Customer Care & Field Operations
Improve Operational Efficiency for Better Customer Experience (CX) & Lower OPEX with AI/ML-driven Operational Analytics
Guavus solutions use advanced algorithms and correlation techniques, based on artificial intelligence (AI) and machine learning (ML), to dramatically reduce the mean time to acknowledge, diagnose and resolve network and customer-premises equipment (CPE) incidents for faster alarm/problem triage with greater network/CPE uptime, service availability and quality-of-experience (QoE).
Most Popular Use Cases
for Customer Care & Field Operations
Reduce/Predict CPE NFF
Do you want to reduce the percentage of No Fault Found (NFF) on returned CPE? Do you want to avoid unnecessary network health exposures for your field technicians?
Trucks dispatched to customer premises often find no fault in the CPE, resulting in unnecessary expense, technician exposure and increased mean-time-to-resolve (MTTR) the actual problem.
Predict the likelihood of successful customer-reported issue resolution by dispatching a technician to the customer premises and provide alternative possible solution(s) when technician dispatch isn’t recommended, resulting in reduced MTTR, employee health risks, and unnecessary CPE swap-out, where the equipment is lost or sent back to warehouse for reconditioning.
Identify Subscriber Micro-Segment with Negative CX/QoE
Are you able to identify problematic subscriber micro-segments to automatically generate trouble tickets and institute inbound care (known problem) call deflection?
Network alarms and/or subscriber complaints about service/equipment.
Identify groups of subscribers having negative experience using a combination of inputs: trouble tickets, care events, network equipment telemetry, service attributes, operational events, network events, and CPE events.
Investigate CX/QoE Issue
Are you able to investigate poor QoE with unknown problem sources to remediate the problems and restore service, as well as cancel truck rolls/service center visits when appropriate?
Unknown source causing negative QoE for subscriber group.
Determine if subscriber group is having negative experience, and if so, identify problem information: 1) what services are affected 2) what specific customers are impacted (account numbers and device identifiers) and 3) what do these customers have in common.
Determine QoE-Impact of Scheduled Maintenance
Can you identify the CX/QoE-impact of problematic scheduled maintenance and take counter-measures?
Unknown impact of scheduled maintenance on subscriber QoE.
Identify impact of scheduled network maintenance on subscriber CX/QoE (e.g. self-inflicted wounds), as well as the visibility into the dispatch of the field ops maintenance teams to remediate fallout, the “back-out” process for network maintenance changes and key processes to prevent maintenance from starting before scheduled time.
Determine QoE-Impact of CPE Firmware Update
Can you identify the CX/QoE-impact of problematic CPE firmware/software updates and take counter-measures?
Unknown impact of CPE firmware/software update on subscriber QoE.
Identify impact on subscriber QoE caused via problematic firmware/software updates which are pushed to subscribers’ CPE, enabling operators to quickly address CX problems seen by subset of subscribers that have received the update. Allowing the safe return to a last-known-good revision before they even know there is an issue (e.g. automated remote device reboot).