Machine learning and inference system

Abstract

A machine learning and inference system operable to reason about content information and to infer a set of patterns and a set of relationships between patterns of the set of patterns. The machine learning and inference system access content information from a plurality of data sources, such as public and private data sources, the public and private data sources include structured and unstructured data. The machine learning and inference system is operable to reason about the content information and to compile a set of augmented content based at least in part on one or more of the content information, the set of patterns and the set of relationships, and its reasoning about the content information. The machine learning and inference system learns over time and enables nested or hierarchical content augmentation and can be customized for specific industries and content such as financial, medical, health, business, manufacturing and social media information content.

I claim: 
     
         1 . A machine learning and inference system for use within an information processing system, the machine learning and inference system comprising:
 a computing platform; and   an application specific augmentation system operable (i) to access content information from a public data source and a private data source, the public data source including at least one of structured and unstructured publicly available content, the private data source including at least one of structured and unstructured private content, and (ii) to provide the content information to the computing platform, the computing platform is operable to infer a set of patterns and a set of relationships between patterns of the set of patterns based at least in part on the content information, wherein the application specific augmentation system is further operable to discover knowledge by reasoning about the content information using the set of patterns and the set of relationships.   
     
     
         2 . The machine learning and inference system of  claim 1 , wherein the application specific augmentation system is further operable to compile one or more sets of relevant augmented content based on the content information, the set of patterns, the set of relationships. 
     
     
         3 . The machine learning and inference system of  claim 2 , wherein the application specific augmentation system is further operable to automatically refine at least one set of the one or more sets of relevant augmented content based on one or more of the content information, structured publicly available content, unstructured publicly available content, unstructured private content, structured private content, and the knowledge discovered by the application specific augmentation system reasoning about the content information. 
     
     
         4 . The machine learning and inference system of  claim 2 , wherein the application specific augmentation system further comprising:
 a relevant augmented content management subsystem operable to manage and to provide the one or more sets of relevant augmented content via a queue.   
     
     
         5 . The machine learning and inference system of  claim 4 , wherein, in response to at least one of a real-time input, a feedback from a user, an automatically generated feedback, an interaction with at least a portion of the set of relevant augmented content, an interaction with the content information, a real-time feedback from a user, and an input from a user, the relevant augmented content management subsystem is further operable to provide a request for updating the one or more sets of relevant augmented content to the application specific augmentation system. 
     
     
         6 . The machine learning and inference system of  claim 5 , wherein, in response to the request for updating the one or more sets of relevant augmented content, the computing platform is operable (i) to infer an updated set of patterns by (a) inferring additional patterns to be added to the set of patterns, (b) cleaning up patterns from the set of patterns, or (c) refining one or more patterns in the set of patterns, and (ii) to infer an updated set of relationships between patterns of the updated set of patterns by (a) inferring new relationships to be added to the set of relationships, (b) cleaning up relationships from the set of relationships, or (c) refining one or more relationships in the set of relationships, and wherein the application specific augmentation system is operable (i) to update the one or more sets of relevant augmented content based at least in part on the updated set of patterns and the updated set of relationships, or (ii) to generate a new set of relevant augmented content based at least in part on the updated set of patterns and the updated set of relationships. 
     
     
         7 . The machine learning and inference system of  claim 2 , wherein the application specific augmentation system is further operable to dynamically update the one or more sets of relevant augmented content in response to at least one of a real-time input, a feedback from a user, an automatically generated feedback, an interaction with at least a portion of the set of relevant augmented content, an interaction with the content information, a real-time feedback from a user, an input from a user, a real-time feedback mechanism, a real-time interaction with the content information, and a real-time interaction with the one or more sets of relevant augmented content. 
     
     
         8 . The machine learning and inference system of  claim 1 , wherein the application specific augmentation system is further operable to build a knowledge graph based at least in part on the knowledge discovered, the set of patterns and the set of relationships. 
     
     
         9 . The machine learning and inference system of  claim 8 , wherein a user is able to interact with the content information or the one or more sets of relevant augmented content by traversing the knowledge graph. 
     
     
         10 . The machine learning and inference system of  claim 1 , wherein the application specific augmentation system is further operable to perform a nested or hierarchical knowledge discovery, and wherein, during a first invocation of the application specific augmentation system, the application specific augmentation system is operable to compile a first set of relevant augmented content based on the content information, the set of patterns, the set of relationships. 
     
     
         11 . The machine learning and inference system of  claim 10 , wherein, during a second invocation of the application specific augmentation system, the application specific augmentation system is operable to provide at least a portion of the first set of relevant augmented content as a new content information to the computing platform, and to compile a second set of relevant augmented content based at least in part on the new content information. 
     
     
         12 . The machine learning and inference system of  claim 11 , wherein the computing platform is operable to infer a new set of patterns, and a new set of relationships between patterns of the new set of patterns based at least in part on the new content information, and wherein the application specific augmentation system is operable to compile the second set of relevant augmented content based at least in part on one or more of the new content information, the content information, the set of patterns, the set of relationships, the new set of patterns, and the new set of relationships. 
     
     
         13 . The machine learning and inference system of  claim 12 , wherein the application specific augmentation system is further operable to share one or more of the first set of relevant augmented content, the second set of relevant augmented content, the set of patterns, the set of relationships, the new set of patterns, and the new set of relationships between a first process and one or more other processes. 
     
     
         14 . The machine learning and inference system of  claim 2 , wherein the application specific augmentation system is further operable to enrich the one or more sets of relevant augmented content over time, and wherein the computing platform is further operable (i) to learn from the one or more sets of relevant augmented content, the set of patterns, and the set of relationships, (ii) to save the one or more sets of relevant augmented content, the set of patterns, and the set of relationships, and (iii) to refine over time the one or more sets of relevant augmented content, the set of patterns, and the set of relationships. 
     
     
         15 . A machine learning and inference system for use within an information processing system, the machine learning and inference system comprising:
 an application specific augmentation system comprising a computing platform and a relevant augmented content subsystem, the application specific augmentation system operable (i) to access a specific content information from a public data source and a private data source, the public data source including at least one of structured and unstructured publicly available content, the private data source including at least one of structured and unstructured private content, and (ii) to provide the specific content information to the computing platform, the computing platform operable to infer a set of patterns and a set of relationships between patterns of the set of patterns based on the specific content information, the relevant augmented content subsystem operable to compile a first set of relevant augmented content based on the specific content information, the set of patterns, and the set of relationships, wherein the specific content information is selected from any one of the group consisting of financial content information, medical content information, health content information, business content information, manufacturing content information, and social media content information.   
     
     
         16 . The machine learning and inference system of  claim 15 , wherein the application specific augmentation system is further operable to enrich the first set of relevant augmented content over time. 
     
     
         17 . The machine learning and inference system of  claim 16 , wherein the computing platform is further operable (i) to learn from one or more of the first set of relevant augmented content, the first set of patterns, and the first set of relationships, (ii) to save one or more of the first set of relevant augmented content, the first set of patterns, and the first set of relationships, and (iii) to refine over time one or more of the first set of relevant augmented content, the first set of patterns, and the first set of relationships. 
     
     
         18 . The machine learning and inference system of  claim 17 , wherein the application specific augmentation system is further operable to reason about the specific content information using the set of patterns and the set of relationships, and to build a knowledge graph based on the set of patterns and the set of relationships, wherein a user is able to interact with the specific content information or the first set of relevant augmented content by traversing the knowledge graph. 
     
     
         19 . A machine learning and inference system for use within an information processing system, the machine learning and inference system comprising:
 a computing platform, wherein the machine learning and inference system is operable (i) to access content information from a public data source and a private data source, the public data source including at least one of structured and unstructured publicly available content, the private data source including at least one of structured and unstructured private content, and (ii) to provide the content information to the computing platform, the computing platform is operable to infer a set of patterns and a set of relationships between patterns of the set of patterns based on the content information, and wherein the machine learning and inference system is further operable to reason about the content information using the set of patterns and the set of relationships; and   a relevant augmented content subsystem operable to compile a set of relevant augmented content based at least in part on the content information, the set of patterns, and the set of relationships.   
     
     
         20 . The machine learning and inference system of  claim 19 , wherein the computing platform is further operable (i) to learn from one or more of the set of relevant augmented content, the set of patterns, and the set of relationships, (ii) to save one or more of the set of relevant augmented content, the set of patterns, and the set of relationships, and (iii) to refine over time one or more of the set of relevant augmented content, the set of patterns, and the set of relationships.