Invention Grant
- Patent Title: Methods and systems for identifying a level of similarity between a plurality of data representations
-
Application No.: US17539264Application Date: 2021-12-01
-
Publication No.: US11714602B2Publication Date: 2023-08-01
- Inventor: Francisco De Sousa Webber
- Applicant: cortical.io AG
- Applicant Address: AT Vienna
- Assignee: cortical.io AG
- Current Assignee: cortical.io AG
- Current Assignee Address: AT Vienna
- Agency: Blueshift IP, LLC
- Agent Cynthia M. Gilbert
- Main IPC: G06F7/20
- IPC: G06F7/20 ; G06F16/2455 ; G06F16/33 ; G06F40/205 ; G06F40/279

Abstract:
A reference map generator clusters, into a semantic map, a set of data documents selected according to at least one criterion and associated with a medical diagnosis. A parser generates an enumeration of measurements occurring in the set of data documents. A representation generator generates for each measurement in the enumeration, a sparse distributed representation (SDR). The method includes storing, by a processor on a second computing device, in each of a plurality of memory cells on the second computing device, one of the generated SDRs. A diagnosis support module receives a document comprising a plurality of measurements. The representation generator generates a compound SDR for the document. Each of the plurality of bitwise comparison circuits determine a level of overlap between the compound SDR and the stored generated SDR. The diagnosis support module provides an identification of the medical diagnosis associated with a stored SDR.
Public/Granted literature
- US20220091817A1 Methods and Systems for Identifying a Level of Similarity Between a Plurality of Data Representations Public/Granted day:2022-03-24
Information query