Detecting Communication Network Insights of Alerts

Abstract

In one embodiment, a computing system accesses a plurality of quality of experience metrics from a plurality of geographic areas, respectively. The system identifies a first geographic area of the plurality of geographic areas connected by a first communication network that has low quality of experiences based on quality of experience metrics and a set of criteria. The set of criteria comprises one or more thresholds corresponding to the quality of experience metrics. The system determines, for the first geographic area, a severity of the low quality of experiences. The severity is based on a connection demand metric associated with each geographic area. The system identifies a second communication network that has one or more quality of experience metrics higher than the first communication network. The system sends, to the client system, instructions for automatically changing from the first communication network to the second communication network.

What is claimed is: 
     
         1 . A method comprising, by one or more computing systems:
 accessing a plurality of quality of experience metrics from a plurality of geographic areas, respectively;   identifying a first geographic area of the plurality of geographic areas connected by a first communication network that has low quality of experiences based on quality of experience metrics and a set of criteria, wherein the set of criteria comprises one or more thresholds corresponding to the quality of experience metrics;   determining, for the first geographic area, a severity of the low quality of experiences, wherein the severity is based on a connection demand metric associated with each geographic area;   identifying a second communication network that has one or more quality of experience metrics higher than the first communication network; and   sending, to a client system, instructions for automatically changing from the first communication network to the second communication network.   
     
     
         2 . The method of  claim 1 , wherein identifying the first geographic area of the plurality of geographic areas connected by the first communication network that has the low quality of experiences comprises:
 determining a percentile value for each quality of experience metric of each geographic area of the plurality of geographic areas; and   filtering the percentile values of the quality of experience metrics of the plurality of geographic areas using the one or more thresholds, wherein the one or more of the geographic areas are determined to have low quality of experiences when each of these geographic areas has at least one quality of experience metric percentile value being above the one or more thresholds.   
     
     
         3 . The method of  claim 1 , further comprising:
 sending, to the client system, instructions for presenting a quality of experience report, wherein the quality of experience report indicates the severity of the low quality of experiences.   
     
     
         4 . The method of  claim 3 , wherein the quality of experience report comprises a solution recommendation for the low quality of experiences for each identified geographic area. 
     
     
         5 . The method of  claim 4 , wherein the solution recommendation comprises one or more recommendation actions comprising one or more of:
 upgrading network;   network densification;   network traffic offloading; or   network load balancing.   
     
     
         6 . The method of  claim 3 , wherein the quality of experience report comprises a user interface, wherein the user interface comprises a map indicating the severity of the low quality of experiences for the first geographic area. 
     
     
         7 . The method of  claim 6 , wherein the user interface is configurable to indicate the quality of experience metrics associated with the low quality of experiences. 
     
     
         8 . The method of  claim 1 , wherein the connection demand metric comprises one or more of:
 a number of samples;   a number of connected devices;   a number of connected users;   an amount of transmitted data;   a network traffic metric; or   a revenue metric.   
     
     
         9 . The method of  claim 1 , wherein the quality of experience metrics comprise one or more of:
 a download speed;   a download speed of busy hours;   a network latency at all hours;   a network latency at busy hours;   a downstream latency;   an upstream latency;   a video quality score;   a quality of experience score;   a packet loss metric;   a signal strength;   a congestion indicator;   a network latency; or   a number of samples.   
     
     
         10 . The method of  claim 1 , wherein the one or more thresholds corresponding to the quality of experience metrics are determined by a machine learning model. 
     
     
         11 . One or more computer-readable non-transitory storage media embodying software that is operable when executed to:
 access a plurality of quality of experience metrics from a plurality of geographic areas, respectively;   identify a first geographic area of the plurality of geographic areas connected by a first communication network that has low quality of experiences based on quality of experience metrics and a set of criteria, wherein the set of criteria comprises one or more thresholds corresponding to the quality of experience metrics;   determine, for the first geographic area, a severity of the low quality of experiences, wherein the severity is based on a connection demand metric associated with each geographic area;   identify a second communication network that has one or more quality of experience metrics higher than the first communication network; and   send, to a client system, instructions for automatically changing from the first communication network to the second communication network.   
     
     
         12 . The computer-readable non-transitory storage media of  claim 11 , wherein identifying the first geographic area of the plurality of geographic areas connected by the first communication network that has the low quality of experiences comprises:
 determining a percentile value for each quality of experience metric of each geographic area of the plurality of geographic areas; and   filtering the percentile values of the quality of experience metrics of the plurality of geographic areas using the one or more thresholds, wherein the one or more of the geographic areas are determined to have low quality of experiences when each of these geographic areas has at least one quality of experience metric percentile value being above the one or more thresholds.   
     
     
         13 . The computer-readable non-transitory storage media of  claim 11 , wherein a solution recommendation comprises one or more recommendation actions comprising one or more of:
 sending, to the client system, instructions for presenting a quality of experience report, wherein the quality of experience report indicates the severity of the low quality of experiences.   
     
     
         14 . The computer-readable non-transitory storage media of  claim 13 , wherein the quality of experience report comprises a solution recommendation for the low quality of experiences for each identified geographic area. 
     
     
         15 . The computer-readable non-transitory storage media of  claim 14 , wherein the solution recommendation comprises the one or more recommendation actions comprising one or more of:
 upgrading network;   network densification;   network traffic offloading; or   network load balancing.   
     
     
         16 . A system comprising: one or more non-transitory computer-readable storage media embodying instructions; and one or more processors coupled to the storage media and operable to execute the instructions to:
 access a plurality of quality of experience metrics from a plurality of geographic areas, respectively;   identify a first geographic area of the plurality of geographic areas connected by a first communication network that has low quality of experiences based on quality of experience metrics and a set of criteria, wherein the set of criteria comprises one or more thresholds corresponding to the quality of experience metrics;   determine, for the first geographic area, a severity of the low quality of experiences, wherein the severity is based on a connection demand metric associated with each geographic area;   identify a second communication network that has one or more quality of experience metrics higher than the first communication network; and   send, to a client system, instructions for automatically changing from the first communication network to the second communication network.   
     
     
         17 . The system of  claim 16 , wherein identifying the first geographic area of the plurality of geographic areas connected by the first communication network that has the low quality of experiences comprises:
 determining a percentile value for each quality of experience metric of each geographic area of the plurality of geographic areas; and   filtering the percentile values of the quality of experience metrics of the plurality of geographic areas using the one or more thresholds, wherein the one or more of the geographic areas are determined to have low quality of experiences when each of these geographic areas has at least one quality of experience metric percentile value being above the one or more thresholds.   
     
     
         18 . The system of  claim 16 , further comprising:
 sending, to the client system, instructions for presenting a quality of experience report, wherein the quality of experience report indicates the severity of the low quality of experiences.   
     
     
         19 . The system of  claim 18 , wherein the quality of experience report comprises a solution recommendation for the low quality of experiences for each identified geographic area. 
     
     
         20 . The system of  claim 19 , wherein the solution recommendation comprises one or more recommendation actions comprising one or more of:
 upgrading network;   network densification;   network traffic offloading; or   network load balancing.