In-Memory Time-Dependent Data Tracker for High-Speed Signal Processing

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional trackers are limited in handling multiple inputs and outputs, and they operate at slow speeds, which restricts their applications, especially in high-speed data processing and complex signal tracking scenarios.

Innovation Solution

An electronic device with processors and memory that updates a logical table with new input vectors over time, calculates a transposed kernel matrix, and determines predicted output values using this matrix and mean vectors, enabling faster and more efficient tracking of time-dependent signals.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If conventional trackers are used to handle multiple inputs and outputs, then the tracker can process multiple signals, but the processing speed is limited

Engineering Contradiction:
Improveprocessing speedVSAvoidcapability to handle multiple inputs and outputs
Core Design Contradiction:
ProductivityVSAdaptability or versatility

Solution Approach 1:

The patent segments the tracking process into distinct functional modules: a logical table for storing historical input vectors, a kernel matrix calculation unit for computing similarity measures, and a prediction unit for generating outputs. This segmentation allows each module to process specific tasks independently, improving overall processing speed while maintaining the ability to handle multiple inputs and outputs through the structured organization of data and computations.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary actions by pre-storing historical input vectors in a logical table and pre-calculating kernel matrices based on historical data. This allows the system to quickly process new inputs without recalculating everything from scratch, thereby increasing processing speed while maintaining comprehensive handling of multiple input signals through the accumulated historical data.

Inventive Principle:
Principle #10Preliminary action

2Adaptability or versatility

If conventional trackers process signals at high speed, then real-time processing is achieved, but the ability to handle multiple inputs and outputs is limited

Engineering Contradiction:
Improvecapability to handle multiple inputs and outputsVSAvoidprocessing speed
Core Design Contradiction:
Adaptability or versatilityVSProductivity

Solution Approach 1:

The patent implements a universal tracking system where a single logical table structure can store multiple types of input vectors, and a unified kernel matrix calculation mechanism can process various input combinations. This multi-functional design enables the tracker to handle multiple inputs and outputs simultaneously while maintaining high processing speed through efficient data structures and algorithms that work across different signal types.

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

Solution Approach 2:

The patent introduces a dimensional transformation by converting input vectors into a logical table format with temporal dimensions, and by calculating kernel matrices that capture relationships across multiple dimensions. This dimensional approach allows the system to process multiple inputs and outputs in parallel while maintaining computational efficiency, resolving the contradiction between versatility and processing speed.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS10949497B2High-speed multi-input tracker based on in-memory operations of time-dependent data
Publication Date: 2021.03.16 CROCUS ENERGY
  • US10949497B2 patent drawing
  • US10949497B2 patent drawing
  • US10949497B2 patent drawing

AI summary

An electronic device includes one or more processors and memory storing a first logical table for a first time. The first logical table includes a plurality of logical columns, each logical column including an input vector of a plurality of input parameters corresponding to a respective time, and a plurality of logical rows intersecting with the plurality of logical columns, each logical row corresponding to a respective input parameter. The device updates a respective logical column with a first input vector that corresponds to a second time subsequent to the first time, thereby obtaining a second logical table; obtains a first transposed kernel matrix between the second logical table for the second time and the first input vector; determines a first predicted output value for the second time; and outputs the first predicted output value.