# US 2024/0202389 A1 · System and method for path analysis to manage computing resources

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

- Number: US 2024/0202389 A1
- Document ID: US20240202389A1
- Status: Published application
- Kind: A1
- Application number: 18/068,761
- Filed: 2022-12-20
- Published: 2024-06-20
- Earliest claimed: 2022-12-20
- Assignees: Dell Products L.P.
- Applicants: Dell Products L.P.
- Inventors: IAN ROCHE; PHILIP E. HUMMEL; DHARMESH M. PATEL
- Web page: https://patentgrep.com/patent/US20240202389A1

## CPC

- G06F 30/20: Design optimisation, verification or simulation (optimisation, verification or simulation of circuit designs G06F30/30)
- G06V 40/10: Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G07C 11/00: Arrangements, systems or apparatus for checking, e.g. the occurrence of a condition, not provided for elsewhere
- G07C 2011/04: {related to queuing systems}
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G07C: TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE

## Abstract

Methods and systems for providing traffic management services are disclosed. To provide traffic management services in a manner that increases computational efficiency of hardware resources necessary to provide the traffic management services, a path manager may manage traffic management services based on fastest routes of individuals. To identify the fastest route of an individual, traversal times along routes between locations, in which the individual is to traverse, may be determined. These traversal times may be updated based on a population density observed using computer vision along the routes between the locations. Using the updated traversal times, a candidate fastest route may be determined, and the traffic may be managed based on the candidate fastest route.

## Claims

### Claim 1

A method for managing traffic flow in an environment based on macro trends, the method comprising:
obtaining a graph, the graph representing the environment, the graph comprising:
nodes that are associated with different locations in the environment, and
edges connecting the nodes, the edges representing traversal times between the different locations;
obtaining a macro trend of the macro trends, the macro trend indicating a level of foot traffic between two of the different locations, and the macro trend being obtained using computer vision;
adjusting a travel time estimate of one or more travel time estimates between two nodes of the graph using the macro trend to obtain an updated graph, the two nodes of the graph representing the two of the different locations;
performing a fastest route analysis using the updated graph to obtain a fastest route; and
managing the traffic flow using the fastest route.

### Claim 2 (depends on 1)

The method of claim 1, wherein obtaining the macro trend comprises:
obtaining an image of a scene associated with an edge of the edges; and
ingesting the image into an inference model to obtain the macro trend.

### Claim 3 (depends on 2)

The method of claim 2, wherein the macro trend comprises one selected from a group consisting of:
a number of people in a queue in the scene; and
a number of people that pass by a point in the scene.

### Claim 4 (depends on 2)

The method of claim 2, where the inference model is programmed to identify a number of people in the scene.

### Claim 5 (depends on 1)

The method of claim 1, wherein adjusting the travel time estimate comprises:
obtaining, using the macro trend, a variable level of delay; and
obtaining the travel time estimate based on the variable level of delay and a static level of delay.

### Claim 6 (depends on 5)

The method of claim 5, wherein obtaining the updated graph comprises replacing a weight of an edge of the edges using the adjusted travel time estimate to obtain an updated edge of the edges.

### Claim 7 (depends on 6)

The method of claim 6, wherein the edge connects the two nodes.

### Claim 8 (depends on 6)

The method of claim 6, wherein performing a fastest route analysis comprises:
using the updated edge to obtain a travel time estimate for a candidate fastest route.

### Claim 9

A non-transitory machine-readable medium having instructions stored therein, which when executed by a processor, cause the processor to perform operations for managing traffic flow in an environment based on macro trends, the operations comprising:
obtaining a graph, the graph representing the environment, the graph comprising:
nodes that are associated with different locations in the environment, and
edges connecting the nodes, the edges representing traversal times between the different locations associated with the nodes;
obtaining a macro trend of the macro trends, the macro trend indicating a level of foot traffic between two of the different locations, and the macro trend being obtained using computer vision;
adjusting a travel time estimate of one or more travel time estimates between two nodes of the graph using the macro trend to obtain an updated graph, the two nodes of the graph representing the two of the different locations;
performing a fastest route analysis using the updated graph to obtain a fastest route; and
managing the traffic flow using the fastest route.

### Claim 10 (depends on 9)

The non-transitory machine-readable medium of claim 9, wherein obtaining the macro trend comprises:
obtaining an image of a scene associated with an edge of the edges; and
ingesting the image into an inference model to obtain the macro trend.

### Claim 11 (depends on 10)

The non-transitory machine-readable medium of claim 10, wherein the macro trend comprises one selected from a group consisting of:
a number of people in a queue in the scene; and
a number of people that pass by a point in the scene.

### Claim 12 (depends on 10)

The non-transitory machine-readable medium of claim 10, where the inference model is programmed to identify a number of people in the scene.

### Claim 13 (depends on 8)

The non-transitory machine-readable medium of claim 8, wherein adjusting the travel time estimate comprises:
obtaining, using the macro trend, a variable level of delay; and
obtaining the travel time estimate based on the variable level of delay and a static level of delay.

### Claim 14 (depends on 13)

The non-transitory machine-readable medium of claim 13, wherein obtaining the updated graph comprises replacing a weight of an edge of the edges using the adjusted travel time estimate to obtain an updated edge of the edges.

### Claim 15

A data processing system, comprising:
a processor; and
a memory coupled to the processor to store instructions, which when executed by the processor, cause the processor to perform operations for managing traffic flow in an environment based on macro trends, the operations comprising:
obtaining a graph, the graph representing the environment, the graph comprising:
nodes that are associated with different locations in the environment, and
edges connecting the nodes, the edges representing traversal times between the different locations associated with the nodes;
obtaining a macro trend of the macro trends, the macro trend indicating a level of foot traffic between two of the different locations, and the macro trend being obtained using computer vision;
adjusting a travel time estimate of the travel time estimates between two nodes of the graph using the macro trend to obtain an updated graph, the two nodes of the graph representing the two of the different locations;
performing a fastest route analysis using the updated graph to obtain a fastest route; and
managing the traffic flow using the fastest route.

### Claim 16 (depends on 15)

The data processing system of claim 15, wherein obtaining the macro trend comprises:
obtaining an image of a scene associated with an edge of the edges; and
ingesting the image into an inference model to obtain the macro trend.

### Claim 17 (depends on 16)

The data processing system of claim 16, wherein the macro trend comprises one selected from a group consisting of:
a number of people in a queue in the scene; and
a number of people that pass by a point in the scene.

### Claim 18 (depends on 16)

The data processing system of claim 16, where the inference model is programmed to identify a number of people in the scene.

### Claim 19 (depends on 15)

The data processing system of claim 15, wherein adjusting the travel time estimate comprises:
obtaining, using the macro trend, a variable level of delay; and
obtaining the travel time estimate based on the variable level of delay and a static level of delay.

### Claim 20 (depends on 19)

The data processing system of claim 19, wherein obtaining the updated graph comprises replacing a weight of an edge of the edges using the adjusted travel time estimate to obtain an updated edge of the edges.
