# US 12,111,951 B2 · Systems and methods for dataset recommendation in a zero-trust computing environment > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,111,951 B2 - Document ID: US12111951B2 - Status: Granted - Kind: B2 - Application number: 18/169,867 - Filed: 2023-02-15 - Published: 2023-08-31 - Granted: 2024-10-08 - Earliest claimed: 2022-02-25 - Assignees: BeeKeeperAI, Inc. - Applicants: BeeKeeperAI, Inc. - Inventors: Mary Elizabeth Chalk; Robert Derward Rogers - Web page: https://patentgrep.com/patent/US12111951B2 ## CPC - G06F 21/6245: {Protecting personal data, e.g. for financial or medical purposes} - G06F 16/2237: {Vectors, bitmaps or matrices} - G06F 16/2458: Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries - G06F 16/2462: {Approximate or statistical queries} - G06F 21/602: {Providing cryptographic facilities or services} - G06F 21/6254: {by anonymising data, e.g. decorrelating personal data from the owner's identification} - G16H 10/60: for patient-specific data, e.g. for electronic patient records - G16H 50/70: for mining of medical data, e.g. analysing previous cases of other patients - G06F 2221/2115: Third party - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Systems and methods for recommendation of cohort sample sets is provided. In some embodiments, a set of dataset requirements is received as a required vector set. The historical vector sets are queried. Each vector set corresponds to a known dataset. The difference between the required vector set and each of the historical vector sets is calculated by framing the distance as a p-value in a hypothesis test, compared against a threshold. The historical vector set with the least difference to the required vector set is identified. The least difference is calculated as a count of differing classes or as a numerically weighted summation of differing classes. ## Claims ### Claim 1 A computerized method for recommending a dataset in a zero-trust environment, the method comprising: receiving a set of dataset requirements as a required vector set; generating historical vector sets, wherein each vector set corresponds to a known dataset, wherein the generating the historical vector sets is performed in a sequestered enclave comprising a virtual machine running on secure computing processors; querying the historical vector sets; aggregating a plurality of permutations of historical vector sets into aggregated vectors, wherein the aggregating combines the historical vector sets into the aggregated vector by appending aggregated classes together; selecting the aggregated vector via an optimization, wherein the optimization is responsive to a minimized distance between the aggregated vector and the required vector set, wherein the distance is a calculated difference; identifying a patient cohort from the aggregated vector; brokering contact between a data consumer and a data steward to enable access to the identified patient cohort, wherein the access includes at least one of research on the patient cohort, screening the patient cohort for a pathology, screening the patient cohort for a medical intervention. ### Claim 2 (depends on 1) The method of claim 1, wherein the calculating the difference is by framing the distance as a p-value in a hypothesis test, compared against a threshold. ### Claim 3 (depends on 1) The method of claim 1, wherein the difference is calculated as a count of differing classes. ### Claim 4 (depends on 1) The method of claim 1, wherein the difference is calculated as a numerically weighted summation of differing classes. ### Claim 5 (depends on 1) The method of claim 1, wherein the dataset requirements are healthcare data and the known dataset is healthcare data. ### Claim 6 (depends on 1) The method of claim 1, wherein the optimization includes a penalty function for at least one of monetary cost, location of patients associated with the data, and source of data. ### Claim 7 A zero-trust computing system for recommending a dataset, the system comprising: a data store for receiving a set of dataset requirements as a required vector set; and a runtime server hosted within a sequestered enclave comprising a virtual machine running on secure computing processors for generating historical vector sets, wherein each vector set corresponds to a known dataset, querying the historical vector sets; calculating the difference between the required vector set and each of the historical vector sets; aggregating a plurality of permutations of historical vector sets into aggregated vectors, wherein the aggregating combines the historical vector sets into the aggregated vector by appending aggregated classes together, selecting the aggregated vector via an optimization, wherein the optimization is responsive to a minimized distance between the aggregated vector and the required vector set, wherein the distance is a calculated difference, identifying a patient cohort from the aggregated vector, brokering contact between a data consumer and a data steward to enable access to the identified patient cohort, wherein the access includes at least one of research on the patient cohort, screening the patient cohort for a pathology, screening the patient cohort for a medical intervention. ### Claim 8 (depends on 7) The system of claim 7, wherein the calculating the difference is by framing the distance as a p-value in a hypothesis test, compared against a threshold. ### Claim 9 (depends on 7) The system of claim 7, wherein the difference is calculated as a count of differing classes. ### Claim 10 (depends on 7) The system of claim 7, wherein the difference is calculated as a numerically weighted summation of differing classes. ### Claim 11 (depends on 7) The system of claim 7, wherein the dataset requirements are healthcare data and the known dataset is healthcare data. ### Claim 12 (depends on 7) The system of claim 7, wherein the optimization includes a penalty function for at least one of monetary cost, location of patients associated with the data, and source of data. ### Claim 13 A computer program products stored on non-volatile computer memory which when executed upon a computer system performs the steps of: receiving a set of dataset requirements as a required vector set; generating historical vector sets, wherein each vector set corresponds to a known dataset by encoding the dataset according to a set of classes, generating a matrix of the encoded dataset and converting the generated matrix into a series of points in a vector space, and wherein the generating the historical vector sets is performed in a sequestered enclave comprising a virtual machine running on secure computing processors; querying the historical vector sets; aggregating a plurality of permutations of historical vector sets into aggregated vectors, wherein the aggregating combines the historical vector sets into the aggregated vector by appending aggregated classes together; selecting the aggregated vector via an optimization, wherein the optimization is responsive to a minimized distance between the aggregated vector and the required vector set, wherein the distance is a calculated difference; identifying a patient cohort from the aggregated vector; brokering contact between a data consumer and a data steward to enable access to the identified patient cohort, wherein the access includes at least one of research on the patient cohort, screening the patient cohort for a pathology, screening the patient cohort for a medical intervention. ### Claim 14 (depends on 13) The computer program product of claim 13, wherein the calculating the difference is by framing the distance as a p-value in a hypothesis test, compared against a threshold. ### Claim 15 (depends on 13) The computer program product of claim 13, wherein the difference is calculated as a count of differing classes. ### Claim 16 (depends on 13) The computer program product of claim 13, wherein the difference is calculated as a numerically weighted summation of differing classes. ### Claim 17 (depends on 13) The computer program product of claim 13, wherein the dataset requirements are healthcare data and the known dataset is healthcare data. ### Claim 18 (depends on 13) The computer program product of claim 13, wherein the optimization includes a penalty function for at least one of monetary cost, location of patients associated with the data, and source of data.