IP Library › Granted Patent US 12,299,603
Granted Patent B2
US 12,299,603 · App. 18/754,550 · Granted May 13, 2025

Vector-based search method and system

Inventors: Steven Dennis Flinn (Sugar Land, TX); Naomi Felina Moneypenny (Bellevue, WA)
Assignee: ManyWorlds, Inc.
G06N5/048G06F16/24575G06F16/9535G06Q50/01H04L51/216G06F40/56
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 12,299,603
App. No.
18/754,550
Granted
May 13, 2025
Kind
B2
Abstract

A vector-based search method and system generates affinity vectors within a multidimensional affinity space by applying neural networks to stored content objects. A neural network is applied to content that is input by a user to generate an affinity vector, which is then compared to the affinity vectors corresponding to the stored content objects using a mathematical-based vector comparison algorithm. One or more of the stored content objects are selected and provided to the user based on the comparison. The selecting of the one or more stored content objects may be further performed based on an inference of a preference from user behaviors.

Claims (44)

1. A computer-implemented search method comprising:

generating by applying one or more computer-implemented neural networks to each of a plurality of content objects at least one distinct affinity value that is associated with each of the plurality of content objects, wherein each of the at least one distinct affinity values represents a degree of relationship with the associated content object;

generating a plurality of affinity vectors within a multi-dimensional affinity space, wherein each of the plurality of affinity vectors corresponds to one of the plurality of content objects and comprises the at least one distinct affinity value associated with the one of the plurality of content objects;

receiving information from a user's input into a search interface;

generating by applying a computer-implemented neural network one or more affinity values that each represent a degree of relationship associated with the received information;

generating an affinity vector comprising the one or more affinity values associated with the received information;

comparing using a mathematical-based vector comparison algorithm the affinity vector associated with the received information and each of the plurality of affinity vectors;

selecting one or more of the plurality of affinity vectors in accordance with the comparing of the affinity vector associated with the received information and the each of the plurality of affinity vectors; and

providing to the user one or more of the plurality of content objects that each correspond to one of the selected one or more of the plurality of affinity vectors.

2. The method of claim 1 , further comprising receiving the information from the user, wherein the received information comprises an image.

3. The method of claim 2 , wherein the received information further comprises a plurality of syntactical elements.

4. The method of claim 1 , further comprising comparing using the mathematical-based vector comparison algorithm, wherein the vector comparison algorithm comprises calculating a cosine similarity.

5. The method of claim 1 , further comprising selecting the one or more of the plurality of affinity vectors in further accordance with an automatic inference of a preference of the user that is inferred from a plurality of usage behaviors associated with the user.

6. The method of claim 5 , further comprising selecting the one or more of the plurality of affinity vectors in the further accordance with the automatic inference of the preference of the user, wherein the preference is determined by comparing at least one of the plurality of affinity vectors with an interest affinity vector that is generated from the plurality of usage behaviors.

7. The method of claim 1 , further comprising providing to the user the one or more of the plurality of content objects, wherein the one or more of the plurality of content objects each comprise an image.

8. A computer-implemented search system comprising one or more processor-based devices configured to:

generate by applying one or more computer-implemented neural networks to each of a plurality of content objects at least one distinct affinity value that is associated with each of the plurality of content objects, wherein each of the at least one distinct affinity values represents a degree of relationship with the associated content object;

generate a plurality of affinity vectors within a multi-dimensional affinity space, wherein each of the plurality of affinity vectors corresponds to one of the plurality of content objects and comprises the at least one distinct affinity value associated with the one of the plurality of content objects;

receive information from a user's input into a search interface;

generate by applying a computer-implemented neural network one or more affinity values that each represent a degree of relationship associated with the received information;

generate an affinity vector comprising the one or more affinity values associated with the received information;

compare using a mathematical-based vector comparison algorithm the affinity vector associated with the received information and each of the plurality of affinity vectors;

select one or more of the plurality of affinity vectors in accordance with the comparing of the affinity vector associated with the received information and the each of the plurality of affinity vectors; and

provide to the user one or more of the plurality of content objects that each correspond to one of the selected one or more of the plurality of affinity vectors.

9. The system of claim 8 , further comprising the one or more processor-based devices configured to receive the information from the user, wherein the received information comprises an image.

10. The system of claim 8 , further comprising the one or more processor-based devices configured to receive the information from the user, wherein the received information comprises a plurality of syntactical elements.

11. The system of claim 8 , further comprising the one or more processor-based devices configured to compare using the mathematical-based vector comparison algorithm, wherein the vector comparison algorithm comprises calculating a cosine similarity.

12. The system of claim 8 , further comprising the one or more processor-based devices configured to select the one or more of the plurality of affinity vectors in further accordance with an automatic inference of a preference of the user that is inferred from a plurality of usage behaviors associated with the user.

13. The system of claim 12 , further comprising the one or more processor-based devices configured to select the one or more of the plurality of affinity vectors in the further accordance with the automatic inference of the preference of the user, wherein the preference is determined by comparing at least one of the plurality of affinity vectors with an interest affinity vector that is generated from the plurality of usage behaviors.

14. The system of claim 8 , further comprising the one or more processor-based devices configured to provide to the user one or more of the plurality of content objects, wherein the provided one or more of the plurality of content objects each comprise an image.

15. A computer-implemented search system comprising one or more processor-based devices configured to:

generate by applying one or more computer-implemented neural networks to each of a plurality of content objects at least one distinct affinity value that is associated with each of the plurality of content objects, wherein each of the at least one distinct affinity values represents a degree of relationship with the associated content object;

generate a plurality of affinity vectors within a multi-dimensional affinity space, wherein each of the plurality of affinity vectors corresponds to one of the plurality of content objects and comprises the at least one distinct affinity value associated with the one of the plurality of content objects, wherein each of the plurality of affinity vectors is associated with one or more contextual neighborhoods within the multi-dimensional affinity space;

receive information from a user's input into a search interface;

generate by applying a computer-implemented neural network one or more affinity values that each represent a degree of relationship associated with the received information;

generate an affinity vector comprising the one or more affinity values associated with the received information;

compare, in accordance with the one or more contextual neighborhoods associated with each of the plurality of affinity vectors and using a mathematical-based vector comparison algorithm, the affinity vector associated with the received information and each of the plurality of affinity vectors;

select one or more of the plurality of affinity vectors in accordance with the comparing of the affinity vector associated with the received information and the each of the plurality of affinity vectors; and

provide to the user one or more of the plurality of content objects that each correspond to one of the selected one or more of the plurality of affinity vectors.

16. The system of claim 15 , further comprising the one or more processor-based devices configured to receive the information from the user, wherein the received information comprises an image.

17. The system of claim 15 , further comprising the one or more processor-based devices configured to receive the information from the user, wherein the received information comprises a plurality of syntactical elements.

18. The system of claim 15 , further comprising the one or more processor-based devices configured to compare using the mathematical-based vector comparison algorithm, wherein the vector comparison algorithm comprises calculating a cosine similarity.

19. The system of claim 15 , further comprising the one or more processor-based devices configured to select the one or more of the plurality of affinity vectors in further accordance with an automatic inference of a preference of the user that is inferred from a plurality of usage behaviors associated with the user.

20. The system of claim 19 , further comprising the one or more processor-based devices configured to select the one or more of the plurality of affinity vectors in the further accordance with the automatic inference of the preference of the user, wherein the preference is determined by comparing at least one of the plurality of affinity vectors with an interest affinity vector that is generated from the plurality of usage behaviors.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Apr 15, 2026
From: MANYWORLDS, INC.
To: MANY WORLDS 2T INNOVATIONS LLC
Reel/Frame 074371/0018 →
Continuity (12)
Continuation 18083082 · Dec 16, 2022
Continuation 16666803 · Oct 29, 2019
Continuation 15249359 · Aug 27, 2016
Continuation 14856654 · Sep 17, 2015
Continuation 14462788 · Aug 19, 2014
Continuation 13555941 · Jul 23, 2012
Continuation In Part 13295414 · Nov 14, 2011
Continuation In Part 13268035 · Oct 7, 2011
Provisional Application 61513920 · Aug 1, 2011
Provisional Application 61496025 · Jun 12, 2011
Provisional Application 61469052 · Mar 29, 2011
Related Publication 20240362508A1 · Oct 31, 2024
References Cited (79)
US 5375244A · McNair · 1994 [cited by applicant]
US 5467428A · Ulug · 1995 [cited by examiner]
US 5754939A · Herz et al. · 1998 [cited by applicant]
US 5790426A · Robinson · 1998 [cited by applicant]
US 5867799A · Lang et al. · 1999 [cited by applicant]
US 5870559A · Leshem et al. · 1999 [cited by applicant]
US 5950200A · Sudai et al. · 1999 [cited by applicant]
US 6321221B1 · Bieganski · 2001 [cited by applicant]
US 6326946B1 · Moran et al. · 2001 [cited by applicant]
US 6438579B1 · Hosken · 2002 [cited by applicant]
US 6571279B1 · Herz et al. · 2003 [cited by applicant]
US 6795826B2 · Flinn · 2004 [cited by applicant]
US 6912505B2 · Linden et al. · 2005 [cited by applicant]
US 6922672B1 · Hailpern · 2005 [cited by applicant]
US 6934748B1 · Louviere · 2005 [cited by applicant]
US 6981040B1 · Konig · 2005 [cited by applicant]
US 7188153B2 · Lunt et al. · 2007 [cited by applicant]
US 7366759B2 · Trevithick · 2008 [cited by applicant]
US 7493294B2 · Flinn et al. · 2009 [cited by applicant]
US 7512612B1 · Akella et al. · 2009 [cited by applicant]
US 7558748B2 · Ehring et al. · 2009 [cited by applicant]
US 7571183B2 · Renshaw et al. · 2009 [cited by applicant]
US 7818392B1 · Martino et al. · 2010 [cited by applicant]
US 7860811B2 · Flinn et al. · 2010 [cited by applicant]
US 8645292B2 · Flinn et al. · 2014 [cited by applicant]
US 9159027B2 · Flinn et al. · 2015 [cited by applicant]
US 9454729B2 · Flinn et al. · 2016 [cited by applicant]
US 10783464B2 · Flinn et al. · 2020 [cited by applicant]
US 20020049738A1 · Epstein · 2002 [cited by applicant]
US 20020052873A1 · Delgado et al. · 2002 [cited by applicant]
US 20020069102A1 · Vellante et al. · 2002 [cited by applicant]
US 20020093537A1 · Bocioned et al. · 2002 [cited by applicant]
US 20030023427A1 · Cassin et al. · 2003 [cited by applicant]
US 20030055666A1 · Roddy · 2003 [cited by applicant]
US 20030154126A1 · Gehlot et al. · 2003 [cited by applicant]
US 20030225550A1 · Hiller et al. · 2003 [cited by applicant]
US 20030233374A1 · Spinola et al. · 2003 [cited by applicant]
US 20030234812A1 · Drucker et al. · 2003 [cited by applicant]
US 20040186776A1 · Llach · 2004 [cited by applicant]
US 20050097008A1 · Ehring et al. · 2005 [cited by applicant]
US 20050097204A1 · Horowitz et al. · 2005 [cited by applicant]
US 20060042483A1 · Work et al. · 2006 [cited by applicant]
US 20060143214A1 · Teicher · 2006 [cited by applicant]
US 20060155681A1 · Chiang et al. · 2006 [cited by applicant]
US 20070061022A1 · Hoffberg-Borghesani et al. · 2007 [cited by applicant]
US 20080209343A1 · Macadaan et al. · 2008 [cited by applicant]
US 20080243817A1 · Chan et al. · 2008 [cited by applicant]
US 20080249967A1 · Flinn et al. · 2008 [cited by applicant]
US 20090248599A1 · Hueter et al. · 2009 [cited by applicant]
US 20100145976A1 · Higgins et al. · 2010 [cited by applicant]
US 20100235313A1 · Rea et al. · 2010 [cited by applicant]
US 20110082825A1 · Sathish et al. · 2011 [cited by applicant]
US 20110125700A1 · Funada · 2011 [cited by applicant]
US 20110219011A1 · Carmel et al. · 2011 [cited by applicant]
WO WO0115052A1 · 2001 [cited by applicant]
WO WO0115449A1 · 2001 [cited by applicant]
WO WO0233628A2 · 2002 [cited by applicant]
Synergizing people, process, and technology to motivate knowledge sharing and collaboration industry case study Pickering, C.K. Collaboration Technologies and Systems (CTS), 2013 Interntional Conference on Year: 2013 pp… [cited by applicant]
Temporally adaptive motion estimation using temporal subband analysis Zung Kon Yim; Jae Ho Chung Circuits and Systems, 1996. ISCAS '96., Connecting the World., 1996 IEEE International Symposium on Year: 1996, vol. 2 pp.… [cited by applicant]
Leveraging temporal, contextual and ordering constraints or recognizing complex activities in video Laxton, B; Jongwoo Lim; Kriegman, D Computer vision and Pattern Recognition, 2007. CVPR '07 IEEE Conference on Year: 20… [cited by applicant]
An implicit spatiotemporal shape model for human activity localization and recognition Oikonomopoulos, A; Patras, I; Pantic, M. Computer Vision and Pattern Recognition Workshops, 2009, CVPR Workshops 2009. IEEE Computer… [cited by applicant]
Relationships Among Distinct Models and Notions of Equivalence for Stochastic Finite-State Systems De Renna E, C.; Leake, R.J. Computers, IEEE Transactions on Year: 1969, vol. C-18, Issue: 7 pp. 633-641, DOI: 10.1109/T-… [cited by applicant]
Study on relationship between optical signals and charge quantity of partial discharge under four typical insulation defects Zhuo Ran; Tang Ju; Fan Lei; Liu Yonggng; Zhang Xiaoxing. Electrical Insulation and Dielectric … [cited by applicant]
Analysis of spatial-temporal regularization methods for linear inverse problems from a common statistical framework Yiheng Zhang; Ghodrati, Alizera; Brooks, D.H. Biomedical Imaging: Nano to Macro, 2004. IEEE Internation… [cited by applicant]
On the Spectral Characterization and Scalable Mining of Network Communities Bo Yang; Jiming Liu; Jianfeng Feng Knowledge and Data Engineering, IEEE Transactions on Year: 2012, vol. 24, Issue: 2 pp. 326-337, DOI: 10.1109… [cited by applicant]
Automated Building of Domain Ontologies from Lecture Notes in Courseware Gantayat, N.; Iyer, S. Technology for Education (T4E), 2011 IEEE International Conference on Year: 2011 pp. 89-95, DOI: 10.1109/T4E.2011.22 Refere… [cited by applicant]
Use of usability evaluation methods in France: The reality in professional practices Roche, A.; Lespinet-Njib, V.; Andre, J.-M. User Science and Engineering (i-USEr), 2014 3rd International Conference on Year: 2014 pp. … [cited by applicant]
Modeling the Risk & Utility of Information Sharing in Social Networks Fouad, M.R.; Elbassioni, K.; Bertino, E. Privacy, Security, Risk and Trust (PASSAT), 2012 International Conference on Social Computing (SocialCom) Ye… [cited by applicant]
Droid Analytics: A Signature Based Analytic System to Collect, Extract, Analyze and Associate Android Malware Min Zheng; Mingshen Sun; Lui, J.C.S. Trust, Security, and Privacy in Computing and Communications (Trustcom),… [cited by applicant]
Using weak ties to understand resource usage behaviors in an online community of educators Ogheneovo Dibie; Tamara Sumner 2015 IEEE/ACM International Conference on Advances in Social Network Analysis and Mining (ASONAM)… [cited by applicant]
Uberveillance and the Internet of Things and People M.G. Michael; Katina Michael; Christine Perakslis, Contemporary Computing and Informatics (IC31), 2014 International Conference on Year: 2014 pp. 1381-1386, DOI: 10.11… [cited by applicant]
Inferring User Relationship from Hidden Information in WLANs Ningning Cheng; Prasant Mohapatra; Mathieu Cunche; Mohamed Ali Kaafar; Roksana Boreli; Srikanth Krishnamurthy MILCOM 2012-2012 IEEE Military Communications Co… [cited by applicant]
Financial Time Series Prediction Using Least Squares Support Vector Machines Within the Evidence Framework T. Van Gestel; J. A. K. Suykens; D.E. Baestaens; A. Lambrechts; G. Lanckriet; B. Vandaele; B. De Moor; J. Vandew… [cited by applicant]
Opinion Formation in Ising Networks M.H. Afrasiabi; R. Guerin; S.S. Venkatesh Information Theory and Applications Workshop (ITA), 2013 Year: 2013 pp. 1-10, DOI: 10.1109/ITA.2013.6502982 IEEE Conference Publications. [cited by applicant]
MsLRR: A Unified Multiscale Low-Rank Representation for Image Segmentation Xiaobai Liu; Qian Xu; Jiayi Ma; Hai jin; Yanduo Zhang IEEE Transactions on Image Processing Year: 2014, vol. 23, Issue 5 pp. 2159-2167, DOI: 10.… [cited by applicant]
A Two-Layer Text Clustering Approach for Retrospective News Event Detection Xianying Dai; Yancheng He; Yunlian Sun Artificial Intelligence and Computational Intelligence (AICI), 2010 International Conference on Year: 20… [cited by applicant]
The Anatomy of A.L.I.C.E. Richard Wallace Parsing the Turing Test 2009. R. Epstein et al. (eds.) Springer Science + Business Media B.V. 2009 pp. 181-210. [cited by applicant]
Collaborative Filtering by Personality Diagnosis: A Hybrid Memory and Model Based Approach. David Pennock; Eric Horvitz; Steve Lawrence; C. Lee Giles Uncertainty in Artificial Intelligence Proceedings 2000 pp. 473-480. [cited by applicant]
Efficient Estimation of the Value of Information in Monte Carlo Models. Tom Chavez; Max Henrion Proceedings of the Tenth Conference on Uncertainty in Artificial Intelligence 1994 pp. 119-127. [cited by applicant]