# US 2019/0318011 A1 · Identification, Extraction and Transformation of Contextually Relevant Content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0318011 A1 - Document ID: US20190318011A1 - Status: Published application - Kind: A1 - Application number: 15/953,924 - Filed: 2018-04-16 - Published: 2019-10-17 - Earliest claimed: 2018-04-16 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Adrian Francisco TERAN GUAJARDO; Hung Minh DANG - Web page: https://patentgrep.com/patent/US20190318011A1 ## CPC - G06F 16/116: {Details of conversion of file system types or formats} - G06F 16/906: Clustering; Classification - G06F 16/908: using metadata automatically derived from the content - G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks - 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 Described herein is a system and method for transforming contextually relevant items. A search query is received, and, for each of a plurality of electronically stored items (e.g., stored in a source platform), a probability that the stored item is relevant to the search query is calculated using a classification model. Stored items having a calculated probability greater than or equal to a threshold probability are identified. Contextually relevant portions of the identified stored items is determined using a contextual model. The determined contextually relevant portions of the identified stored items are extracted. The extracted contextually relevant portions of the identified stored items are transformed into a target platform. An output of the extracted contextually relevant portions of the identified stored items in the target platform is provided. ## Claims ### Claim 1 A system for transforming contextually relevant items, comprising: a processing system comprising a processor and memory having computer-executable instructions stored thereupon which, when executed by the processor, cause the processing system to: receive a search query; calculate a probability, for each of a plurality of electronically stored items, that the stored item is relevant to the search query using a classification model, the plurality of electronically stored items stored in a source platform; identify stored items having a calculated probability greater than or equal to a threshold probability; determine contextually relevant portions of the identified stored items using a contextual model; extract the determined contextually relevant portions of the identified stored items; transform the extracted contextually relevant portions of the identified stored items into a target platform; and provide an output of the extracted contextually relevant portions of the identified stored items in the target platform. ### Claim 2 (depends on 1) The system of claim 1, wherein the stored items comprise at least one of a binary file, a database file, a text-based file, an image file, or an audio file. ### Claim 3 (depends on 1) The system of claim 1, wherein the source platform is a feature of the classification model. ### Claim 4 (depends on 1) The system of claim 1, wherein the target platform is a feature of the classification model. ### Claim 5 (depends on 1) The system of claim 1, wherein the classification model is trained using at least one of a linear regression algorithm, a logistic regression algorithm, a decision tree algorithm, a support vector machine (SVM) algorithm, a Naive Bayes algorithm, a K-nearest neighbors (KNN) algorithm, a K-means algorithm, a random forest algorithm, a dimensionality reduction algorithm, or a Gradient Boost & Adaboost algorithm. ### Claim 6 (depends on 1) The system of claim 1, wherein the source platform is a feature of the contextual model. ### Claim 7 (depends on 1) The system of claim 1, wherein the target platform is a feature of the contextual model. ### Claim 8 (depends on 1) The system of claim 1, wherein the contextual model is trained using at least one of a linear regression algorithm, a logistic regression algorithm, a decision tree algorithm, a support vector machine (SVM) algorithm, a Naive Bayes algorithm, a K-nearest neighbors (KNN) algorithm, a K-means algorithm, a random forest algorithm, a dimensionality reduction algorithm, or a Gradient Boost & Adaboost algorithm. ### Claim 9 (depends on 1) The system of claim 1, the memory having further computer-executable instructions stored thereupon which, when executed by the processor, cause the processing system to: receive feedback information from a user; and adapt at least one of the classification model, the contextual model, or a transformation component that transforms the extracted contextually relevant portions based upon the received feedback information. ### Claim 10 A method of identifying, extracting and transforming contextually relevant portions of electronically stored items, comprising: receiving a search query; calculating a probability, for each of a plurality of electronically stored items, that the stored item is relevant to the search query using a classification model, the plurality of electronically stored items stored in a source platform; identifying stored items having a calculated probability greater than or equal to a threshold probability; determining contextually relevant portions of the identified stored items using a contextual model; extracting the determined contextually relevant portions of the identified stored items; transforming the extracted contextually relevant portions of the identified stored items into a target platform; and providing an output of the extracted contextually relevant portions of the identified stored items in the target platform. ### Claim 11 (depends on 10) The method of claim 10, wherein the stored items comprise at least one of a text-based file, an image file, or an audio file. ### Claim 12 (depends on 10) The method of claim 10, wherein the source platform is a feature of at least one of the classification model or the contextual model. ### Claim 13 (depends on 10) The method of claim 10, wherein at least one of the classification model or the contextual model is trained using at least one of a linear regression algorithm, a logistic regression algorithm, a decision tree algorithm, a support vector machine (SVM) algorithm, a Naive Bayes algorithm, a K-nearest neighbors (KNN) algorithm, a K-means algorithm, a random forest algorithm, a dimensionality reduction algorithm, or a Gradient Boost & Adaboost algorithm. ### Claim 14 (depends on 10) The method of claim 10, further comprising: receiving feedback information from a user; and adapting at least one of the classification model, the contextual model, or a transformation component that transforms the extracted contextually relevant portions based upon the received feedback information. ### Claim 15 A computer storage media storing computer-readable instructions that when executed cause a computing device to: receive a search query; calculate a probability, for each of a plurality of electronically stored items, that the stored item is relevant to the search query using a classification model, the plurality of electronically stored items stored in a source platform; identify stored items having a calculated probability greater than or equal to a threshold probability; determine contextually relevant portions of the identified stored items using a contextual model; extract the determined contextually relevant portions of the identified stored items; transform the extracted contextually relevant portions of the identified stored items into a target platform; and provide an output of the extracted contextually relevant portions of the identified stored items in the target platform. ### Claim 16 (depends on 15) The computer storage media of claim 15, wherein the stored items comprise at least one of a binary file, a database file, a text-based file, an image file, or an audio file. ### Claim 17 (depends on 15) The computer storage media of claim 15, wherein the source platform is a feature of at least one of the classification model or the contextual model. ### Claim 18 (depends on 15) The computer storage media of claim 15, wherein at least one of the classification model or the contextual model is trained using at least one of a linear regression algorithm, a logistic regression algorithm, a decision tree algorithm, a support vector machine (SVM) algorithm, a Naive Bayes algorithm, a K-nearest neighbors (KNN) algorithm, a K-means algorithm, a random forest algorithm, a dimensionality reduction algorithm, or a Gradient Boost & Adaboost algorithm. ### Claim 19 (depends on 15) The computer storage media of claim 15, storing further computer-readable instructions that when executed cause a computing device to: receive feedback information from a user; and adapt at least one of the classification model, the contextual model, or a transformation component that transforms the extracted contextually relevant portions based upon the received feedback information. ### Claim 20 (depends on 15) The computer storage media of claim 15, wherein one of the features when training the classification model is at least one of an organizational hierarchy or group membership.