IP Library › Granted Patent US 12,748,781
Granted Patent B2
US 12,748,781 · App. 18/812,584 · Granted Sep 29, 2026

Managing data processing efficiency, and applications thereof

Inventor: Robert Raymond Lindner (Fitchburg, WI)
Assignee: H1 Insights, Inc.
G06F16/285G06F16/215G06F16/2465G06F40/205
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,748,781
App. No.
18/812,584
Granted
Sep 29, 2026
Kind
B2
Abstract

The present disclosure relates to a system, method, and computer program product for linking data records in memory. An embodiment includes accessing a first record stored in memory. The first record holds information describing a first person and accessing at least one additional record stored in memory. The additional records hold information describing additional persons. The embodiment continues by parsing the information of the first record and additional record and assigning the parsed information to predefined categories within the respective records. After assigning the information into categories, the embodiment determines a similarity score between categorical information in the first record and categorical information of additional records. The embodiment then modifies a category of an additional record based on the similarity score to associate the additional record with the first person.

Claims (46)

1 . A computer-implemented method, comprising:

assigning, by one or more processors, a data record of an individual to a predetermined category;

allocating, by the one or more processors based on the predetermined category, an amount of memory to process the assigned data record;

in response to the amount of memory being allocated, training, by the one or more processors, a training system using the assigned data record to identify further individuals possessing similar demographic data as the individual to which the data record belongs;

identifying, by the one or more processors, the further individuals by processing further data records of individuals using the trained training system;

predicting, by the one or more processors using the trained training system, future behaviors of the further individuals based on an order of similarity between the further individuals and the individual; and

generating, by the one or more processors using the trained training system, an outcome score that correlates to the order of similarity to identify the further individuals that perform the future behaviors.

2 . The computer-implemented method of claim 1 , wherein the data record comprises: income data, consumer data, web-browsing data, or an individual's mortgage history.

3 . The computer-implemented method of claim 1 , further comprising accessing, by the one or more processors, a data record describing the individual.

4 . The computer-implemented method of claim 1 , further comprising comparing, by the one or more processors, the assigned data record against other data records stored in a database using a pair-wise function in order to determine that the assigned data record is linked, grouped, or modified to mirror an identity described by a separate data record of the other data records.

5 . The computer-implemented method of claim 1 , further comprising linking, grouping, or modifying the assigned data record to a separate data record when a pair-wise function results in a similarity score exceeding a predetermined threshold.

6 . The computer-implemented method of claim 1 , further comprising:

determining, by the one or more processors, that a current number of the one or more processors meets a current processing need of at least one of obtaining, parsing, assigning, normalizing, or linking operations; and

employing, by the one or more processors, an additional processor based on the current processing need not being satisfied, or turning off, by the one or more processors, a current processor based on the current processing need being satisfied.

7 . The computer-implemented method of claim 1 , further comprising determining, by the one or more processors, a continuation of using a third-party processor based on analyzing a current efficiency of the third-party processor, wherein the current efficiency is determined based on analyzing at least one of a size and amount of the data record to be processed or a number of the third-party processor currently in operation.

8 . A non-transitory computer readable medium storing instructions that when executed by one or more processors causes the one or more processors to perform operations comprising:

assigning a data record of an individual to a predetermined category;

allocating, based on the predetermined category, an amount of memory to process the assigned data record;

in response to the amount of memory being allocated, training a training system using the assigned data record to identify further individuals possessing similar demographic data as the individual to which the data record belongs;

identifying the further individuals by processing further data records of individuals using the trained training system;

predicting, using the trained training system, future behaviors of the further individuals based on an order of similarity between the further individuals and the individual; and

generating, using the trained training system, an outcome score that correlates to the order of similarity to identify the further individuals that perform the future behaviors.

9 . The non-transitory computer readable medium of claim 8 , wherein the data record comprises: income data, consumer data, web-browsing data, or an individual's mortgage history.

10 . The non-transitory computer readable medium of claim 8 , wherein the operations further comprise accessing a data record describing the individual.

11 . The non-transitory computer readable medium of claim 8 , wherein the operations further comprise comparing the assigned data record against other data records stored in a database using a pair-wise function in order to determine that the assigned data record is linked, grouped, or modified to mirror an identity described by a separate data record of the other data records.

12 . The non-transitory computer readable medium of claim 8 , wherein the operations further comprise linking, grouping, or modifying the assigned data record to a separate data record when a pair-wise function results in a similarity score exceeding a predetermined threshold.

13 . The non-transitory computer readable medium of claim 8 , wherein the operations further comprise:

determining that a current number of the one or more processors meets a current processing need of at least one of obtaining, parsing, assigning, normalizing, or linking operations; and

employing an additional processor based on the current processing need not being satisfied, or turning off a current processor based on the current processing need being satisfied.

14 . The non-transitory computer readable medium of claim 8 , wherein the operations further comprise determining a continuation of using a third-party processor based on analyzing a current efficiency of the third-party processor, wherein the current efficiency is determined based on analyzing at least one of a size and amount of the data record to be processed or a number of the third-party processor currently in operation.

15 . A computing system, comprising:

a memory storing instructions;

one or more processors, coupled to the memory, configured to process the stored instructions to:

assign a data record of an individual to a predetermined category;

allocate, based on the predetermined category, an amount of memory to process the assigned data record;

in response to the amount of memory being allocated, train a training system using the assigned data record to identify further individuals possessing similar demographic data as the individual to which the data record belongs;

identify the further individuals by processing further data records of individuals using the trained training system;

predict, using the trained training system, future behaviors of the further individuals based on an order of similarity between the further individuals and the individual; and

generate, using the trained training system, an outcome score that correlates to the order of similarity to identify the further individuals that perform the future behaviors.

16 . The computing system of claim 15 , wherein the data record comprises: income data, consumer data, web-browsing data, or an individual's mortgage history.

17 . The computing system of claim 15 , wherein the one or more processors are further configured to compare the assigned data record against other data records stored in a database using a pair-wise function in order to determine that the assigned data record is linked, grouped, or modified to mirror an identity described by a separate data record of the other data records.

18 . The computing system of claim 15 , wherein the one or more processors are further configured to link, group, or modify the assigned data record to a separate data record when a pair-wise function results in a similarity score exceeding a predetermined threshold.

19 . The computing system of claim 15 , wherein the one or more processors are further configured to:

determine that a current number of the one or more processors meets a current processing need of at least one of obtaining, parsing, assigning, normalizing, or linking operations; and

employ an additional processor based on the current processing need not being satisfied, or turning off a current processor based on the current processing need being satisfied.

20 . The computing system of claim 15 , wherein the one or more processors are further configured to determine a continuation of using a third-party processor based on analyzing a current efficiency of the third-party processor, wherein the current efficiency is determined based on analyzing at least one of a size and amount of the data record to be processed or a number of the third-party processor currently in operation.

Assignments (3)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 29, 2026
From: VEDA DATA SOLUTIONS, INC
To: H1 INSIGHTS, INC.
Reel/Frame 073623/0895 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 5, 2024
From: LINDNER, ROBERT RAYMOND
To: VEDA DATA SOLUTIONS, LLC
Reel/Frame 068491/0940 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 5, 2024
From: VEDA DATA SOLUTIONS LLC
To: VEDA DATA SOLUTIONS, INC.
Reel/Frame 068491/0943 →
Continuity (4)
Continuation 17699358 · Mar 21, 2022
Continuation 16731258 · Dec 31, 2019
Continuation 15072111 · Mar 16, 2016
Related Publication 20250231966A1 · Jul 17, 2025
References Cited (16)
US 6381031B1 · Mishima · 2002 [cited by applicant]
US 10521456B2 · Lindner · 2019 [cited by applicant]
US 11314782B2 · Lindner · 2022 [cited by applicant]
US 12111849B2 · Lindner · 2024 [cited by applicant]
US 20040172393A1 · Kazi et al. · 2004 [cited by applicant]
US 20100223349A1 · Thorson · 2010 [cited by applicant]
US 20130097157A1 · Ng et al. · 2013 [cited by applicant]
US 20130185306A1 · Botros · 2013 [cited by applicant]
US 20130293558A1 · George et al. · 2013 [cited by applicant]
US 20140304306A1 · Proctor et al. · 2014 [cited by applicant]
US 20150073929A1 · Psota et al. · 2015 [cited by applicant]
US 20160092557A1 · Stojanovic et al. · 2016 [cited by applicant]
US 20170091303A1 · Rashid et al. · 2017 [cited by applicant]
US 20170091393A1 · Muhammad et al. · 2017 [cited by applicant]
US 20180137150A1 · Osesina · 2018 [cited by examiner]
US 20220318274A1 · Lindner · 2022 [cited by applicant]