# US 2021/0174189 A1 · Optimization Framework for Real-Time Rendering of Media Using Machine Learning Techniques

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

- Number: US 2021/0174189 A1
- Document ID: US20210174189A1
- Status: Published application
- Kind: A1
- Application number: 16/704,044
- Filed: 2019-12-05
- Published: 2021-06-10
- Earliest claimed: 2019-12-05
- Assignees: International Business Machines Corporation
- Applicants: International Business Machines Corporation
- Inventors: Sinem Guven Kaya; Noah Zheutlin; Rohan R. Arora; Gerard Randolph Vanloo
- Web page: https://patentgrep.com/patent/US20210174189A1

## CPC

- G06F 9/547: {Remote procedure calls [RPC]; Web services}
- G06N 3/08: Learning methods
- G06F 9/542: {Event management; Broadcasting; Multicasting; Notifications}
- G06N 3/04: Architecture, e.g. interconnection topology
- G06N 3/0499: Feedforward networks
- G06N 3/09: Supervised learning
- G06N 3/045: Combinations of networks
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Embodiments relate to an intelligent computer platform to multi-dimensionally optimize device operation. Static hardware device data is acquired and dynamic hardware characteristic data is tracked over one or more temporal segments. A neural model (NM) is trained with corresponding device and network data. The acquired static and dynamic data is populated into the MLM, and locale processing patterns corresponding to the populated data are identified. One or more data points and corresponding measurements of the tracked hardware device characteristic data are temporally analyzed. A processing locale corresponding to the temporal analysis is identified and returned as output data, and one or more encoded actions in compliance with the identified processing locale are selectively implemented.

## Claims

### Claim 1

A computer system comprising:
a processing unit operatively coupled to memory;
an artificial intelligence (AI) platform, in communication with the processing unit, having tools to optimize device operation, the tools comprising:
a device manager to acquire static hardware device data and track dynamic hardware characteristic data over one or more temporal segments;
a data manager, operatively coupled to the device manager, to train a neural model (NM) with corresponding device and network data, including populate the acquired static and dynamic data into the NM, and identify locale processing patterns corresponding to the populated data;
an analyzer, operatively coupled to the data manager, to temporally analyze one or more data points and corresponding measurements of the tracked hardware device characteristic data;
the data manager to identify a processing locale corresponding to the temporal analysis, and to return the identified processing locale as output data; and
the device manager to selectively implement one or more encoded actions in compliance with the identified processing locale.

### Claim 2 (depends on 1)

The computer system of claim 1, further comprising the device manager to identify one or more device operation optimizations corresponding to the temporal analysis, and selectively implement one or more of the identified device optimizations.

### Claim 3 (depends on 2)

The computer system of claim 2, wherein the selectively implemented processing locale and selectively implemented one or more device operation optimizations enable communication of data in a format selected from the group consisting of: augmented reality (AR) and virtual reality (VR).

### Claim 4 (depends on 2)

The computer system of claim 2, further comprising the analyzer to create a directed graph (DG) to reflect hardware device characteristic data and populate one or more nodes of the (DG) with static hardware device data and the dynamically tracked characteristic data.

### Claim 5 (depends on 4)

The computer system of claim 4, further comprising the analyzer to dynamically assign a weight to one or more edges connecting the nodes in the created DG, the weight assignment corresponding to updated static and dynamic device and network data, and update the DG and populated data responsive the dynamic weight assignment.

### Claim 6 (depends on 5)

The computer system of claim 5, wherein the dynamic weight assignment reflects implementation of the one or more identified device operation optimizations.

### Claim 7 (depends on 2)

The computer system of claim 2, wherein the one or more device operation optimization is selected from the group consisting of: use image mode, frame per second (FSP) rate, and resolution.

### Claim 8

A computer program product to support and enable multi-dimensional device operation optimization, the computer program product comprising a computer readable storage medium having program code embodied therewith, the program code executable by a processor to:
acquire static hardware device data and track dynamic hardware characteristic data over one or more temporal segments;
train a machine neural model (NM) with corresponding device and network data, including populate the acquired static and dynamic data into the NM, and identify locale processing patterns corresponding to the populated data;
temporally analyze one or more data points and corresponding measurements of the tracked hardware device characteristic data;
identify a processing locale corresponding to the temporal analysis, and return the identified processing locale; and
selectively implement one or more encoded actions in compliance with the identified processing locale.

### Claim 9 (depends on 8)

The computer program product of claim 8, further comprising program code to identify one or more device operation optimizations corresponding to the temporal analysis, and the processing unit to selectively implement one or more of the identified device operation optimizations.

### Claim 10 (depends on 9)

The computer program product of claim 9, wherein the selectively implemented processing locale and selectively implemented one or more device operation optimizations enable communication of data in a format selected from the group consisting of: augmented reality (AR) and virtual reality (VR).

### Claim 11 (depends on 9)

The computer program product of claim 9, further comprising program code to create a directed graph (DG) to reflect hardware device characteristic data and populate one or more nodes of the (DG) with static hardware device data and the dynamically tracked characteristic data.

### Claim 12 (depends on 11)

The computer program product of claim 11, further comprising program code to dynamically assign a weight to one or more edges connecting the nodes in the created DG, the weight corresponding to updated static and dynamic device and network data, and update the DG and populated data responsive the dynamic weight assignment.

### Claim 13 (depends on 12)

The computer program product of claim 12, wherein the dynamic weight assignment reflects implementation of the one or more identified device operation optimizations.

### Claim 14 (depends on 9)

The computer program product of claim 9, wherein the one or more device operation optimization is selected from the group consisting of: use image mode, frame per second (FSP) rate, and resolution.

### Claim 15

A computer implemented method, comprising:
acquiring static hardware device data and tracking dynamic hardware characteristic data over one or more temporal segments;
training a neural model (NM) with corresponding device and network data, including populating the acquired static and dynamic data into the NM, and identifying locale processing patterns corresponding to the populated data;
temporally analyzing one or more data points and corresponding measurements of the tracked hardware device characteristic data;
identifying a processing locale corresponding to the temporal analysis, and returning the identified processing locale; and
selectively implementing one or more encoded actions in compliance with the identified processing locale.

### Claim 16 (depends on 15)

The computer implemented method of claim 15, further comprising identifying one or more device operation optimizations corresponding to the temporal analysis, and selectively implementing one or more of the identified device operation optimizations.

### Claim 17 (depends on 16)

The computer implemented method of claim 16, wherein the selectively implemented processing locale and selectively implemented one or more device optimizations enable communication of data in a format selected from the group consisting of: augmented reality (AR) and virtual reality (VR).

### Claim 18 (depends on 16)

The computer implemented method of claim 16, further comprising creating a directed graph (DG) reflecting hardware device characteristic data and populating one or more nodes of the (DG) with static hardware device data and the dynamically tracked characteristic data.

### Claim 19 (depends on 18)

The computer implemented method of claim 18, further comprising dynamically assigning a weight to one or more edges connecting the nodes in the created DG, the weight corresponding to updated static and dynamic device and network data, and updating the DG and populated data responsive the dynamic weight assignment.

### Claim 20 (depends on 19)

The computer implemented method of claim 19, wherein the dynamic weight assignment reflects implementation of the one or more identified device operation optimizations, and wherein the one or more device operation optimization is selected from the group consisting of: use image mode, frame per second (FSP) rate, and resolution.
