Interested in licensing this patent?

MTEC can help explore whether this patent might be available for licensing for your application.

Publication Number

US-12645977-B1

Patent

Publication Date

2026-06-02

Expiration Date


Abstract

Systems and methods ingest extensive data regarding parties and contextual data to determine correlation between a variety of data types, parameters related thereto, and member service representative (MSR) contact events and corresponding staffing levels. The appropriate level of staffing, based on real-time and historical context to meet demand for calls, emails, messages, and other contact or servicing can be calculated without overstaffing.

Core Innovation

A method ingests member service representative (MSR) contact data describing at least one MSR contact event into a contact record having a record format, and ingests contextual data describing context surrounding the at least one MSR contact event into the same record format. The contextual data comprises Internet of Things (IoT) device data received from at least one of vehicles or appliances and is indicative of changes in usage patterns of the vehicles or appliances. The method determines a plurality of previously-unknown correlations between the MSR contact data and the contextual data using unsupervised machine learning and stores a plurality of correlation entries including parameters associated with the plurality of previously-unknown correlations.

The method identifies an additional correlation and determines, using supervised machine learning and based on similarities between the additional correlation and the plurality of previously-unknown correlations, to revise a given correlation entry by widening or narrowing a range of parameters for a contextual type associated with the given correlation entry. The method analyzes the plurality of previously-unknown correlations in reference to one another using the supervised machine learning to identify two or more causative correlations.

The method receives real-time context data, determines at least one current correlation between the real-time context data and contextual data, and maps the at least one current correlation to at least one of the two or more causative correlations. The method determines a predicted call volume during a timeframe based on the at least one current correlation and the real-time context data, and determines a predicted MSR staffing level for a quality of service level during the timeframe based on the predicted call volume.

The method determines that a scheduled MSR staffing level does not satisfy the predicted MSR staffing level at the quality of service and causes an update to MSR scheduling based on a difference between the scheduled MSR staffing level and the predicted MSR staffing level.

Claims Coverage

Independent claims are included for a method, a system, and a non-transitory computer-readable medium, with seven inventive features across the independent claim sets.

Ingesting MSR contact data with record-formatted contextual IoT data indicative of usage-pattern changes

Ingest MSR contact data describing at least one MSR contact event into a contact record having a record format, and ingest contextual data describing context surrounding the at least one MSR contact event into the record format, where the contextual data comprises Internet of Things (IoT) device data received from at least one of vehicles or appliances indicative of changes in usage patterns.

Discovering previously-unknown correlations using unsupervised machine learning and storing correlation entries

Determine a plurality of previously-unknown correlations between the MSR contact data and the contextual data using unsupervised machine learning, and store a plurality of correlation entries including parameters associated with the plurality of previously-unknown correlations.

Revising correlation entries with supervised machine learning by widening or narrowing parameter ranges

Identify an additional correlation, and determine using supervised machine learning based on similarities between the additional correlation and the plurality of previously-unknown correlations to revise a given correlation entry by widening or narrowing a range of parameters for a contextual type associated with a given previously-unknown correlation.

Identifying two or more causative correlations by analyzing correlations with supervised machine learning

Analyze the plurality of previously-unknown correlations in reference to one another using the supervised machine learning to identify two or more causative correlations.

Using real-time context data to determine current correlations mapped to causative correlations

Receive real-time context data, determine at least one current correlation between the real-time context data and contextual data, and ensure the at least one current correlation corresponds to at least one of the two or more causative correlations.

Predicting call volume and predicted MSR staffing level at a quality of service level

Determine a predicted call volume during a timeframe based on the at least one current correlation and the real-time context data, and determine a predicted MSR staffing level for a quality of service during the timeframe based on the predicted call volume.

Updating MSR scheduling when scheduled staffing does not satisfy predicted staffing at quality of service

Determine that a scheduled MSR staffing level does not satisfy the predicted MSR staffing level at the quality of service, and cause an update to MSR scheduling based on a difference between the scheduled MSR staffing level and the predicted MSR staffing level.

Across the independent claims, the core coverage is the combination of record-formatted ingestion of MSR contact data and IoT-based contextual data indicative of usage-pattern changes, unsupervised discovery and supervised refinement of previously-unknown correlations including causative correlations, real-time correlation determination mapped to causative correlations, prediction of call volume and predicted MSR staffing at a quality of service level, and causing an update to MSR scheduling based on a difference between scheduled and predicted staffing.

Stated Advantages

Documented Applications

No documented applications found

JOIN OUR MAILING LIST

Stay Connected with MTEC

Keep up with active and upcoming solicitations, MTEC news and other valuable information.