Patent Issued for System And Method For Managing Routing Of Customer Calls To Agents (USPTO 10,412,224)

2019 SEP 25 (NewsRx) -- By a News Reporter-Staff News Editor at Insurance Daily News -- From Alexandria, Virginia, NewsRx journalists report that a patent by the inventor Merritt, Sears (Groton, MA), filed on February 14, 2019, was published online on September 23, 2019.

The patent’s assignee for patent number 10,412,224 is Massachusetts Mutual Life Insurance Company (Springfield, Massachusetts, United States).

News editors obtained the following quote from the background information supplied by the inventors: “Customer contact centers provide an important interface for customers/partners of an organization to contact the organization. The contact can be for a request for a product or service, for trouble reporting, service request, etc. The contact mechanism in a conventional call center is via a telephone, but it could be via a number of other electronic channels, including e-mail, online chat, etc.

“The contact center consists of a number of human agents, each assigned to a telecommunication device, such as a phone or a computer for conducting email or Internet chat sessions, that is connected to a central switch. Using these devices, the agents generally provide sales, customer service, or technical support to the customers or prospective customers of a contact center, or of a contact center’s clients. Conventionally, a contact center operation includes a switch system that connects callers to agents. In an inbound contact center, these switches route inbound callers to a particular agent in a contact center, or, if multiple contact centers are deployed, to a particular contact center for further routing. When a call is received at a contact center (which can be physically distributed, e.g., the agents may or may not be in a single physical location), if a call is not answered immediately, the switch will typically place the caller on hold and then route the caller to the next agent that becomes available. This is sometimes referred to as placing the caller in a call queue. In conventional methods of routing inbound callers to agents, high business value calls can be subjected to a long wait while the low business value calls are often answered more promptly, possibly causing dissatisfaction on the part of the high business value caller.

“There is a need for a system and method for identifying high business value inbound callers at a call center during a time period in which inbound callers are awaiting connection to an agent. Additionally, there is a need to improve traditional methods of routing callers, such as ‘round-robin’ caller routing, to improve allocation of limited call center resources to high business value inbound callers.”

As a supplement to the background information on this patent, NewsRx correspondents also obtained the inventor’s summary information for this patent: “Embodiments described herein can automatically route a call from a customer to one of a plurality of call queue assignments based on predicted value of the telephone call. In a first step, the method retrieves from a customer database a set of enterprise customer data associated with an identified customer in a customer call. The customer database stores enterprise customer data associated with prospects, leads, and purchasers of an enterprise, such as a sponsoring organization or client of the call center. In various embodiments, the enterprise customer data comprises one or more of customer event data, activity event data, and attributions data.

“In an embodiment, the process then retrieves customer demographic data associated with the identified customer. In various embodiments, the customer demographic data may be associated with the identified customer by two or more identifying data including name of the identified customer, address of the identified customer, and zip code of the identified customer.

“The method and system selects a predictive model from a plurality of predictive models. Each of the plurality of predictive model is configured to determine a respective business outcome signal representative of one of more of likelihood of accepting an offer to purchase a product likelihood and accepting an offer to purchase a product, likelihood of not lapsing in payments for a purchased product, and likelihood of accepting an offer to purchase a product and not lapsing in payments for the purchased products. The method and system selects the one of the plurality of predictive models for which the set of enterprise customer data has a highest importance in determining the respective business outcome signal.

“The method and system executes the selected predictive model to determine a value prediction signal. In various embodiments, the value prediction signal includes one or more of a first signal representative of the likelihood that the identified customer will accept an offer to purchase a product, a second signal representative of the likelihood that the identified customer will lapse in payments for a purchased product, and a third signal representative of the likelihood that the identified customer will accept an offer to purchase the product and will not lapse in payments for the purchased product. In an embodiment, the selected predictive model determines the value prediction signal in real time by applying a logistic regression model in conjunction with a tree based model to the set of the enterprise customer data and the retrieved customer demographic data.

“Based on the value prediction signal determined, the selected predictive model classifies the identified customer into one of a first value group and a second value group. When the predictive model classifies the identified customer into the first value group, the call management system routes the customer call for the identified customer to a first call queue assignment. When the predictive model classifies the identified customer into the second value group, the call management system routes the customer call for the identified customer to a second call queue assignment.

“In various embodiments of routing customer calls, the first call queue assignment comprises a first queue position in a call queue, and the second call queue assignment comprises a second queue position in a call queue. In an embodiment, the call queue is a hold list for callers on hold for inbound customer calls. In a further embodiment of routing inbound customer calls, the first call queue assignment comprises a first call queue for connection to an agent from a first pool of call center agents, and second call queue assignment comprises a second call queue for connection to an agent from a second pool of call center agents. In another embodiment, involving outbound customer calls (call backs) initiated in response to inbound calls, the call queue is a call back list.

“The selected predictive model can include a logistic regression model and a tree based model. In an embodiment, the logistic regression model employs l.sub.1 regularization. In an embodiment, the logistic regression model employs l.sub.2 regularization. In an embodiment, the tree based model is a random forests ensemble learning method for classification. The value prediction signal can include one or more of a first signal representative of a likelihood that the identified customer will accept an offer to purchase a product, a second signal representative of a likelihood that the identified customer will lapse in payments for a purchased product, and a third signal representative of a likelihood that the identified customer will accept an offer to purchase the product and will not lapse in payments for the purchased product. In various embodiments, the a value prediction signal is a buy-only signal, a lapse-only signal, a buy-don’t-lapse signal, or combination of these signals.

“In one embodiment, a processor based method for managing customer calls within a call center comprises, upon receiving a customer call at a call center from an identified customer, retrieving, by a processor, from a customer database that stores enterprise customer data associated with customers of an enterprise, a set of the enterprise customer data associated with the identified customer in the customer call, wherein the set of the enterprise customer data comprises one or more of customer event data, activity event data, and attributions data; retrieving, by the processor, customer demographic data associated with the identified customer in the customer call; selecting, by the processor, a predictive model from a plurality of predictive models, each of the plurality of predictive models being configured to determine a respective business outcome signal representative of one of more of likelihood of accepting an offer to purchase a product, not lapsing in payments for a purchased product, and accepting an offer to purchase a product and not lapsing in payments for the purchased products, wherein the selected predictive model is the one of the plurality of predictive models for which the set of enterprise customer data has a highest importance in determining the respective business outcome signal; executing, by the processor, the selected predictive model to generate a value prediction signal by applying a logistic regression model in conjunction with a tree based model to the set of the enterprise customer data and the retrieved customer demographic data, the value prediction signal comprising one or more of a first signal representative of the likelihood that the identified customer will accept an offer to purchase a product, a second signal representative of the likelihood that the identified customer will lapse in payments for a purchased product, and a third signal representative of the likelihood that the identified customer will accept an offer to purchase the product and will not lapse in payments for the purchased product; classifying, by the selected predictive model executing on the processor based on the value prediction signal determined by the selected predictive model, the identified customer into one of a first value group and a second value group; and when the classifying step classifies the identified customer into the first value group, routing, by the processor, the customer call for the identified customer to a first call queue assignment; wherein the first call queue assignment comprises one or more of a first queue position in a call queue, and a first call queue for connection to an agent from a first pool of call center agents; and when the classifying step classifies the identified customer into the second value group, routing, by the processor, the customer call for the identified customer to a second call queue assignment; wherein the second call queue assignment comprises one or more of a second queue position in the call queue, and a second call queue for connection to an agent from a second pool of call center agents.

“In an embodiment, a system for managing customer calls within a call center, comprises an inbound telephone call receiving device for receiving a customer call to the call center; non-transitory machine-readable memory that stores a customer database including enterprise customer data associated with prospects, leads, and purchasers of an enterprise serviced by the call center, wherein the enterprise customer data comprises customer event data, activity event data, and attributions data; a predictive modeling module that stores a first predictive model of customer value, wherein the first predictive model comprises a first logistic regression model operating in conjunction with a first tree based model configured to determine a first business outcome signal, and that stores a second predictive model of customer value; and that stores a second predictive model of customer value, wherein the second predictive model comprises a second logistic regression model operating in conjunction with a second tree based model configured to determine a second business outcome signal; wherein each of the first business outcome signal and the second business outcome signal is representative of one or more of likelihood of accepting an offer to purchase a product, likelihood of not lapsing in payments for a purchased product, and likelihood of accepting an offer to purchase a product and not lapsing in payments for the purchased products; and a processor, configured to execute an inbound queue management module, wherein the processor in communication with the non-transitory machine-readable memory and the predictive modeling module executes a set of instructions instructing the processor to: upon receiving the customer call at the inbound telephone call receiving device from an identified customer, retrieve from the customer database a set of the enterprise customer data associated with the identified customer in the customer call, wherein the set of enterprise customer data comprises one or more of the customer event data, the activity event data, and attributions data; retrieve external third-party customer demographic data associated with the identified customer; select one of the first predictive model of customer value or the second predictive model of customer value, wherein for the selected predictive model the set of enterprise customer data has a highest importance in determining the respective business outcome signal; determine a value prediction signal for the identified customer via applying the selected predictive model to the set of the enterprise customer data and the retrieved customer demographic data; classify the identified customer into one of a first value group and a second value group based on the value prediction signal determined; and direct the inbound telephone call receiving device: when the inbound queue management module classifies the identified customer into the first value group, to route the customer call of the identified customer to a first call queue assignment; wherein the first call queue assignment comprises one or more of a first queue position in a call queue, and a first call queue for connection to an agent from a first pool of call center agents; and when the inbound queue management module classifies the identified customer into the second value group, to route the customer call of the identified customer to a second call queue assignment; wherein the second call queue assignment comprises one or more of a second queue position in the call queue, and a second call queue for connection to an agent from a second pool of call center agents.

“In an embodiment, a processor based method for managing customer calls within a call center, comprises, upon receiving a customer call at a call center from an identified customer, retrieving, by a processor, from a customer database that stores enterprise customer data associated with customers of an enterprise, a set of the enterprise customer data associated with the identified customer in the customer call, wherein the set of the enterprise customer data comprises one or more of customer event data, activity event data, and attributions data; retrieving, by the processor, customer demographic data associated with the identified customer in the customer call; selecting, by the processor, a predictive model from a plurality of predictive models; each of the plurality of predictive models being configured to determine a respective business outcome signal representative of one of more of likelihood of accepting an offer to purchase a product, likelihood of not lapsing in payments for a purchased product, and likelihood of accepting an offer to purchase a product and not lapsing in payments for the purchased products; wherein the selected predictive model is the one of the plurality of predictive models for which the set of enterprise customer data has a highest importance in determining the respective business outcome signal; executing, by the processor, the selected predictive model to generate a value prediction signal by applying a logistic regression model in conjunction with a tree based model to the set of the enterprise customer data and the retrieved customer demographic data, the value prediction signal comprising one or more of a first signal representative of a likelihood that the identified customer will accept an offer to purchase a product, a second signal representative of a likelihood that the identified customer will lapse in payments for a purchased product, and a third signal representative of a likelihood that the identified customer will accept an offer to purchase the product and will not lapse in payments for the purchased product; classifying, by the selected predictive model executing on the processor based on the value prediction signal determined by the selected predictive model, the identified customer into one of a first value group and a second value group; and when the classifying step classifies the identified customer into the first value group, routing, by the processor, the customer call for the identified customer to a priority call queue assignment; wherein the priority call queue assignment comprises one or more of a priority queue position in a call queue, and a priority call queue for connection to an agent from a first pool of call center agents; and when the classifying step classifies the identified customer into the second value group, routing, by the processor, the customer call for the identified customer to a subordinate call queue assignment; wherein the subordinate call queue assignment comprises one or more of a subordinate queue position in the call queue, and a subordinate call queue for connection to an agent from a second pool of call center agents.

“Other objects, features, and advantages of the present disclosure will become apparent with reference to the drawings and detailed description of the illustrative embodiments that follow.”

The claims supplied by the inventors are:

“What is claimed is:

“1. A processor-based method, comprising: receiving a customer call from an identified customer at an inbound call receiving device; in response to receiving the customer call: retrieving, by a processor, a set of enterprise customer data for the identified customer in the customer call; retrieving, by the processor, customer demographic data for the identified customer; selecting, by the processor, a predictive machine-learning model from a plurality of predictive machine-learning models, wherein each of the plurality of predictive machine-learning models is configured to determine a respective business outcome signal representative of one of more of likelihood of accepting an offer to purchase a product, not lapsing in payments for a purchased product, and accepting an offer to purchase a product and not lapsing in payments for the purchased products, wherein the selected predictive machine-learning model is the one of the plurality of predictive machine-learning models for which the set of enterprise customer data for the identified customer has a highest importance in determining the respective business outcome signal; executing, by the processor, the selected predictive machine-learning model configured to determine, for each of a plurality of customer records, a value prediction signal by inputting customer demographic data and enterprise customer data into a logistic regression model operating in conjunction with a tree based model, the predictive machine-learning model outputting a first subset of the plurality of customer records into a first value group and a second subset of the plurality of customer records into a second value group; wherein the value prediction signal comprises one or more of a first signal representative of a likelihood that the identified customer will accept an offer to purchase a product, a second signal representative of a likelihood that the identified customer will lapse in payments for a purchased product, and a third signal representative of a likelihood that the identified customer will accept an offer to purchase the product and will not lapse in payments for the purchased product; classifying, by the processor, the identified customer into one of the first value group and the second value group based on the value prediction signal determined for the identified customer; and directing, by the processor, the inbound call receiving device, in the event the processor classifies the identified customer into the first value group, to route the identified customer to a priority call queue assignment; in the event the processor classifies the identified customer into the second value group, to route the identified customer to a subordinate call queue assignment.

“2. The processor based method according to claim 1, wherein the set of the enterprise customer data for the identified customer comprises one or more of customer event data, activity event data, and attributions data.

“3. The processor based method according to claim 1, wherein the set of the enterprise customer data for the identified customer is retrieved from a customer database that stores enterprise customer data associated with customers of an enterprise.

“4. The processor based method according to claim 1, wherein the enterprise customer data is associated with prospects, leads, and purchasers of an enterprise.

“5. The processor based method according to claim 1, wherein the enterprise customer data is further associated with new business applicants of the enterprise.

“6. The processor based method according to claim 2, wherein the respective business outcome of the selected business model targets one or more of the prospects, leads, and purchasers of the enterprise, and the enterprise customer data comprises customer event data associated with the one or more of the prospects, leads, and purchasers of the enterprise targeted by the respective business outcome.

“7. The processor based method according to claim 1, wherein the enterprise customer data comprises activity events data representative of one or more of promotional activities, customer prospecting activities, and call center CRM activities.

“8. The processor based method of claim 1, wherein priority call queue assignment is a priority queue position in a call queue, and the subordinate call queue assignment is a subordinate queue position in the call queue.

“9. The processor-based method according to claim 1, wherein the priority call queue assignment is a queue position in a hold list for callers on hold for live connection to an agent, and the subordinate call queue assignment is a queue position in a call-back queue.

“10. The method of claim 1, wherein the step of selecting the predictive machine-learning model from the plurality of predictive machine-learning models selects the predictive machine-learning model from three or more predictive machine-learning models.

“11. The processor based method according to claim 1, wherein the likelihood that the identified customer will lapse in payments for a purchased product comprises a likelihood that the identified customer will fail to make a payment for the purchased product during a predetermined time period following purchase of the purchased product, wherein the predetermined time period was previously determined by modeling lifetime value over varying durations of the time period following purchase of the purchased product.

“12. The processor-based method according to claim 1, wherein the logistic regression model is one of a logistic regression model with l.sub.1 regularization or a logistic regression model with l.sub.2 regularization, and the tree-based model is a random forests ensemble learning method for classification.

“13. The processor based method according to claim 1, wherein the first value group comprises customers having a first set of modeled lifetime values, and the second value group comprises customers having a second set of modeled lifetime values, wherein modeled lifetime values in the first set of modeled lifetime values are higher than modeled lifetime values in the second set of modeled lifetime values.

“14. A system for managing customer calls within a call center, comprising: an inbound telephone call receiving device for receiving a customer call to the call center; non-transitory machine-readable memory that stores a customer database including enterprise customer data associated with customers of an enterprise serviced by the call center; a predictive modeling module that stores a first predictive model of customer value, wherein the first predictive model comprises a first logistic regression model operating in conjunction with a first tree based model configured to determine a first business outcome signal; and that stores a second predictive model of customer value, wherein the second predictive model comprises a second logistic regression model operating in conjunction with a second tree based model configured to determine a second business outcome signal; wherein each of the first business outcome signal and the second business outcome signal is representative of one or more of likelihood of accepting an offer to purchase a product, likelihood of not lapsing in payments for a purchased product, and likelihood of accepting an offer to purchase a product and not lapsing in payments for the purchased products; and a processor, wherein the processor in communication with the non-transitory machine-readable memory and the predictive modeling module executes a set of instructions instructing the processor to: upon receiving the customer call at the inbound telephone call receiving device from an identified customer, retrieve from the customer database a set of enterprise customer data associated with the identified customer in the customer call; retrieve customer demographic data associated with the identified customer; select one of the first predictive model of customer value or the second predictive model of customer value, wherein the selected predictive model is the one of the first predictive model of customer value and the second predictive model of customer value for which the retrieved set of enterprise customer data customer has a highest importance in determining the respective business outcome signal; determine a value prediction signal for the identified customer via applying the selected predictive model to the retrieved set of enterprise customer data and the retrieved customer demographic data; classify the identified customer into one of a first value group and a second value group based on the value prediction signal determined; and direct the inbound telephone call receiving device: in the event the inbound queue management module classifies the identified customer into the first value group, to route the customer call of the identified customer to a priority call queue assignment; in the event the inbound queue management module classifies the identified customer into the second value group, to route the customer call of the identified customer to a subordinate call queue assignment.

“15. The system according to claim 14, wherein the enterprise customer data comprises customer event data, activity event data, and attributions data.

“16. The system according to claim 14, wherein the customer database includes enterprise customer data associated with prospects, leads, and purchasers of the enterprise serviced by the call center.

“17. The system according to claim 14, wherein the instruction to retrieve customer demographic data associated with the identified customer comprises retrieving external customer demographic data associated with the identified customer from a third party database.

“18. The system according to claim 14, wherein the respective business outcome of the selected business model targets one or more of the prospects, leads, and purchasers of the enterprise, and the enterprise customer data comprises customer event data associated with the one or more of the prospects, leads, and purchasers of the enterprise targeted by the respective business outcome.

“19. The system according to claim 14, wherein the priority call queue assignment is a priority queue position in a call queue, and the subordinate call queue assignment is a subordinate queue position in the call queue.

“20. The system according to claim 14, wherein the priority call queue assignment is a queue position in a hold list for callers on hold for live connection to an agent, and the subordinate call queue assignment is a queue position in a call-back queue.”

For additional information on this patent, see: Merritt, Sears. System And Method For Managing Routing Of Customer Calls To Agents. U.S. Patent Number 10,412,224, filed February 14, 2019, and published online on September 23, 2019. Patent URL: http://patft.uspto.gov/netacgi/nph-Parser?Sect1=PTO1&Sect2=HITOFF&d=PALL&p=1&u=%2Fnetahtml%2FPTO%2Fsrchnum.htm&r=1&f=G&l=50&s1=10,412,224.PN.&OS=PN/10,412,224RS=PN/10,412,224

(Our reports deliver fact-based news of research and discoveries from around the world.)