Game performance prediction from real-world performance data

Patent metadata

Field	Value
Publication number	US-11826657-B2
Application number	US-202217690216-A
Country	US
Kind code	B2
Filing date	Mar 9, 2022
Priority date	Nov 11, 2021
Publication date	Nov 28, 2023
Grant date	Nov 28, 2023

Abstract

In non-limiting examples of the present disclosure, systems, methods, and devices for matching device configurations to games are presented. A set of device configuration tiers may be generated from gameplay telemetry data generated by a plurality of client devices executing a plurality of games. A device configuration for a specific client device may be determined based at least on the specific client device's GUI type. When the specific client device accesses a software game library a determination may be made based on a performance tier corresponding to the device configuration for the specific client device as to whether the specific client device can adequately execute each game. One or more recommendations may be rendered and displayed in the game library based on the determination of whether the specific client device can adequately execute each game.

First claim

What is claimed is:

1. A computer-implemented method for matching device configurations to games, the computer-implemented method comprising:
determining a device configuration of a client device, the determining comprising analyzing a graphics processing unit (GPU) ID of a GPU of the client device;
determining a performance tier of the device configuration from a set of device configuration performance tiers generated from telemetry data from a plurality of client devices with different GPUs executing a plurality of games, wherein the telemetry data comprises frame rate data for each of the plurality of games executed by the plurality of client devices;
receiving an indication that the client device is accessing a software game library;
identifying, from a first subset of the telemetry data comprising telemetry data for a first specific game included in the software game library, that the determined performance tier of the device configuration for the client device is associated with a minimum acceptable frame rate for the first specific game;
identifying, from a second subset of the telemetry data comprising telemetry data for a second specific game included in the software game library, that the determined performance tier of the device configuration for the client device is associated with a frame rate that is below a minimum acceptable frame rate for the second specific game; and
providing, for display on a display device connected to the client device:
a first icon corresponding to the first specific game and an indication that the client device is a good fit for executing the first specific game, and
a second icon corresponding to the second specific game and a selectable user interface element for executing the second specific game by a server computing device.

2. The computer-implemented method of claim 1 , wherein the telemetry data further comprises display resolution data for each of the plurality of games executed by the plurality of client devices.

3. The computer-implemented method of claim 1 , wherein the plurality of client devices that generated the telemetry data are classified into device configuration groups based on GPU IDs and central processing unit (CPU) IDs.

4. The computer-implemented method of claim 1 , further comprising:
providing, for display on the display device, a third icon corresponding to the second specific game and an indication that the client device is not a good fit for executing the second specific game.

5. The computer-implemented method of claim 1 , further comprising:
identifying, from a third subset of the telemetry data comprising telemetry data for a third specific game included in the software game library, that the determined performance tier of the device configuration for the client device is associated with a frame rate that is below a threshold frame rate for the third specific game; and
in response to the client device executing the third specific game, automatically reducing processing operations for one or more tasks other than execution of the third specific game on the client device.

6. The computer-implemented method of claim 5 , wherein automatically reducing processing operations for one or more tasks other than execution of the third specific game on the client device comprises turning off electronic notifications for one or more applications executed by the client device.

7. The computer-implemented method of claim 5 , wherein automatically reducing processing operations for one or more tasks other than execution of the third specific game on the client device comprises pausing one or more background tasks being executed by the client device.

8. The computer-implemented method of claim 1 , wherein generating the set of device configuration performance tiers comprises processing the telemetry data with one or more machine learning models that have been trained to classify device configurations into performance tiers.

9. The computer-implemented method of claim 8 , wherein the one or more machine learning models comprise a neural network and an activation function.

10. The computer-implemented method of claim 9 , further comprising:
determining that a frame rate of the first specific game on the client device is below a threshold value; and
providing negative feedback to the neural network, wherein providing the negative feedback comprises training the neural network using back propagation.

11. The computer-implemented method of claim 9 , further comprising:
determining that a frame rate of the first specific game on the client device is above a threshold value; and
providing positive feedback to the neural network, wherein providing the positive feedback comprises training the neural network using back propagation.

12. The computer-implemented method of claim 1 , wherein in generating the set of device configuration performance tiers, the telemetry data is processed with one or more machine learning models that have been trained to automatically remove personal identifying information.

13. A system for matching device configurations to games, comprising:
a memory for storing executable program code; and
a processor, functionally coupled to the memory, the processor being responsive to computer-executable instructions contained in the program code and operative to:
determine a device configuration of a client device, wherein determining the device configuration comprises identifying a graphics processing unit (GPU) type of the client device;
determine a performance tier of the device configuration from a set of device configuration performance tiers generated from telemetry data from a plurality of client devices with different GPUs executing a plurality of games, wherein the telemetry data comprises frame rate data for each of the plurality of games executed by the plurality of client devices;
receive an indication that the client device is accessing a software game library;
identify, from a first subset of the telemetry data comprising telemetry data for a first specific game included in the software game library, that the determined performance tier of the device configuration for the client device is associated with a minimum acceptable frame rate for the first specific game;
identify, from a second subset of the telemetry data comprising telemetry data for a second specific game included in the software game library, that the determined performance tier of the device configuration for the client device is associated with a frame rate that is below a minimum acceptable frame rate for the second specific game; and
provide, for display on a display device connected to the client device:
a first icon corresponding to the first specific game and an indication that the client device is a good fit for executing the first specific game, and
a second icon corresponding to the second specific game and a selectable user interface element for executing the second specific game by a server computing device.

14. The system of claim 13 , wherein the telemetry data further comprises display resolution data for each of the plurality of games executed by the plurality of client devices.

15. The system of claim 13 , wherein the plurality of client devices that generated the telemetry data are classified into device configuration groups based on GPU types and central processing unit (CPU) types.

16. The system of claim 13 , wherein the processor is further responsive to the computer-executable instructions contained in the program code and operative to:
provide, for display on the display device, a third icon correspondi

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Verma Arunabh
• Rana Rajneil Singh
• Hosseini Khayat Seyed Ali
• Dubois Matthew Carl
• Dobyns Daniel Aaron
• Merry Sebastian Carl
• Solimini Griffin
• Hsu Shu-Wei
• Bailey William Jarrad
• Kiesow Timothy John
• Hamilton Eric
• Kavi Kripal

Classifications

• A63F13/77 Primary

  involving data related to game devices or game servers, e.g. configuration data, software version or amount of memory · CPC title

• A63F13/335

  using Internet · CPC title

• G06N3/10

  Interfaces, programming languages or software development kits, e.g. for simulating neural networks · CPC title

• A63F2300/535

  for monitoring, e.g. of user parameters, terminal parameters, application parameters, network parameters · CPC title

• A63F13/67 Primary

  adaptively or by learning from player actions, e.g. skill level adjustment or by storing successful combat sequences for re-use · CPC title