Artificial intelligence-based recommender and self-provisioner

• US 8,626,587 B2
• Filed: 12/10/2010
• Issued: 01/07/2014
• Est. Priority Date: 12/10/2010
• Status: Active Grant

• Current Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Original Assignee: Verizon Patent and Licensing Incorporated (Verizon Communications Inc.)
• Inventors: Kandanala, Venket S., Srinivasan, Karthik, Joshi, Nicky Pinakin, Sankaran, Anand N., Gunda, Siddhartha X., Mahajan, Pankul X., Parambath, Jubish C., Ramalingam, Paranjothi X., Caputo, Lisa A., Varadharajan, Sundarajan, Mathew, Varughese P.
• Primary Examiner(s): Alvarez, Raquel
• Application Number:
  US12/965,149
• Publication Number:
  US 20120150642A1
• Time in Patent Office: 1,124 Days
• Field of Search: 705/14.49, 705/14.53, 705/14.66, 705/14.67
• US Class Current: 705/14.53
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

A method including providing at least one of a phone service, an Internet access service, or a television service to customers; identifying a customer when the customer uses the at least one of the phone service, the Internet access service, or the television service; selecting products or services for which the customer qualifies based on the identifying; gathering customer-specific data for the customer; generating recommendations that pertain to the at least one of the phone service, the Internet access service, or the television service for the customer based on the products or the services for which the customer qualifies, the customer-specific data, and other factors, wherein the other factors include at least one of a location of the customer or a time in which the recommendations is to be provided to the customer; and providing the recommendations to the customer via the at least service.

Claims

1. A method comprising:

providing at least one of a phone service, an Internet access service, or a television service to customers;

identifying a customer, based on a device identifier, when the customer uses the at least one of the phone service, the Internet access service, or the television service;

determining at least one of a product or a service to which the customer is subscribed based on the identifying;

qualifying the customer, based on the determining, for at least one of another product or another service to recommend pertaining to the least one of the phone service, the Internet access service, or the television service;

selecting the at least one of the other product or the other service to recommend for which the customer qualifies based on the qualifying;

gathering customer-specific data of the customer;

receiving rules that include criteria for generating recommendations on behalf of the customer;

generating, by a device, recommendations that pertain to the at least one of the phone service, the Internet access service, or the television service for the customer based on the at least one of the other product or the other service for which the customer qualifies, the customer-specific data, the rules, and other factors, wherein the other factors include a location of the customer;

assigning a weight, which corresponds to a likelihood of the customer selecting a recommendation, to each of the recommendations;

sorting the recommendations in an order based on the weights assigned to the recommendations, wherein the rules include a first rule to adjust the weight based on a duration between a last purchase date of the customer and a recommendation date, a second rule to adjust the weight based on whether the customer has ever used a product or a service included in the recommendation, and a third rule to adjust a weight of the recommendation that corresponds to a regional package; and

providing the recommendations to the customer via the at least one of the phone service, the Internet access service, or the television service.

2. The method of claim 1, further comprising:

receiving a selection of a recommendation from the customer; and

provisioning the at least one service based on the selection of the recommendation, and wherein the rules include a rule pertaining to an affinity of the customer having a product or a service to purchase another product or another service, a rule that includes an affinity of the customer purchasing a portion of a multi-package combination when the customer already is subscribed to another portion of the multi-package combination, and a rule pertaining to a purchase and a cancellation history.

3. The method of claim 1, further comprising:

archiving the recommendations; and

modifying one or more of the rules based on the archived recommendations.

4. The method of claim 1, wherein the providing comprises:

generating a customer-specific user interface that allows the customer to select from the recommendations; and

providing the recommendations in the order that is from the most likely to the least likely that the customer will select a particular recommendation, wherein the other factors include a time of a year, current events, a state of an economy, a sale history pertaining to a recommendation, and a release of a new service or a new product.

5. The method of claim 1, wherein the rules include a rule pertaining to an association of packages with respect to one or multiple factors for customers that have at least one package, a rule pertaining to a current package of the customer and all combination of packages that can be offered to the customer, and a rule pertaining to an association of packages with respect to one or multiple factors for customers with no packages.

6. The method of claim 1, wherein when the recommendations pertain to the television service in which television content is being recommended, the rules include whether the customer has previously viewed a particular television package being recommended, wherein the customer-specific data includes data pertaining to service usage, purchasing history, cancellation history, changes of service, content searches, type of equipment used by the customer, type of service used by the customer, and calls to customer service.

7. The method of claim 1, wherein the location of the customer corresponds to a ZIP code associated with the customer, and wherein the rules include a set of rules directed towards eliminating one or more recommendations, wherein the set of rules include a rule pertaining to a content filtering associated with the customer, a rule pertaining to previous offers directed towards the customer that were unsuccessful, and a rule that excludes a recommendation because of a current service used by the customer.

8. The method of claim 1, wherein the selecting further comprises:

accessing customer profile information based on the identifying;

determining products used by the customer or services subscribed to by the customer based on the accessing;

determining products or services associated with a marketing campaign;

comparing the products or the services based on the accessing with the products or the services associated with the marketing campaign; and

selecting products or services for which the customer qualifies, wherein the rules include a rule to select a default product or a default service when an insufficient number of recommendations is generated.

9. A device comprising logic configured to:

a communication interface;

a memory, wherein the memory stores instructions;

a processor, wherein the processor executes the instructions to;

obtain customer-specific data for customers receiving at least one of phone service, Internet access service, or television service;

determine at least one of a product or a service to which a customer is subscribed based on the customer-specific data

obtain a list of products or services to which the customer is not subscribed;

qualify the customer for at least one of a product or a service to recommend pertaining to the least one of the phone service, the Internet access service, or the television service in response to a determination of the least one of the product or the service to which the customer is subscribed and the list of products or services to which the customer is not subscribed;

obtain rules that include criteria for selecting recommendations that pertain to the at least one of the phone service, the Internet access service, or the television service;

generate recommendations that pertain to the at least one of the phone service, the Internet access service, or the television service for the customer based on the customer-specific data, the rules, the at least one of the product or the service for which the customer qualifies, and other factors, wherein the other factors include a location of the customer in which the customer receives the least one of the phone service, the Internet access service, or the television service;

assign a weight, which corresponds to a likelihood of the customer selecting a recommendation, to each of the recommendations; and

sort the recommendations in an order based on the weights assigned to the recommendations, wherein the rules include a first rule to adjust the weight based on a duration between a last purchase date of the customer and a recommendation date, a second rule to adjust the weight based on whether the customer has ever used a product or a service included in the recommendation, and a third rule to adjust a weight of the recommendation that corresponds to a regional package.

10. The device of claim 9, wherein the other factors include a time in which the recommendations are being provided to the customer, a state of the economy, current events, a sale history pertaining to a recommendation, and a release of a new service or a new product.

11. The device of claim 9, wherein the processor further executes the instructions to:

archive the recommendations; and

modify one or more of the rules based on the archived recommendations.

12. The device of claim 11, wherein the processor further executes the instructions to:

increase the weight or decrease the weight based on a measurement of success of the recommendation with other customers.

13. The device of claim 9, wherein the rules include criteria pertaining to customer migration history, customer affinity to a recommendation based on customer'"'"'s current subscription, and customer usage.

14. The device of claim 9, wherein the recommendations pertain to a television content package or a television content bundle associated with sports or movies, wherein the customer-specific data includes data pertaining to service usage, purchasing history, cancellation history, changes of service, content searches, type of equipment used by the customer, type of service used by the customer, and calls to customer service.

15. The device of claim 14, wherein the rules include criteria pertaining to one or more of a time period between a last purchase date and a recommendation date or whether the customer has previously viewed the television content package or the television content bundle.

16. The device of claim 9, wherein the processor further executes the instructions to:

generate the recommendations on a customer basis or a customer device-level basis, wherein the rules include a rule pertaining to an association of packages with respect to one or multiple factors for customers that have at least one package, a rule pertaining to a current package of the customer and all combination of packages that can be offered to the customer, and a rule pertaining to an association of packages with respect to one or multiple factors for customers with no packages.

17. A method comprising:

identifying a customer when the customer uses a television service;

selecting at least one of another product or another service to recommend to the customer;

gathering customer-specific data of the customer;

receiving rules that include criteria for generating recommendations on behalf of the customer;

generating, by a device, recommendations that pertain to the television service based on the at least one of the other product or the other service, the customer-specific data, and the rules,

assigning a weight, which corresponds to a likelihood of the customer selecting a recommendation, to each of the recommendations;

sorting the recommendations in an order based on the weights assigned to the recommendations, wherein the rules include a first rule to adjust the weight based on a duration between a last purchase date of the customer and a recommendation date, a second rule to adjust the weight based on whether the customer has ever used a product or a service included in the recommendation, and a third rule to adjust a weight of the recommendation that corresponds to a regional package; and

providing the recommendations to the customer via the television service.

18. The method of claim 17, further comprising:

receiving a selection of a recommendation from the customer; and

provisioning the at least one service based on the selection of the recommendation.

19. The method of claim 17, wherein the providing comprises:

generating a customer-specific user interface that allows the customer to select from the recommendations; and

providing the recommendations in the order that is from the most likely to the least likely that the customer will select a particular recommendation.

20. The method of claim 17, wherein the rules include criteria pertaining to customer migration history, customer affinity to a recommendation based on customer'"'"'s current subscription, and customer usage.