# US 12,602,449 B2 · Pattern change discovery between high dimensional data sets > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,602,449 B2 - Document ID: US12602449B2 - Status: Granted - Kind: B2 - Application number: 18/441,887 - Filed: 2024-02-14 - Published: 2024-07-11 - Granted: 2026-04-14 - Earliest claimed: 2012-10-25 - Assignees: The Research Foundation for The State University of New York - Applicants: The Research Foundation for The State University of New York - Inventors: Yi Xu; Zhongfei Mark Zhang - Web page: https://patentgrep.com/patent/US12602449B2 ## CPC - G06F 17/18: for evaluating statistical data {, e.g. average values, frequency distributions, probability functions, regression analysis (forecasting specially adapted for a specific administrative, business or logistic context G06Q10/04)} - G06F 18/213: Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract The general problem of pattern change discovery between high-dimensional data sets is addressed by considering the notion of the principal angles between the subspaces is introduced to measure the subspace difference between two high-dimensional data sets. Current methods either mainly focus on magnitude change detection of low-dimensional data sets or are under supervised frameworks. Principal angles bear a property to isolate subspace change from the magnitude change. To address the challenge of directly computing the principal angles, matrix factorization is used to serve as a statistical framework and develop the principle of the dominant subspace mapping to transfer the principal angle based detection to a matrix factorization problem. Matrix factorization can be naturally embedded into the likelihood ratio test based on the linear models. The method may be unsupervised and addresses the statistical significance of the pattern changes between high-dimensional data sets. ## Claims ### Claim 1 A method for distinguishing statistical significance of changes between first semantic data representing at least one of multimedia data, social network data, and news data at a first time and second semantic data representing at least one of multimedia data, social network data, and news data at a second time, the second semantic data being different from the first semantic data, comprising: linearly modelling at least a dominant subspace of the first semantic data and the second semantic data in a linear model defining a respective matrix; factoring each matrix into a feature basis matrix and an indicator matrix; determining principal angles which are independent of respective magnitudes of the changes, dependent on at least the feature basis matrices and the indicator matrices; adaptively determining a threshold of statistical significance based on the linear model; determining a statistical significance of the changes based on at least the principal angles and the threshold; and selectively outputting a subset of at least one of the first semantic data, and the second semantic data through a computer communication network interface associated with a prediction of a change in trajectory of the at least one of multimedia data, social network data, and news data, dependent on the statistical significance of the changes. ### Claim 2 (depends on 1) The method according to claim 1, further comprising ranking a set of objects comprising the second semantic data in dependence on at least the principal angles. ### Claim 3 (depends on 1) The method according to claim 1, further comprising ranking the subset of objects comprising the second semantic data in dependence on at least the determined statistical significance of the changes. ### Claim 4 (depends on 1) The method according to claim 1, wherein the first semantic data has a dimensionality scale which is of at least thousands. ### Claim 5 (depends on 4) The method according to claim 4, wherein said factoring comprises iteratively optimizing a factorization of the respective matrix into an estimated feature basis matrix and an estimated indicator matrix corresponding to a set of principal angles representing the changes, with at least one automated processor. ### Claim 6 (depends on 5) The method according to claim 5, wherein said determining the statistical significance of the changes comprises determining a statistical likelihood ratio with respect to alternate hypotheses regarding a statistical significance of the changes based on sets of basis vectors determined dependent on the set of principal angles from the optimized factorization of the matrix. ### Claim 7 (depends on 1) The method according to claim 1, wherein the first semantic data comprises equity market data and a news feed at a first time, and the second semantic data comprises equity market data and a news feed at a second time. ### Claim 8 A non-transitory computer readable medium storing instructions for controlling an automated processor to determine a statistical significance of changes over time in semantic data representing at least one of multimedia data, social network data, and news data having a dimensionality scale which is of at least thousands, comprising: steps for linearly modelling at least a dominant subspace of the semantic data over time to produce a linear model comprising a matrix; steps for factoring the matrix into a feature basis matrix and an indicator matrix; steps for determining a set of principal angles dependent on at least the feature basis matrices and the indicator matrices; steps for adaptively determining a threshold of statistical significance based on the linear model; steps for determining a statistical significance of changes of the semantic data over time based on an analysis of at least the principal angles and the threshold; and steps for outputting a subset of the semantic data associated with a prediction of a change in trajectory of the at least one of multimedia data, social network data, and news data, through a computer communication network interface dependent on the determined statistical significance of the changes. ### Claim 9 (depends on 8) The non-transitory computer readable medium according to claim 8, further comprising steps for adapting a process for factoring the matrix into the feature basis matrix and the indicator matrix. ### Claim 10 (depends on 8) The non-transitory computer readable medium according to claim 8, further comprising instructions for ranking a set of objects comprising the semantic data in dependence on at least the principal angles. ### Claim 11 (depends on 8) The non-transitory computer readable medium according to claim 8, further comprising instructions for ranking a set of objects comprising the semantic data in dependence on at least the determined statistical significance of the changes of the semantic data over time. ### Claim 12 (depends on 8) The non-transitory computer readable medium according to claim 8, wherein said instructions for factoring comprise instructions for iteratively optimizing a factorization of the respective matrix into an estimated feature basis matrix and an estimated indicator matrix corresponding to a set of principal angles representing the changes of the semantic data over time, with at least one automated processor. ### Claim 13 (depends on 12) The non-transitory computer readable medium according to claim 12, wherein said instructions for determining the statistical significance of the changes of the semantic data over time comprise instructions for determining a statistical likelihood ratio with respect to alternate hypotheses regarding a statistical significance of the of changes of the semantic data over time based on sets of basis vectors determined dependent on the set of principal angles from the optimized factorization of the matrix. ### Claim 14 (depends on 8) The non-transitory computer readable medium according to claim 8, wherein the semantic data comprises equity market data and a news feed, further comprising instructions for predicting whether a statistically significant change in an equity market trajectory is about to occur based on at least the determined statistical significance of the changes of the semantic data over time. ### Claim 15 A system for determining a statistical significance of changes over time in a semantic data set representing at least one of multimedia data, social network data, and news data, having a dimensionality scale which is of at least thousands, comprising: a memory configured store the changes over time in the semantic data set; and at least one automated processor configured to: linearly model at least a dominant subspace of the semantic data set, to produce respective linear models of the semantic data set at different times, each comprising a respective matrix; factor each respective matrix into a respective feature basis matrix and a respective indicator matrix; determine a set of principal angles between the linear model of the semantic data set at the different times, dependent on at least the respective feature basis matrices and the respective indicator matrices; and adaptively determine a threshold of statistical significance based on the linear model; and determine a statistical significance of changes over time based on an analysis of at least the principal angles; and a computer communication network interface configured to communicate a subset of the semantic data set associated with a prediction of a change in trajectory of the at least one of multimedia data, social network data, and news data, dependent on the determined statistical significance of the changes. ### Claim 16 (depends on 15) The system according to claim 15, wherein the at least one automated processor is further configured to rank at least a portion of the determined significant changes over time, and the computer communication network interface is further configured to communicate the ranking of the portion of the determined significant changes over time. ### Claim 17 (depends on 15) The system according to claim 15, wherein said factoring comprises iteratively optimizing the factorization of the respective matrix into the respective feature basis matrix and the respective indicator matrix. ### Claim 18 (depends on 15) The system according to claim 15, wherein the semantic data set comprises equity market data and a news feed, and the information comprises a prediction of whether a statistically significant change in equity market trajectory is about to occur.