# US 12,117,975 B2 · Linking, deploying, and executing distributed analytics with distributed datasets > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,117,975 B2 - Document ID: US12117975B2 - Status: Granted - Kind: B2 - Application number: 17/469,104 - Filed: 2021-09-08 - Published: 2021-12-30 - Granted: 2024-10-15 - Earliest claimed: 2015-12-28 - Assignees: International Business Machines Corporation - Applicants: International Business Machines Corporation - Inventors: Theodoros Salonidis; Bong Jun Ko; Swati Rallapalli; Rahul Urgaonkar; Dinesh C. Verma - Web page: https://patentgrep.com/patent/US12117975B2 ## CPC - G06F 16/211: {Schema design and management} - G06F 16/23: Updating - G06F 16/951: Indexing; Web crawling techniques - G06F 16/9538: Presentation of query results - G06F 16/955: using information identifiers, e.g. uniform resource locators [URL] - G06Q 10/063: Operations research, analysis or management - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06Q: INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR ## Abstract Methods and systems for execution of distributed analytics include building a global linked structure that describes correspondences between dataset metadata structures, analytics metadata structures, and location metadata structures and that encodes compatibility between respective datasets, analytics, and locations. A set of analytics and compatible datasets for execution is determined based on the dataset metadata structures, analytics metadata structures, and global linked structure. An optimal execution location is determined based on the determined set of analytics and compatible datasets, the location metadata structures, and the global linked structure. The set of analytics and compatible datasets are deployed to the optimal location for execution. ## Claims ### Claim 1 A computer-implemented method for execution of distributed analytics, comprising: building a global linked structure that includes correspondences between, and links together, dataset metadata structures that characterize one or more datasets, analytics metadata structures that characterize one or more analytics, and location metadata structures that characterize a plurality of physical computing locations of a distributed computing network and include information defining resources of the plurality of physical computing locations, the global linked structure encoding compatibility between respective datasets, analytics, and locations, including a condition that matches types of data, analytics, and resource constraints of physical location; determining a set of analytics and a set of compatible datasets compatible with the set of analytics based on the dataset metadata structures, analytics metadata structures, and global linked structure; determining an optimal execution location from a plurality of physical computing locations in a distributed computing network for execution of the set of analytics on the set of compatible datasets based on costs that are determined based on the location metadata structures, and the global linked structure; and deploying the sets of analytics and compatible datasets to the optimal execution location. ### Claim 2 (depends on 1) The method of claim 1, further comprising creating the dataset metadata structures that characterize one or more datasets or creating the analytics metadata structures that characterize one or more analytics, wherein the dataset metadata structures or the analytics metadata structures each respectively comprises structured and unstructured components. ### Claim 3 (depends on 2) The method of claim 2, wherein creating the dataset metadata structures is performed responsive to publication of the one or more datasets or submission of a user's query. ### Claim 4 (depends on 2) The method of claim 2, wherein creating the analytics metadata structures is performed responsive to publication of the one or more analytics or submission of user's query. ### Claim 5 (depends on 1) The method of claim 1, wherein the dataset metadata structures comprise known types of analytics that may be applied to a respective dataset. ### Claim 6 (depends on 1) The method of claim 1, further comprising executing the deployed set of analytics on the set of compatible datasets at the optimal execution location to perform a data processing task with an optimal performance. ### Claim 7 (depends on 1) The method of claim 1, wherein the global linked structure links datasets, analytics, and physical computing locations through link portions of their respective dataset metadata structures, analytics metadata structures, and location metadata structures. ### Claim 8 (depends on 1) The method of claim 1, wherein the analytics metadata structures comprise known types of dataset that may be used by a respective analytic. ### Claim 9 (depends on 1) The method of claim 1, further comprising creating the location metadata structures that characterize one or more execution locations. ### Claim 10 (depends on 1) The method of claim 1, wherein the location metadata structures comprise information defining available physical and computing resources at the plurality of locations and a set of links to analytics and datasets. ### Claim 11 A computer readable storage medium comprising a computer readable program for data analytics deployment, wherein the computer readable program when executed on a computer causes the computer to perform the steps of: building a global linked structure that includes correspondences between, and links together, dataset metadata structures that characterize one or more datasets, analytics metadata structures that characterize one or more analytics, and location metadata structures that characterize a plurality of physical computing locations of a distributed computing network and include information defining resources of the plurality of physical computing locations, the global linked structure encoding compatibility between respective datasets, analytics, and locations, including a condition that matches types of data, analytics, and resource constraints of physical location; determining a set of analytics and compatible datasets compatible with the set of analytics based on the dataset metadata structures, analytics metadata structures, and global linked structure; determining an optimal execution location from a plurality of physical computing locations in a distributed computing network for execution of the set of analytics on the set of compatible datasets based on costs that are determined based on the location metadata structures, and the global linked structure; and deploying the sets of analytics and compatible datasets to the optimal execution location. ### Claim 12 A system for data analytics deployment, comprising: a distributed computing network including a plurality of physical computing locations; and at least one processor device operatively coupled to a memory and configured; to build a global linked structure that includes correspondences between and links dataset metadata structures that characterize one or more datasets, analytics metadata structures that characterize one or more analytics, and location metadata structures that characterize the plurality of physical computing locations and including information defining resources of the plurality of physical computing locations, the global linked structure encoding compatibility between respective datasets, analytics, and locations, including a condition that matches types of data, analytics, and resource constraints of physical location, to determine a set of analytics and a set of compatible datasets compatible with the set of analytics based on the dataset metadata structures, analytics metadata structures, and global linked structure; to determine an optimal execution location from the plurality of physical computing locations for execution of the set of analytics on the set of compatible datasets based on costs that are determined based on the location metadata structures, and the global linked structure; and to deploy the sets of analytics and compatible datasets to the optimal execution location. ### Claim 13 (depends on 12) The system of claim 12, wherein the at least one processor device is further configured to create the dataset metadata structures that characterize one or more datasets and comprise structured and unstructured components. ### Claim 14 (depends on 13) The system of claim 13, wherein the at least one processor device is further configured to create said dataset metadata structures responsive to publication of the one or more datasets or submission of a user's query. ### Claim 15 (depends on 12) The system of claim 12, wherein the dataset metadata structures comprise known types of analytics that may be applied to a respective dataset. ### Claim 16 (depends on 12) The system of claim 12, wherein the at least one processor device is further configured to create the analytics metadata structures that characterize one or more analytics and comprise structured and unstructured components. ### Claim 17 (depends on 16) The system of claim 16, wherein the at least one processor device is further configured to create said analytics metadata structures responsive to publication of the one or more analytics or submission of a user's query. ### Claim 18 (depends on 12) The system of claim 12, wherein the at least one processor device is further configured to create the location metadata structures that characterize one or more execution locations. ### Claim 19 (depends on 12) The system of claim 12, wherein the location metadata structures comprise information defining available physical and computing resources at the plurality of computing locations and a set of links to analytics and datasets. ### Claim 20 (depends on 1) The method of claim 1, wherein deploying includes packaging analytics and datasets along with their metadata structures using a container.