# US 12,113,936 B1 · System and method for managing routing of customer calls

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 12,113,936 B1
- Document ID: US12113936B1
- Status: Granted
- Kind: B1
- Application number: 18/454,450
- Filed: 2023-08-23
- Granted: 2024-10-08
- Earliest claimed: 2013-12-30
- Assignees: Massachusetts Mutual Life Insurance Company
- Applicants: Massachusetts Mutual Life Insurance Company
- Inventors: Gareth Ross; Andrew Reagan; Randall Schwager
- Web page: https://patentgrep.com/patent/US12113936B1

## CPC

- H04M 3/5235: {Dependent on call type or called number [DNIS]}
- G06N 5/04: Inference or reasoning models
- G06N 20/00: Machine learning
- G06Q 30/0202: Market predictions or forecasting for commercial activities
- H04M 3/5191: {interacting with the Internet}
- H04M 3/5232: {Call distribution algorithms}
- H04M 3/5238: {with waiting time or load prediction arrangements}
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR

## Abstract

A call management system of a call center identifies an inbound caller based upon computer analysis of customer identifiers, which may include at least two of customer name, street address, and zip code. Approximate string matching analysis matches n-grams generated from strings within customer identifiers, with n-grams generated from customer identification fields while searching one or more databases. Approximate string matching can incorporate a closeness metric based on Jaccard distance, and a Gaussian mixture model of best matches. In one embodiment, a Polymr search engine analyzes customer identifiers of inbound callers to retrieve customer data, such as customer demographic data, matched to the customer identifiers. In another embodiment, the Polymr search engine analyzes customer identifiers of inbound callers to identify repeat callers and retrieve previously collected customer data. Retrieved customer data is used in predictive modeling and scoring value of the inbound call, and in routing the scored inbound call.

## Claims

### Claim 1

A method for managing customer calls within a call center, comprising:
upon receiving a customer call within the call center from an inbound caller, retrieving, by a processor, a customer identifier associated with the inbound caller;
querying, by the processor, records in a customer demographic database to determine which of the records in the customer demographic database correspond to the customer identifier;
executing, by the processor, a predictive machine-learning model configured to determine a value prediction signal representative of value of the inbound caller by applying the predictive machine-learning model to the records retrieved from the customer demographic database;
routing, by the processor, the customer call to a call queue in accordance with the value prediction signal.

### Claim 2 (depends on 1)

The method of claim 1, wherein the value prediction signal corresponds to a likelihood of the inbound caller lapsing.

### Claim 3 (depends on 1)

The method of claim 1, wherein the value prediction signal corresponds to a likelihood of the inbound caller accepting an offer.

### Claim 4 (depends on 1)

The method of claim 1, further comprising:
identifying, by the processor, the records within the customer demographic database by generating an n-gram corresponding to the customer identifier and applying an n-gram model to extract a set of n-grams from strings representing a plurality of customer identifiers that correspond to the inbound caller.

### Claim 5 (depends on 4)

The method of claim 4, further comprising:
applying, by the processor, approximate string matching analysis to identify the set of n-grams extracted from the strings representing the plurality of customer identifiers.

### Claim 6 (depends on 4)

The method of claim 4, wherein the n-gram model comprises a predetermined kmer size or a predetermined step size.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
analyzing, by the processor, records in a lead database to determine whether any of the records in the lead database corresponds to the inbound caller.

### Claim 8

A system comprising:
a processor; and
a non-transitory computer readable medium in communication with the processor, the computer readable medium configured to store a set of instructions, wherein when executed, the set of instructions cause the processor to:
upon receiving a customer call within the call center from an inbound caller, retrieve a customer identifier associated with the inbound caller;
query records in a customer demographic database to determine which of the records in the customer demographic database correspond to the customer identifier;
execute a predictive machine-learning model configured to determine a value prediction signal representative of value of the inbound caller by applying the predictive machine-learning model to the records retrieved from the customer demographic database;
route the customer call to a call queue in accordance with the value prediction signal.

### Claim 9 (depends on 8)

The system of claim 8, wherein the value prediction signal corresponds to a likelihood of the inbound caller lapsing.

### Claim 10 (depends on 8)

The system of claim 8, wherein the value prediction signal corresponds to a likelihood of the inbound caller accepting an offer.

### Claim 11 (depends on 8)

The system of claim 8, wherein the set of instructions further cause the processor to:
identify the records within the customer demographic database by generating an n-gram corresponding to the customer identifier and applying an n-gram model to extract a set of n-grams from strings representing a plurality of customer identifiers that correspond to the inbound caller.

### Claim 12 (depends on 11)

The system of claim 11, wherein the set of instructions further cause the processor to:
apply approximate string matching analysis to identify the set of n-grams extracted from the strings representing the plurality of customer identifiers.

### Claim 13 (depends on 11)

The system of claim 11, wherein the n-gram model comprises a predetermined kmer size or a predetermined step size.

### Claim 14 (depends on 8)

The system of claim 8, wherein the set of instructions further cause the processor to:
analyze records in a lead database to determine whether any of the records in the lead database corresponds to the inbound caller.

### Claim 15

A system comprising:
a customer demographic database configured to store demographic data; and
a server in communication with the customer demographic database, the server configured to:
upon receiving a customer call within the call center from an inbound caller, retrieve a customer identifier associated with the inbound caller;
query records in the customer demographic database to determine which of the records in the customer demographic database correspond to the customer identifier;
execute a predictive machine-learning model configured to determine a value prediction signal representative of value of the inbound caller by applying the predictive machine-learning model to the records retrieved from the customer demographic database;
route the customer call to a call queue in accordance with the value prediction signal.

### Claim 16 (depends on 15)

The system of claim 15, wherein the value prediction signal corresponds to a likelihood of the inbound caller lapsing.

### Claim 17 (depends on 15)

The system of claim 15, wherein the value prediction signal corresponds to a likelihood of the inbound caller accepting an offer.

### Claim 18 (depends on 15)

The system of claim 15, wherein the server is further configured to:
identify the records within the customer demographic database by generating an n-gram corresponding to the customer identifier and applying an n-gram model to extract a set of n-grams from strings representing a plurality of customer identifiers that correspond to the inbound caller.

### Claim 19 (depends on 18)

The system of claim 18, wherein the n-gram model comprises a predetermined kmer size or a predetermined step size.

### Claim 20 (depends on 15)

The system of claim 15, wherein the server is further configured to:
analyze records in a lead database to determine whether any of the records in the lead database corresponds to the inbound caller.