Client Crash Data Handling via Segmented Storage and Privacy Constraints

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

When a process crashes on an operating system of a client, the large dump file generated to capture the operating state is impractical to send and may contain personal identifiable information (PII), posing privacy concerns and inefficiencies in diagnosis.

Innovation Solution

A method and system that generate crash data from the dump file, store it in a cryptographically secure location on the client, and prevent its transmission to an analysis server unless the user is logged in, ensuring privacy and persistence across reboots, while only sending non-personal identifiable information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If the complete dump file is sent to the analysis server, then comprehensive crash diagnosis information is obtained, but the file size becomes too large to transmit efficiently and personal identifiable information is exposed

Engineering Contradiction:
Improvecrash diagnosis informationVSAvoiddata transmission volume
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent segments the dump file processing into two distinct paths: (1) extraction and transmission of only essential crash data to the analysis server, and (2) local retention of the complete dump file encrypted in secure storage. This segmentation allows comprehensive diagnosis capability while minimizing data transmission volume and protecting user privacy.

Inventive Principle:
Principle #1Segmentation

2Loss of information

If the complete dump file is sent to the analysis server, then comprehensive crash diagnosis information is obtained, but user privacy is compromised due to inclusion of personal identifiable information

Engineering Contradiction:
Improvecrash diagnosis informationVSAvoiduser privacy exposure
Core Design Contradiction:
Loss of informationVSObject-affected harmful factors

Solution Approach 1:

The patent extracts only the essential crash data elements needed for diagnosis (such as stack traces, register states, and error codes) from the complete dump file, leaving personal identifiable information behind in the locally stored encrypted dump file. This extraction principle enables comprehensive crash diagnosis while protecting user privacy by not transmitting PII to external servers.

Inventive Principle:
Principle #2Taking out (Extraction)

3Object-affected harmful factors

If crash data is stored in a cryptographically secure location, then user privacy is protected, but data access and transmission become more complex

Engineering Contradiction:
Improveuser privacy protectionVSAvoiddata storage and access mechanism
Core Design Contradiction:
Object-affected harmful factorsVSDevice complexity

Solution Approach 1:

The patent implements preliminary cryptographic protection by encrypting the complete dump file in secure storage location before any potential transmission scenario arises. The encryption keys are managed through the OS credential guard mechanism, which预先 establishes security boundaries. This preliminary action ensures privacy protection is automatically in place without adding complexity to the normal crash reporting workflow when the user is present.

Inventive Principle:
Principle #10Preliminary action

Data Source

PatentUS8621282B1Crash data handling
Publication Date: 2013.12.31 GOOGLE LLC
  • US8621282B1 patent drawing
  • US8621282B1 patent drawing
  • US8621282B1 patent drawing

AI summary

Systems and methods for handling a crash of a process running on an operating system (OS) of a client are provided. In some aspects, a method includes generating crash data based on a dump file associated with the crash of the process. The crash data is associated with a first user logged in to the OS at the time of the crash. The method also includes storing the crash data in a cryptographically secure location on the client such that the crash data persists across reboot of the client. The method also includes preventing the crash data from being sent to an analysis server when the first user is not logged in to the OS.