Distributed Compute Allocation Across Ad Hoc Connected Devices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing computing devices operate in fixed processing models optimized for individual tasks, failing to allocate tasks to devices with greater capability for efficient task completion.

Innovation Solution

A method for distributing compute operations across connected computing devices by selecting sensor and execution devices based on shared context information, including sensor accuracy, latency, energy usage, and battery level, to optimize task allocation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If devices execute tasks in fixed processing models optimized for individual tasks, then each device can perform its specific tasks efficiently, but the system fails to allocate tasks to devices with greater capability for efficient task completion

Engineering Contradiction:
Improvetask completion efficiencyVSAvoidtask allocation flexibility
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic task allocation where computing devices can transition between roles (sensor device, execution device, coordination device) based on real-time context information. The fixed processing model is replaced with a flexible architecture that dynamically assigns tasks to devices with optimal capabilities, resolving the contradiction between individual device efficiency and system-wide task allocation flexibility.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent enables computing devices to perform multiple functions by allowing them to act as sensor devices, execution devices, or coordination devices depending on the task requirements. This multi-functionality allows the system to allocate tasks to devices with greater capability while maintaining the ability of each device to perform its specific tasks, thus resolving the contradiction between productivity and adaptability.

Inventive Principle:
Principle #6Universality (Multi-functionality)

2Productivity

If tasks are distributed across multiple devices based on context information, then task allocation efficiency improves, but system complexity increases

Engineering Contradiction:
Improvetask allocation efficiencyVSAvoidsystem complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The patent introduces a coordination device that acts as an intermediary to manage task distribution across the network. This intermediary handles the complex decisions about task allocation based on context information, while individual computing devices maintain relatively simple local logic. This resolves the contradiction by centralizing the complexity management while distributing the actual task execution, improving task allocation efficiency without overwhelming individual devices.

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent segments the computing system into distinct functional roles (coordination device, sensor device, execution device) with specialized responsibilities. This segmentation allows each component to focus on specific tasks, reducing individual device complexity while enabling efficient system-wide task allocation through the coordinated interaction of segmented components.

Inventive Principle:
Principle #1Segmentation

3Productivity

If context information is shared among devices, then optimal task allocation is achieved, but communication overhead and energy consumption increase

Engineering Contradiction:
Improvetask allocation optimizationVSAvoidcommunication energy consumption
Core Design Contradiction:
ProductivityVSUse of energy by moving object

Solution Approach 1:

The patent implements selective context information sharing where devices exchange only the specific context data relevant to task allocation decisions rather than all possible information. This local quality approach minimizes communication overhead and energy consumption while still enabling optimal task allocation by sharing only the necessary quality of context information.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent implements partial context information sharing by selectively exchanging only the most critical context data needed for task allocation (such as current task status, device capability, and immediate environmental conditions) rather than complete context information. This partial action reduces communication energy consumption while maintaining sufficient information for effective task allocation optimization.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS12588042B2Method for distributed compute operation across connected devices
Publication Date: 2026.03.24 QUALCOMM INC
  • US12588042B2 patent drawing
  • US12588042B2 patent drawing
  • US12588042B2 patent drawing

AI summary

Various embodiments include methods and implementing computing devices, for distributing compute operation across connected wired or wireless computing devices. Various embodiments may include establishing an ad hoc communication connection with a second computing device, in which the ad hoc communication connection is part of a network of a plurality of wired or wireless computing devices communicatively connected via a plurality of ad hoc communication connections, receiving context information of the second wired or computing device via the ad hoc communication connection, selecting at least one sensor wired or wireless computing device from the plurality of wired or wireless computing devices, selecting at least one execution wired or wireless computing device from the plurality of wired or wireless computing devices, assigning a data gathering part of a work item to the sensor computing device, and assigning an execution part of the work item to the execution wired or wireless computing device.