# US 10,482,349 B2 · Systems and methods for reducing data density in large datasets > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,482,349 B2 - Document ID: US10482349B2 - Status: Granted - Kind: B2 - Application number: 16/210,796 - Filed: 2018-12-05 - Published: 2019-06-20 - Granted: 2019-11-19 - Earliest claimed: 2015-04-17 - Assignees: Inscape Data, Inc. - Applicants: Inscape Data, Inc. - Inventors: Zeev Neumeier - Web page: https://patentgrep.com/patent/US10482349B2 ## CPC - G06V 20/40: in video content (extracting overlay text G06V20/62; video retrieval G06F16/70; processing of video elementary streams in video servers H04N21/234; processing of video elementary streams in video clients H04N21/44) - G06F 16/786: {using motion, e.g. object motion or camera motion} - G06F 18/2413: based on distances to training or reference patterns - G06V 10/764: using classification, e.g. of video objects - G06V 20/47: {Detecting features for summarising video content} - G06V 40/172: {Classification, e.g. identification} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract Techniques and systems are provided for identifying unknown content. For example, a number of vectors out of a plurality of vectors projected from an origin point can be determined that are between a reference data point and an unknown data point. The number of vectors can be used to estimate an angle between a first vector (from the origin point to a reference data point) and a second vector (from the origin point to an unknown data point). A distance between the reference data point and the unknown data point can then be determined. Using the determined distance, candidate data points can be determined from a set of reference data points. The candidate data points can be analyzed to identify the unknown data point. ## Claims ### Claim 1 A computer-implemented method, comprising: obtaining a reference data point; determining first representative data associated with the reference data point, the first representative data indicating a relationship between a vector associated with the reference data point and a plurality of projected vectors; removing a number of bits associated with the reference data point from storage in response to determining the first representative data; obtaining an unknown data point; determining second representative data associated with the unknown data point, the second representative data indicating a relationship between a vector associated with the unknown data point and the plurality of projected vectors; and identifying, using the first representative data and the second representative data, one or more candidate data points for matching the unknown data point, wherein identifying the one or more candidate data points includes comparing the unknown data point to the reference data point. ### Claim 2 (depends on 1) The method of claim 1, wherein the number of bits associated with the reference data point is removed prior to identifying one or more candidate data points for matching the unknown data point. ### Claim 3 (depends on 1) The method of claim 1, wherein the first representative data includes a length of the vector associated with the reference data point. ### Claim 4 (depends on 1) The method of claim 1, wherein the first representative data includes information indicating whether a projected vector is to an algebraic left or an algebraic right of the vector associated with the reference data point. ### Claim 5 (depends on 4) The method of claim 4, wherein the first representative data includes a length of the vector associated with the reference data point. ### Claim 6 (depends on 1) The method of claim 1, further comprising storing the first representative data. ### Claim 7 (depends on 1) The method of claim 1, wherein the second representative data includes a length of the vector associated with the unknown data point. ### Claim 8 (depends on 1) The method of claim 1, wherein the second representative data includes information indicating whether a projected vector is to an algebraic left or an algebraic right of the vector associated with the unknown data point. ### Claim 9 (depends on 8) The method of claim 8, wherein the second representative data includes a length of the vector associated with the unknown data point. ### Claim 10 (depends on 1) The method of claim 1, further comprising: determining, using the first representative data and the second representative data, third representative data, the third representative data indicating a relationship between the vector associated with the reference data point and the vector associated with the unknown data point; and identifying the reference data point as a candidate data point based on the third representative data. ### Claim 11 (depends on 10) The method of claim 10, wherein the third representative data includes an angle between the vector associated with the reference data point and the vector associated with the unknown data point. ### Claim 12 (depends on 10) The method of claim 10, wherein the third representative data includes an angle between the vector associated with the reference data point and the vector associated with the unknown data point, and wherein the angle is estimated based on a number of the plurality of projected vectors between the vector associated with the reference data point and the vector associated with the unknown data point. ### Claim 13 (depends on 10) The method of claim 10, wherein the third representative data includes a distance between the reference data point and the unknown data point. ### Claim 14 (depends on 10) The method of claim 10, wherein the third representative data includes: an angle between the vector associated with the reference data point and the vector associated with the unknown data point; and a distance between the reference data point and the unknown data point, wherein the distance is determined using the angle, a length of the vector associated with the reference data point, and a length of the vector associated with the unknown data point, and wherein the reference data point is identified as the candidate data point based on the distance. ### Claim 15 (depends on 1) The method of claim 1, wherein the unknown data point is associated with content being presented by a display. ### Claim 16 (depends on 1) The method of claim 1, further comprising identifying video content being presented by a display, wherein identifying the video content includes comparing the unknown data point with the one or more candidate data points. ### Claim 17 (depends on 1) The method of claim 1, wherein the reference data point includes pixel data, and wherein removing the number of bits associated with the reference data point includes removing some or all of the pixel data from the storage. ### Claim 18 A system comprising: one or more processors; one or more non-transitory machine-readable storage media containing instructions which when executed on the one or more processors, cause the one or more processors to perform operations including: obtaining a reference data point; determining first representative data associated with the reference data point, the first representative data indicating a relationship between a vector associated with the reference data point and a plurality of projected vectors; removing a number of bits associated with the reference data point from storage in response to determining the first representative data; obtaining an unknown data point; determining second representative data associated with the unknown data point, the second representative data indicating a relationship between a vector associated with the unknown data point and the plurality of projected vectors; and identifying, using the first representative data and the second representative data, one or more candidate data points for matching the unknown data point, wherein identifying the one or more candidate data points includes comparing the unknown data point to the reference data point. ### Claim 19 (depends on 18) The system of claim 18, wherein the number of bits associated with the reference data point is removed prior to identifying one or more candidate data points for matching the unknown data point. ### Claim 20 (depends on 18) The system of claim 18, further comprising instructions, which when executed on the one or more processors, cause the one or more processors to perform operations including: determining, using the first representative data and the second representative data, third representative data, the third representative data indicating a relationship between the vector associated with the reference data point and the vector associated with the unknown data point; and identifying the reference data point as a candidate data point based on the third representative data.