# US 12,113,660 B1 · Graphical user interface and alerting system for detecting and mitigating problems in an agent network

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

- Number: US 12,113,660 B1
- Document ID: US12113660B1
- Status: Granted
- Kind: B1
- Application number: 18/581,450
- Filed: 2024-02-20
- Granted: 2024-10-08
- Earliest claimed: 2023-09-22
- Assignees: SAS Institute Inc.
- Applicants: SAS Institute Inc.
- Inventors: Jennifer Lee Hargrove; Ellen Laura Mir; John L. Maynard; Karen D. Haralson; Corey K. Kozak
- Web page: https://patentgrep.com/patent/US12113660B1

## CPC

- H04L 41/06: Management of faults, events, alarms or notifications
- H04L 41/046: comprising network management agents or mobile agents therefor
- H04L 41/22: comprising specially adapted graphical user interfaces [GUI]
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

In some examples a system can receive sets of usage data from agent computer systems associated with agents. The agents can be associated with service providers that provide services to service users. The system can generate a corresponding set of metric values for a common set of metrics for each agent based on a corresponding set of usage data. The common set of metrics can be used for all of the agents to detect anomalies related to the agents. The system can generate a score for each agent based on the corresponding set of metric values, wherein the score indicates a risk level associated with the agent. The system can compare the scores for the agents to a predefined threshold to identify one or more agents that may be problematic. The system can then generate a graphical user interface indicating the one or more identified agents.

## Claims

### Claim 1

A computing system of an entity, the computing system comprising:
one or more processors; and
one or more memories including program code that is executable by the one or more processors for causing the one or more processors to:
receive a plurality of sets of usage data from a plurality of agent computer systems associated with a plurality of agents, each agent computing system of the plurality of agent computing systems being associated with a corresponding agent of the plurality of agents and providing a corresponding set of usage data of the plurality of sets of usage data, wherein:
the plurality of agent computing systems are different from the computing system,
the plurality of agents are different from the entity,
the plurality of agent computing systems provide an infrastructure to support a plurality of service providers in providing one or more services to a plurality of service users,
the plurality of service providers are distinct from the plurality of agents, the entity, and the plurality of service users, and
the plurality of sets of usage data describe interactions between the plurality of service providers and the plurality of service users;
generate a corresponding set of metric values for a common set of metrics for each respective agent of the plurality of agents based on a corresponding set of usage data of the plurality of sets of usage data, wherein:
at least one metric value of the corresponding set of metric values is generated based on an output from a trained machine-learning model,
the common set of metrics are usable for all of the plurality of agents to detect anomalies related to the plurality of agents, and
the corresponding set of metric values for at least one agent of the plurality of agents is generated at least in part by normalizing the corresponding set of usage data from a first format to a second format;
generate a respective score for each respective agent of the plurality of agents based on the corresponding set of metric values, wherein the respective score indicates a respective risk level associated with the respective agent;
compare the respective score for each respective agent of the plurality of agents to a predefined threshold to identify one or more agents among the plurality of agents having respective scores that meet or exceed the predefined threshold; and
generate a graphical user interface indicating the one or more identified agents.

### Claim 2 (depends on 1)

The computing system of claim 1, wherein a service provider of the plurality of service providers is configured to:
train a machine-learning model based on training data to generate the trained machine-learning model; and
execute the trained machine-learning model to generate the output used to generate the at least one metric value.

### Claim 3 (depends on 1)

The computing system of claim 1, wherein the one or more memories further include program code that is executable by the one or more processors for causing the one or more processors to:
identify an anomaly associated with an agent of the plurality of agents based on the respective score associated with the agent.

### Claim 4 (depends on 1)

The computing system of claim 1, wherein the one or more memories further include program code that is executable by the one or more processors for causing the one or more processors to:
generate the corresponding set of metric values for each respective agent based on external data obtained from a source other than the plurality of agent computer systems.

### Claim 5 (depends on 1)

The computing system of claim 1, wherein the one or more memories further include program code that is executable by the one or more processors for causing the one or more processors to:
convert the respective score for each respective agent into a plurality of transformed scores that fall into a predesignated range of scores; and
generate the graphical user interface to indicate the plurality of transformed scores.

### Claim 6 (depends on 1)

The computing system of claim 1, wherein the one or more memories further include program code that is executable by the one or more processors for causing the one or more processors to:
generate the respective score for each respective agent by performing a weighted sum of the corresponding set of metric values.

### Claim 7 (depends on 1)

The computing system of claim 1, wherein:
the plurality of agent computer systems include a plurality of networks;
the plurality of service providers are part of the plurality of networks and configured to provide the one or more services to the service users;
the service users are client devices in communication with the plurality of service providers in the plurality of networks; and
the plurality of sets of usage data describes network activity between the plurality of service providers and the client devices.

### Claim 8 (depends on 1)

The computing system of claim 1, wherein the plurality of sets of usage data includes claims data, enrollment data, and case data.

### Claim 9 (depends on 1)

The computing system of claim 1, wherein the one or more memories further include program code that is executable by the one or more processors for causing the one or more processors to:
for each respective agent of the plurality of agents:
determine a subset of service providers, among the plurality of service providers, associated with the respective agent;
determine a first number of risky providers, in the subset of service providers, using the output from the trained machine-learning model;
determine a second number of active providers in the subset of service providers; and
compute a metric value, of the corresponding set of metric values for the respective agent, based on the first number and the second number.

### Claim 10 (depends on 1)

The computing system of claim 1, wherein the one or more memories further include program code that is executable by the one or more processors for causing the one or more processors to:
for each respective agent of the plurality of agents:
determine a subset of service providers, among the plurality of service providers, associated with the respective agent;
determine a first number of new providers, in the subset of service providers, that enrolled with the respective agent within a predefined time window of a current time;
determine a second number of active providers in the subset of service providers; and
compute a metric value, of the corresponding set of metric values for the respective agent, based on the first number and the second number.

### Claim 11

A method comprising:
receiving, by one or more processors of a computing system of an entity, a plurality of sets of usage data from a plurality of agent computer systems associated with a plurality of agents, each agent computing system of the plurality of agent computing systems being associated with a corresponding agent of the plurality of agents and providing a corresponding set of usage data of the plurality of sets of usage data, wherein:
the plurality of agent computing systems are different from the computing system,
the plurality of agents are different from the entity,
the plurality of agent computing systems provide an infrastructure to support a plurality of service providers in providing one or more services to a plurality of service users,
the plurality of service providers are distinct from the plurality of agents, the entity, and the plurality of service users, and
the plurality of sets of usage data describe interactions between the plurality of service providers and the plurality of service users;
generating, by the one or more processors, a corresponding set of metric values for a common set of metrics for each respective agent of the plurality of agents based on a corresponding set of usage data of the plurality of sets of usage data, wherein:
at least one metric value of the corresponding set of metric values is generated based on an output from a trained machine-learning model,
the common set of metrics are usable for all of the plurality of agents to detect anomalies related to the plurality of agents, and
the corresponding set of metric values for at least one agent of the plurality of agents is generated at least in part by normalizing the corresponding set of usage data from a first format to a second format;
generating, by the one or more processors, a respective score for each respective agent of the plurality of agents based on the corresponding set of metric values, wherein the respective score indicates a respective risk level associated with the respective agent;
comparing, by the one or more processors, the respective score for each respective agent of the plurality of agents to a predefined threshold to identify one or more agents among the plurality of agents having respective scores that meet or exceed the predefined threshold; and
generating, by the one or more processors, a graphical user interface indicating the one or more identified agents.

### Claim 12 (depends on 11)

The method of claim 11, wherein a service provider of the plurality of service providers is configured to:
train a machine-learning model based on training data to generate the trained machine-learning model; and
execute the trained machine-learning model to generate the output used to generate the at least one metric value.

### Claim 13 (depends on 11)

The method of claim 11, further comprising:
identifying an anomaly associated with an agent of the plurality of agents based on the respective score associated with the agent.

### Claim 14 (depends on 11)

The method of claim 11, further comprising:
generating the corresponding set of metric values for each respective agent based on external data obtained from a source other than the plurality of agent computer systems.

### Claim 15 (depends on 11)

The method of claim 11, further comprising:
converting the respective score for each respective agent into a plurality of transformed scores that fall into a predesignated range of scores; and
generating the graphical user interface to indicate the plurality of transformed scores.

### Claim 16 (depends on 11)

The method of claim 11, further comprising:
generating the respective score for each respective agent by performing a weighted sum of the corresponding set of metric values.

### Claim 17 (depends on 11)

The method of claim 11, wherein:
the plurality of agent computer systems include a plurality of networks;
the plurality of service providers are part of the plurality of networks and configured to provide the one or more services to the service users;
the service users are client devices in communication with the plurality of service providers in the plurality of networks; and
the plurality of sets of usage data describes network activity between the plurality of service providers and the client devices.

### Claim 18 (depends on 11)

The method of claim 11, wherein the plurality of sets of usage data includes claims data, enrollment data, and case data.

### Claim 19 (depends on 11)

The method of claim 11, further comprising:
for each respective agent of the plurality of agents:
determining a subset of service providers, among the plurality of service providers, associated with the respective agent;
determining a first number of risky providers, in the subset of service providers, using the output from the trained machine-learning model;
determining a second number of active providers in the subset of service providers; and
computing a metric value, of the corresponding set of metric values for the respective agent, based on the first number and the second number.

### Claim 20 (depends on 11)

The method of claim 11, further comprising:
for each respective agent of the plurality of agents:
determining a subset of service providers, among the plurality of service providers, associated with the respective agent;
determining a first number of new providers, in the subset of service providers, that enrolled with the respective agent within a predefined time window of a current time;
determining a second number of active providers in the subset of service providers; and
computing a metric value, of the corresponding set of metric values for the respective agent, based on the first number and the second number.

### Claim 21

A non-transitory computer-readable medium including program code that is executable by one or more processors of a computing system of an entity for causing the one or more processors to:
receive a plurality of sets of usage data from a plurality of agent computer systems associated with a plurality of agents, each agent computing system of the plurality of agent computing systems being associated with a corresponding agent of the plurality of agents and providing a corresponding set of usage data of the plurality of sets of usage data, wherein:
the plurality of agent computing systems are different from the computing system,
the plurality of agents are different from the entity,
the plurality of agent computing systems provide an infrastructure to support a plurality of service providers in providing one or more services to a plurality of service users,
the plurality of service providers are distinct from the plurality of agents and the plurality of service users, and
the plurality of sets of usage data describe interactions between the plurality of service providers and the plurality of service users;
generate a corresponding set of metric values for a common set of metrics for each respective agent of the plurality of agents based on a corresponding set of usage data of the plurality of sets of usage data, wherein:
at least one metric value of the corresponding set of metric values is generated based on an output from a trained machine-learning model,
the common set of metrics are usable for all of the plurality of agents to detect anomalies related to the plurality of agents, and
the corresponding set of metric values for at least one agent of the plurality of agents is generated at least in part by normalizing the corresponding set of usage data from a first format to a second format;
generate a respective score for each respective agent of the plurality of agents based on the corresponding set of metric values, wherein the respective score indicates a respective risk level associated with the respective agent;
compare the respective score for each respective agent of the plurality of agents to a predefined threshold to identify one or more agents among the plurality of agents having respective scores that meet or exceed the predefined threshold; and
generate a graphical user interface indicating the one or more identified agents.

### Claim 22 (depends on 21)

The non-transitory computer-readable medium of claim 21, wherein a service provider of the plurality of service providers is configured to:
train a machine-learning model based on training data to generate the trained machine-learning model; and
execute the trained machine-learning model to generate the output used to generate the at least one metric value.

### Claim 23 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising program code that is executable by the one or more processors for causing the one or more processors to:
identify an anomaly associated with an agent of the plurality of agents based on the respective score associated with the agent.

### Claim 24 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising program code that is executable by the one or more processors for causing the one or more processors to:
generate the corresponding set of metric values for each respective agent based on external data obtained from a source other than the plurality of agent computer systems.

### Claim 25 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising program code that is executable by the one or more processors for causing the one or more processors to:
convert the respective score for each respective agent into a plurality of transformed scores that fall into a predesignated range of scores; and
generate the graphical user interface to indicate the plurality of transformed scores.

### Claim 26 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising program code that is executable by the one or more processors for causing the one or more processors to:
generate the respective score for each respective agent by performing a weighted sum of the corresponding set of metric values.

### Claim 27 (depends on 21)

The non-transitory computer-readable medium of claim 21, wherein:
the plurality of agent computer systems include a plurality of networks;
the plurality of service providers are part of the plurality of networks and configured to provide the one or more services to the service users;
the service users are client devices in communication with the plurality of service providers in the plurality of networks; and
the plurality of sets of usage data describes network activity between the plurality of service providers and the client devices.

### Claim 28 (depends on 21)

The non-transitory computer-readable medium of claim 21, wherein the plurality of sets of usage data includes claims data, enrollment data, and case data.

### Claim 29 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising program code that is executable by the one or more processors for causing the one or more processors to:
for each respective agent of the plurality of agents:
determine a subset of service providers, among the plurality of service providers, associated with the respective agent;
determine a first number of risky providers, in the subset of service providers, using the output from the trained machine-learning model;
determine a second number of active providers in the subset of service providers; and
compute a metric value, of the corresponding set of metric values for the respective agent, based on the first number and the second number.

### Claim 30 (depends on 21)

The non-transitory computer-readable medium of claim 21, further comprising program code that is executable by the one or more processors for causing the one or more processors to:
for each respective agent of the plurality of agents:
determine a subset of service providers, among the plurality of service providers, associated with the respective agent;
determine a first number of new providers, in the subset of service providers, that enrolled with the respective agent within a predefined time window of a current time;
determine a second number of active providers in the subset of service providers; and
compute a metric value, of the corresponding set of metric values for the respective agent, based on the first number and the second number.