# US 2019/0377983 A1 · System and Method for Determining and Suggesting Contextually-Related Slide(s) in Slide Suggestions > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2019/0377983 A1 - Document ID: US20190377983A1 - Status: Published application - Kind: A1 - Application number: 16/005,342 - Filed: 2018-06-11 - Published: 2019-12-12 - Earliest claimed: 2018-06-11 - Assignees: Microsoft Technology Licensing, LLC - Applicants: Microsoft Technology Licensing, LLC - Inventors: Shyam Sunder VIJAY - Web page: https://patentgrep.com/patent/US20190377983A1 ## CPC - G06F 16/51: Indexing; Data structures therefor; Storage structures - G06F 16/583: using metadata automatically derived from the content - G06F 18/217: {Validation; Performance evaluation; Active pattern learning techniques} - G06F 40/289: Phrasal analysis, e.g. finite state techniques or chunking - G06F 40/30: Semantic analysis - 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 determining contextually-related slide(s). Content and/or semantic structure of a slide is analyzed to determine information regarding the slide. In some embodiments, the slide is analyzed for keyword(s), topic(s), and/or concept(s). A machine learning algorithm is used to identify other slide(s) that are related to the slide in accordance with the determined information. Link(s) to the identified other slide(s) are provided within the slide. ## Claims ### Claim 1 A system for determining a contextually-related slide, comprising: a computer comprising a processor and a memory having computer-executable instructions stored thereupon which, when executed by the processor, cause the computer to: analyze at least one of content or semantic structure of a slide to determine information regarding the slide; use a machine learning algorithm to identify one or more other slides that are related to the slide in accordance with the determined information; and provide a link to the identified one or more other slides within the slide. ### Claim 2 (depends on 1) The system of claim 1, wherein the machine learning algorithm calculates probabilities, for each of the other slides, that a particular slide is related to the slide based upon the determined information regarding the slide, and, one or more other slides with calculated probabilities greater than a threshold probability are identified as related to the slide. ### Claim 3 (depends on 1) The system of claim 1, wherein the machine learning algorithm applies a model trained in at least one of a supervised, unsupervised, or semi-supervised manner. ### Claim 4 (depends on 3) The system of claim 3, wherein the model is adaptively updated based upon user feedback. ### Claim 5 (depends on 1) The system of claim 1, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide is performed in response to an inferred trigger event. ### Claim 6 (depends on 1) The system of claim 1, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide is performed in response to a user-initiated trigger event. ### Claim 7 (depends on 1) The system of claim 1, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide comprises analyzing the slide for at least one of a keyword, a topic, or a concept. ### Claim 8 (depends on 1) The system of claim 1, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide comprises performing at least one of voice recognition, image recognition or facial recognition. ### Claim 9 (depends on 1) The system of claim 1, wherein the identified one or more other slides are stored in a same presentation as the slide. ### Claim 10 (depends on 1) The system of claim 1, wherein the identified one or more other slides are stored in a different presentation as the slide, and copies of the identified one or more other slides are added to the presentation comprising the slide. ### Claim 11 (depends on 1) The system of claim 1, wherein the machine learning algorithm comprises 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, an artificial neural network (ANN), or a Gradient Boost & Adaboost algorithm. ### Claim 12 A method of determining a contextually-related slide, comprising: analyzing at least one of content or semantic structure of a slide to determine information regarding the slide; using a machine learning algorithm to identify one or more other slides that are related to the slide in accordance with the determined information; and providing a link to the identified one or more other slides within the slide. ### Claim 13 (depends on 12) The method of claim 12, wherein the machine learning algorithm calculates probabilities, for each of the other slides, that a particular slide is related to the slide based upon the determined information regarding the slide, and, one or more other slides with calculated probabilities greater than a threshold probability are identified as related to the slide. ### Claim 14 (depends on 12) The method of claim 12, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide is performed in response to an inferred trigger event. ### Claim 15 (depends on 12) The method of claim 12, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide comprises analyzing the slide for at least one of a keyword, a topic, or a concept. ### Claim 16 A computer storage media storing computer-readable instructions that when executed cause a computing device to: analyze at least one of content or semantic structure of a slide to determine information regarding the slide; use a machine learning algorithm to identify one or more other slides that are related to the slide in accordance with the determined information; and provide a link to the identified one or more other slides within the slide. ### Claim 17 (depends on 16) The computer storage media claim 16, wherein the machine learning algorithm calculates probabilities, for each of the other slides, that a particular slide is related to the slide based upon the determined information regarding the slide, and, one or more other slides with calculated probabilities greater than a threshold probability are identified as related to the slide. ### Claim 18 (depends on 16) The computer storage media of claim 16, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide is performed in response to a user-initiated trigger event. ### Claim 19 (depends on 16) The computer storage media of claim 16, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide comprises analyzing the slide for at least one of a keyword, a topic, or a concept. ### Claim 20 (depends on 16) The computer storage media of claim 16, wherein analyzing at least one of content or semantic structure of a slide to determine information regarding the slide comprises performing at least one of image recognition or facial recognition.