least one tag comprises a value pair comprising a customer name, a service level of the customer, satisfaction level of the customer, status of service, or a combination thereof, and
the customer profile is matched against the plurality of rules further by
calculating a vector dot product between the at least one tag of the customer profile and each of the plurality of rules in a rule database, and
selecting a rule of from the set of rules closest to the value pair based on the calculated vector dot product.
8. The system of claim 7 , wherein the matching is based on a statistical technique.
9. The system of claim 7 , wherein the customer profile comprises tag: value pairs.
10. The system of claim 9 , wherein some of the tag: value pairs are missing.
11. A method, comprising:
identifying, by a processor, a customer based on an incoming customer communication;
matching, by the processor, at least one tag against a set of rules in a rule database to determine a rule that most closely matches the at least one tag;
selecting, by the processor, the rule applicable to the incoming customer communication based on the matching, the rule having a destination associated therewith;
preparing, by the processor, data to facilitate processing of the incoming customer communication; and
routing, by the processor, a call to the destination associated with the selected rule and sending the prepared data to the destination, wherein
the at least one tag comprises a value pair comprising a customer name, a service level of the customer, satisfaction level of the customer, status of service, or a combination thereof, and
the matching of the at least one tag against the set of rules further comprises
calculating a vector dot product between the at least one tag and each of the set of rules in the rule database, and
selecting a rule of from the set of rules closest to the value pair based on the calculated vector dot product.
12. The method of claim 11 , wherein the customer communication comprises a telephone call.
13. The method of claim 11 , wherein the selecting of the applicable rule is based on a statistical matching technique.
14. The method of claim 11 , wherein the destination comprises a telephone number associated with a live agent.
15. The method of claim 14 , wherein the data comprises information to assist the live agent to handle the call.
16. The method of claim 14 , wherein the information comprises a script of prompts to be uttered by the live agent to the customer.
17. A non-transitory computer-readable medium having stored thereon a sequence of instructions that, when executed by a processor, are configured to cause the processor to:
identify a customer based on an incoming customer communication;
match at least one tag against a set of rules in a rule database to determine a rule that most closely matches the at least one tag;
select the rule applicable to the incoming customer communication based on the matching, the rule having a destination associated therewith;
prepare data to facilitate processing of the incoming customer communication; and
route a call to the destination associated with the selected rule and sending the prepared data to the destination, wherein
the at least one tag comprises a value pair comprising a customer name, a service level of the customer, satisfaction level of the customer, status of service, or a combination thereof, and
the at least one tag is matched against the set of rules further comprises
calculating a vector dot product between the at least one tag and each of the set of rules in the rule database, and
selecting a rule of from the set of rules closest to the value pair based on the calculated vector dot product.
18. The non-transitory computer-readable medium of claim 17 , wherein the customer communication comprises a telephone call.
19. The non-transitory computer-readable medium of claim 17 , wherein selecting the applicable rule is based on a statistical matching technique.
20. The non-transitory computer-readable medium of claim 17 , wherein the destination comprises a telephone number associated with a live agent.