# US 11,907,775 B2 · Intelligent API content governance framework > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,907,775 B2 - Document ID: US11907775B2 - Status: Granted - Kind: B2 - Application number: 17/648,042 - Filed: 2022-01-14 - Published: 2023-07-20 - Granted: 2024-02-20 - Earliest claimed: 2022-01-14 - Assignees: Dell Products L.P. - Applicants: Dell Products L.P. - Inventors: Bijan Kumar Mohanty; Manoj Nambirajan; Hung Dinh; Mohit Kumar Agarwal - Web page: https://patentgrep.com/patent/US11907775B2 ## CPC - G06F 9/547: {Remote procedure calls [RPC]; Web services} - 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 In one aspect, an example methodology implementing the disclosed techniques includes receiving a new application programming interface (API) specification and extracting one or more keywords from the new API specification. The method also includes identifying, using a trained machine learning (ML) model, one or more existing API specifications that are similar to the new API specification based on the one or more keywords from the new API specification and, responsive to the identification, outputting information regarding the one or more existing API specifications that are similar to the new API specification. ## Claims ### Claim 1 A computer implemented method comprising: receiving a new application programming interface (API) specification, wherein the new API specification corresponds to a new API that is being designed and not yet developed; extracting one or more keywords from the new API specification; identifying, using a trained machine learning (ML) model, one or more existing API specifications that are similar to the new API specification based on the one or more keywords from the new API specification, wherein the trained ML model includes a set of feature vectors corresponding to a plurality of existing API specifications; and responsive to the identification, outputting information regarding the one or more existing API specifications that are similar to the new API specification. ### Claim 2 (depends on 1) The method of claim 1, wherein the new API specification corresponds to a new API that is being designed. ### Claim 3 (depends on 1) The method of claim 1, wherein the outputting includes ordering the one or more existing API specifications according to similarity to the new API specification. ### Claim 4 (depends on 1) The method of claim 1, wherein the one or more extracted keywords are indicative of a context and intent of the new API specification. ### Claim 5 (depends on 1) The method of claim 1, wherein the identifying one or more existing API specifications further comprises: generating a feature vector based on the extracted one or more keywords; and using the feature vector and the trained ML model to predict the one or more existing API specifications that are similar to the new API specification. ### Claim 6 (depends on 5) The method of claim 5, wherein generating the feature vector includes using Term Frequency-Inverse Document Frequency (TF-IDF). ### Claim 7 (depends on 1) The method of claim 1, wherein the identifying one or more existing API specifications is based on cosine similarity. ### Claim 8 (depends on 1) The method of claim 1, wherein the new API specification is received from an API marketplace associated with an organization. ### Claim 9 (depends on 1) The method of claim 1, wherein the new API specification is received from an API design tool associated with an organization. ### Claim 10 (depends on 1) The method of claim 1, wherein the new API specification is received from an API runtime associated with an organization. ### Claim 11 A system comprising: one or more non-transitory machine-readable mediums configured to store instructions; and one or more processors configured to execute the instructions stored on the one or more non-transitory machine-readable mediums, wherein execution of the instructions causes the one or more processors to carry out a process comprising: receiving a new application programming interface (API) specification, wherein the new API specification corresponds to a new API that is being designed and not yet developed; extracting one or more keywords from the new API specification; identifying, using a trained machine learning (ML) model, one or more existing API specifications that are similar to the new API specification based on the one or more keywords from the new API specification, wherein the trained ML model includes a set of feature vectors corresponding to a plurality of existing API specifications; and responsive to the identification, outputting information regarding the one or more existing API specifications that are similar to the new API specification. ### Claim 12 (depends on 11) The system of claim 11, wherein the outputting includes to order the one or more existing API specifications according to similarity to the new API specification. ### Claim 13 (depends on 11) The system of claim 11, wherein the one or more extracted keywords are indicative of a context and intent of the new API specification. ### Claim 14 (depends on 11) The system of claim 11, wherein the identifying one or more existing API specifications further comprises: generating a feature vector based on the extracted one or more keywords; and using the feature vector and the trained ML model to predict the one or more existing API specifications that are similar to the new API specification. ### Claim 15 (depends on 14) The system of claim 14, wherein generating the feature vector includes using Term Frequency-Inverse Document Frequency (TF-IDF). ### Claim 16 (depends on 11) The system of claim 11, wherein the identifying one or more existing API specifications is based on cosine similarity. ### Claim 17 (depends on 11) The system of claim 11, wherein the new API specification is received from one of an API marketplace, an API design tool, or an API runtime associated with an organization. ### Claim 18 A non-transitory computer-readable medium storing program instructions that are executable to: receive, by a computing device, a new application programming interface (API) specification, wherein the new API specification corresponds to a new API that is being designed and not yet developed; extract, by the computing device, one or more keywords from the new API specification; identify, by the computing device using a trained machine learning (ML) model, one or more existing API specifications that are similar to the new API specification based on the one or more keywords from the new API specification, wherein the trained ML model includes a set of feature vectors corresponding to a plurality of existing API specifications; and responsive to the identification, output, by the computing device, information regarding the one or more existing API specifications that are similar to the new API specification.