# US 2020/0401660 A1 · Semantic space scanning for differential topic extraction > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2020/0401660 A1 - Document ID: US20200401660A1 - Status: Published application - Kind: A1 - Application number: 16/444,638 - Filed: 2019-06-18 - Published: 2020-12-24 - Earliest claimed: 2019-06-18 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Alexander James WILSON; Romain REY - Web page: https://patentgrep.com/patent/US20200401660A1 ## CPC - G06F 16/35: Clustering; Classification - G06F 40/30: Semantic analysis - G06F 40/216: using statistical methods - G06F 40/284: Lexical analysis, e.g. tokenisation or collocates - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) ## Abstract A system for extracting differential topics from a dataset including a user interface, a memory for storing executable program code, and one or more electronic processors coupled to the memory and the user interface. The electronics processors are configured to receive a dataset from one or more servers, wherein the dataset comprises user feedback data associated with a software program. The electronic processors are also configured to extract text from the dataset, convert the extracted text to vector data, and determine anomalous data clusters associated with the vector data using statistical analysis. The electronic processors are also configured to differentiate overlapping anomalous data clusters using a classification algorithm, wherein the differentiated overlapping anomalous data clusters are associated with specific topics, and export each specific topic associated with the differentiated overlapping data cluster. ## Claims ### Claim 1 A system for extracting differential topics from a dataset, the system comprising: a user interface; a memory for storing executable program code; and one or more electronic processors coupled to the memory and the user interface, the electronic processors configured to: receive a dataset from one or more servers, wherein the dataset comprises user feedback data associated with a software program; extract text from the dataset; convert extracted text to vector data; determine anomalous data clusters associated with the vector data using statistical analysis; differentiate overlapping anomalous data clusters using a classification algorithm, wherein the differentiated overlapping anomalous data clusters are associated with specific topics; and export each specific topic associated with the differentiated overlapping data clusters. ### Claim 2 (depends on 1) The system of claim 1, wherein the servers receive data from users via a plurality of user devices. ### Claim 3 (depends on 2) The system of claim 2, wherein the user devices are voice assistant devices. ### Claim 4 (depends on 1) The system of claim 1, wherein the statistical analysis is a Bayesian scan statistical analysis. ### Claim 5 (depends on 1) The system of claim 1, wherein the statistical analysis is a Bayesian Gamma-Poisson statistical analysis. ### Claim 6 (depends on 1) The system of claim 1, wherein the classification algorithm is a forest classification algorithm. ### Claim 7 (depends on 1) The system of claim 1, wherein the electronic processors are configured to assign metadata to the extracted text. ### Claim 8 (depends on 7) The system of claim 7, wherein the assigned metadata comprises the original position of one or more extracted text elements within the dataset. ### Claim 9 (depends on 1) The system of claim 1, wherein the electronic processors are configured to map the vector data in high-dimensional space. ### Claim 10 (depends on 1) The system of claim 1, wherein the vector data is extracted using a distributional semantics modeling. ### Claim 11 A method for extracting differential topics from a dataset, the method comprising: receiving, at a computing device, a dataset from one or more servers, wherein the dataset comprises user feedback data associated with a software program; extracting, via the computing device, text from the dataset; converting, via the computing device, the extracted text to vector data within a high-dimensional vector space; determining, via the computing device, anomalous data clusters associated with the vector data using statistical analysis; differentiating, via the computing device, overlapping anomalous data clusters using a classification algorithm, wherein the differentiated overlapping anomalous data clusters are associated with specific topics within the user feedback data; and exporting, via the computing device, each specific topic associated with the differentiated overlapping data clusters. ### Claim 12 (depends on 11) The method of claim 11, wherein the servers receive data from users via a plurality of user devices. ### Claim 13 (depends on 12) The method of claim 12, wherein the user devices are voice assistant devices. ### Claim 14 (depends on 11) The method of claim 11, wherein the statistical analysis is a Bayesian scan statistical analysis. ### Claim 15 (depends on 12) The method of claim 12, wherein the statistical analysis is a Bayesian Gamma-Poisson statistical analysis. ### Claim 16 (depends on 11) The method of claim 11, wherein the classification algorithm is a forest classification algorithm. ### Claim 17 (depends on 11) The method of claim 11, wherein the extracted text is converted to vector data by the electronic processing executing one or more distributional semantic modeling algorithms. ### Claim 18 A system for extracting geographically differential topics from a dataset, the system comprising: a user interface; a memory for storing executable program code; and one or more electronic processors coupled to the memory and the user interface, the one or more electronic processors configured to: receive a dataset from one or more servers, wherein the dataset comprises user feedback data associated with a software program; execute a differential topic extraction algorithm to isolate relevant text within the dataset; extract text from the dataset; convert extracted text to vector data by executing a distributional semantics modeling algorithm; map the vector data in a high-dimensional space; determine anomalous data clusters associated with the vector data using a Bayesian scan statistics statistical analysis; differentiate overlapping anomalous data clusters using a classification algorithm, wherein the differentiated overlapping anomalous data clusters are associated with specific topics; and export each specific topic associated with the differentiated overlapping data clusters. ### Claim 19 (depends on 18) The system of claim 18, wherein the classification algorithm is a forest classification algorithm. ### Claim 20 (depends on 18) The system of claim 18, wherein the Bayesian scan statistics statistical analysis is a Bayesian Gamma-Poisson statistical analysis.