Computation Modules for Parallel Data Processing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing data processing technologies are hardware-intensive and inefficient in handling diverse data types such as graphical, textual, and combined data, particularly requiring high resources and being rigid in dealing with natural languages.
Innovation Solution
A data processing device and method utilizing a large number of computation modules with artificial neuronal networks, allowing for flexible specialization and unsupervised learning through categorical constructions, which reduces hardware requirements and enhances processing efficiency by only activating relevant modules for specific data types.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If huge databases are used for data processing, then data processing capability is improved, but hardware requirements increase significantly
Solution Approach 1:
The system divides the data processing task into multiple independent computation modules, each specialized for specific data types. Instead of using one huge database, the system segments functionality across many smaller modules that can be activated as needed, reducing overall hardware requirements while maintaining processing capability.
Solution Approach 2:
The system dynamically activates only the computation modules needed for current data processing tasks. Modules remain idle when not needed, consuming minimal resources. This dynamic activation allows the system to maintain high processing capability when needed while reducing hardware requirements during idle periods.
2Ease of manufacture
If statistical methods are used for natural language processing, then processing is simplified, but adaptability to soft natural languages decreases
Solution Approach 1:
The computation modules perform unsupervised learning, allowing them to automatically adapt to natural language patterns without external intervention. The system self-adjusts to handle the soft and variable nature of natural languages through internal learning mechanisms rather than requiring rigid pre-programmed statistical models.
3Adaptability or versatility
If a large number of computation modules are used, then processing flexibility is improved, but device complexity increases
Solution Approach 1:
The system segments processing functionality into standardized computation modules that can be independently activated. This segmentation approach increases flexibility for handling different data types while managing complexity through modular architecture, where each module follows the same interface and activation patterns.
Solution Approach 2:
Each computation module is designed with universal interfaces and standardized activation mechanisms, allowing the same module type to handle different data types through parameter configuration rather than structural variation. This universality reduces overall system complexity despite having many specialized modules.
Data Source
AI summary
A data processing device and a computer-implemented method are configured to execute in parallel a data hub process (6) comprising at least a segmentation sub-process (61) which segments input data into data segments and at least one keying sub-process (62) which provides keys to the data segments creating keyed data segments, wherein the data hub process (6) stores the keyed data segments in a shared memory device (4) as shared keyed data segments and a plurality of processes in the form of computation modules (7) wherein each computation module (7) is configured to access the at least one shared memory device (4) to look for modulo-specific data segments which are shared keyed data segments that are keyed with at least one key which is specific for at least one of the computation modules (7) and to execute a machine learning method on the module-specific data segments, said machine learning method comprising data interpretation and classification methods using at least one pre-trained neuronal network (71) and to output the result of the executed machine learning method to the shared memory device (4) or another computation module.