Real time cognitive monitoring of correlations between variables

Patent metadata

Field	Value
Publication number	US-2018348274-A1
Application number	US-201715820301-A
Country	US
Kind code	A1
Filing date	Nov 21, 2017
Priority date	Jun 2, 2017
Publication date	Dec 6, 2018
Grant date	—

Abstract

Real time cognitive monitoring of correlations between variables including receiving, by a circuit, a first set of data results and a second set of data results, wherein each set of data results comprises binary data points; adding a unit of charge to a collection capacitor on the circuit for each of the first set of data results that indicates a positive data point; removing a unit of charge from the collection capacitor for each of the second set of data results that indicates a positive data point; and triggering a first sense amp on the circuit if the charge on the collection capacitor exceeds a high charge threshold, indicating that the positive data points in the first set of data results is greater than the positive data points in the second set of data results to a first statistical significance.

First claim

1 . A method of real time cognitive monitoring of correlations between variables comprising:
receiving, by a circuit, a first set of data results and a second set of data results, wherein each set of data results comprises binary data points; adding a unit of charge to a collection capacitor on the circuit for each of the first set of data results that indicates a positive data point; removing a unit of charge from the collection capacitor for each of the second set of data results that indicates a positive data point; triggering a first sense amp on the circuit if the charge on the collection capacitor exceeds a high charge threshold, indicating that the positive data points in the first set of data results is greater than the positive data points in the second set of data results to a first statistical significance; and triggering a second sense amp on the circuit if the charge on the collection capacitor drops below a low charge threshold, indicating that the positive data points in the second set of data results is greater than the positive data points in the first set of data results to a second statistical significance.

2 . The method of claim 1 ,
wherein adding the unit of charge to the collection capacitor comprises transferring the unit of charge to the collection capacitor from a first charge capacitor charged to the circuit voltage; and wherein removing the unit of charge to the collection capacitor comprises transferring a negative unit of charge to the collection capacitor from a second charge capacitor charged to ground.

3 . The method of claim 2 , wherein the ratio of the capacity of the charge capacitors to the collection capacitor is a function of circuit voltage and a statistically significant number of units of charge.

4 . The method of claim 1 , wherein the high charge threshold and the low charge threshold are calculated as a function of a probability range, a confidence level, and a statistically significant number of units of charge.

5 . The method of claim 1 , further comprising:
precharging the collection capacitor to a midpoint voltage, wherein the collection capacitor comprises a first collection capacitor and a second collection capacitor separated by a precharge pass gate, and wherein precharging the collection capacitor to the midpoint voltage comprises:
placing a voltage above the midpoint voltage on the first collection capacitor;
placing a voltage below the midpoint voltage on the second collection capacitor; and
opening the precharge pass gate causing the first collection capacitor and the second collection capacitor to be charged to the midpoint voltage.

6 . The method of claim 1 , further comprising:
resetting the collection capacitor to a midpoint voltage in response to triggering the first sense amp; and resetting the collection capacitor to a midpoint voltage in response to triggering the second sense amp.

7 . The method of claim 1 , wherein the positive data points in the first set of data results indicate a first type of relationship between a first test result and a second test result, and wherein the positive data points in the second set of data results indicate a second type of relationship between the first test result and the second test result.

8 - 20 . (canceled)

Assignees

• IBM

Inventors

• Erickson Karl R
• Paone Phil C
• Paulik George F
• Paulsen David P
• Richetta Raymond A
• Sheets Ii John E
• Uhlmann Gregory J

Classifications

• G01R29/24

  Arrangements for measuring quantities of charge · CPC title

• G06F2207/4802

  Special implementations · CPC title

• G01R27/2605 Primary

  Measuring capacitance (capacitive sensors G01D5/24) · CPC title

• G06F7/02 Primary

  Comparing digital values (G06F7/06, {G06F7/22,} G06F7/38 take precedence) · CPC title

• G01R7/02

  for forming a sum or a difference · CPC title