# US 2023/0056439 A1 · Credential-based data access and synthesis > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2023/0056439 A1 - Document ID: US20230056439A1 - Status: Published application - Kind: A1 - Application number: 17/445,363 - Filed: 2021-08-18 - Published: 2023-02-23 - Earliest claimed: 2021-08-18 - Assignees: The Boeing Company - Applicants: The Boeing Company - Inventors: Atul Uttam Dimble; Kiran Narayan; Ryan B. Whitaker - Web page: https://patentgrep.com/patent/US20230056439A1 ## CPC - G06F 21/6218: {to a system of files or objects, e.g. local or distributed file system or database} - G06F 16/245: Query processing - G06F 21/602: {Providing cryptographic facilities or services} - G06N 3/08: Learning methods - G06N 5/022: Knowledge engineering; Knowledge acquisition - G06N 3/045: Combinations of networks - G06N 3/0475: Generative networks - G06N 5/04: Inference or reasoning models - G06N 20/00: Machine learning - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS ## Abstract A method at a computing system is described. The method comprises receiving on behalf of a user a request for information, determining access credentials of the user, and based at least on the access credentials, identifying a first portion of the information that the user has permission to access, and a second portion of the information that the user does not have permission to access. The method further comprises obtaining synthesized data configured to replace at least part of the second portion of the information, the synthesized data being different than the second portion of information, relevant to the request, and not including any information that the user does not have permission to access, and providing a data set for access by the user, the data set including the first portion of the information and the synthesized data. ## Claims ### Claim 1 At a computing system, a method, comprising: receiving on behalf of a user a request for information; determining access credentials of the user; based at least on the access credentials, identifying a first portion of the information that the user has permission to access, and a second portion of the information that the user does not have permission to access; obtaining synthesized data configured to replace at least part of the second portion of the information, the synthesized data being different than the second portion of information, relevant to the request, and not including any information that the user does not have permission to access; and providing a data set for access by the user, the data set including the first portion of the information and the synthesized data. ### Claim 2 (depends on 1) The method of claim 1, where the request includes a natural language request, the method further comprising parsing the natural language request based at least on one or more taxonomies and ontologies. ### Claim 3 (depends on 1) The method of claim 1, where the data set is encrypted, and where the data set is configured to be decrypted via a user-specific decryption key. ### Claim 4 (depends on 1) The method of claim 1, where providing the data set comprises providing an indication that the synthesized data is synthetic. ### Claim 5 (depends on 1) The method of claim 1, where the first portion of the information and the synthesized data are obtained from one or more data sources identified via an orchestration graph. ### Claim 6 (depends on 5) The method of claim 5, where providing the data set comprises executing a query execution plan defined by the orchestration graph. ### Claim 7 (depends on 1) The method of claim 1, where the synthesized data is synthesized via one or more neural networks trained based at least on non-synthesized data. ### Claim 8 (depends on 1) The method of claim 1, where the access credentials of the user include one or more of an organizational access credential of the user, and a geographic location of the user. ### Claim 9 A computing system, comprising: a logic subsystem; and a storage subsystem comprising instructions executable by the logic subsystem to: receive on behalf of a user a request for information; determine access credentials of the user; based at least on the access credentials, identify a first portion of the information that the user has permission to access, and a second portion of the information that the user does not have permission to access; obtain synthesized data configured to replace at least part of the second portion of the information, the synthesized data being different than the second portion of information, relevant to the request, and not including any information that the user does not have permission to access; and provide a data set for access by the user, the data set including the first portion of the information and the synthesized data. ### Claim 10 (depends on 9) The computing system of claim 9, where the request includes a natural language request, further comprising instructions executable to parse the natural language request based at least on one or more taxonomies and ontologies. ### Claim 11 (depends on 9) The computing system of claim 9, where the data set is encrypted, and where the data set is configured to be decrypted via a user-specific decryption key. ### Claim 12 (depends on 9) The computing system of claim 9, where the instructions executable to provide the data set are further executable to provide an indication that the synthesized data is synthetic. ### Claim 13 (depends on 9) The computing system of claim 9, where the first portion of the information and the synthesized data are obtained from one or more data sources identified via an orchestration graph. ### Claim 14 (depends on 13) The computing system of claim 13, where the instructions executable to provide the data set are further executable to execute a query execution plan defined by the orchestration graph. ### Claim 15 (depends on 9) The computing system of claim 9, where the synthesized data is synthesized via one or more neural networks trained based at least on non-synthesized data. ### Claim 16 (depends on 9) The computing system of claim 9, where the access credentials of the user include one or more of an organizational access credential of the user, and a geographic location of the user. ### Claim 17 At a computing system, a method, comprising: receiving on behalf of a user a request for information; determining access credentials of the user; based at least on the access credentials, identifying a first portion of the information that the user has permission to access, and a second portion of the information that the user does not have permission to access; generating, via one or more neural networks trained based at least on non-synthesized data, synthesized data configured to replace at least part of the second portion of the information, the synthesized data being different than the second portion of information, relevant to the request, and not including any information that the user does not have permission to access; and providing an encrypted data set for access by the user, the data set including the first portion of the information and the synthesized data. ### Claim 18 (depends on 17) The method of claim 17, further comprising parsing the request based at least on one or more taxonomies and ontologies. ### Claim 19 (depends on 17) The method of claim 17, wherein providing the data set comprises executing a query execution plan at one or more provisioning bots of the computing system. ### Claim 20 (depends on 17) The method of claim 17, where the access credentials of the user include one or more of an organizational access credential of the user, and a geographic location of the user.