Methodology to automatically incorporate feedback to enable self learning in neural learning artifactories

Abstract

Approaches, techniques, and mechanisms are disclosed for generating, enhancing, applying and updating knowledge neurons for providing decision making information to a wide variety of client applications. Domain keywords for knowledge domains are generated from domain data of selected domain data sources, along with keyword values for the domain keywords, and are used to generate knowledge artifacts for inclusion in knowledge neurons. These knowledge neurons may be enhanced by domain knowledge data sets found in various data sources and used to generate neural responses to neural queries received from the client applications. Neural feedbacks may be used to update and/or generate knowledge neurons. Any ML algorithm can use, or operate in conjunction with, a neural knowledge artifactory comprising the knowledge neurons to enhance or improve baseline accuracy, for example during a cold start period, for augmented decision making and/or for labeling data points or establishing ground truth to perform supervised learning.

What is claimed is: 
     
         1 . A computer-implemented method comprising:
 receiving, by an artificial intelligence (AI) knowledge data server from an internet-of-things (IOT) device over one or more computer networks, a specific computer message that includes a specific set of IOT device-generated data items;   identifying, based at least in part on the specific set of IOT device-generated data items, one or more knowledge data units from among a plurality of knowledge data units maintained in a knowledge data repository, wherein the plurality of knowledge data units in the knowledge data repository is generated at least partly through machine learning with a machine learning model implemented by a computing device;   using a plurality of sets of IOT device-generated data items including the specific set of IOT device-generated data items to generate a plurality of samples and a corresponding plurality of observed values;   generating a prediction mapping that maps the plurality of samples to the corresponding plurality of observed values;   updating the one or more knowledge data units in the knowledge data repository with one or more specific prediction values predicted by the prediction mapping; and   causing the one or more knowledge data units to be used by an AI knowledge data query processor implemented using one or more computer devices to generate knowledge data responses to knowledge data query requests from client computing devices.   
     
     
         2 . The method of  claim 1 , wherein the plurality of samples and the corresponding plurality of observed values are maintained as historical data at the AI knowledge data server. 
     
     
         3 . The method of  claim 1 , wherein the prediction mapping is used to predict a preferred value for a knowledge data property in the one or more knowledge data units. 
     
     
         4 . The method of  claim 3 , wherein the preferred value for the knowledge data property is generated using one or more machine learning methods that comprise one or more of: regression-based machine learning methods, classification-based machine learning methods, decision-tree-based machine learning methods, or random-forest-based machine learning methods. 
     
     
         5 . The method of  claim 3 , wherein the preferred value for the knowledge data property is generated by minimizing an objective function measuring prediction accuracy. 
     
     
         6 . The method of  claim 1 , wherein the prediction mapping is used to update an existing knowledge data unit in the knowledge data repository. 
     
     
         7 . The method of  claim 1 , wherein the prediction mapping is used to generate a new knowledge data unit to be stored in the knowledge data repository. 
     
     
         8 . A non-transitory computer readable medium that stores computer instructions which, when executed by one or more computing processors, cause the one or more computing processors to perform:
 receiving, by an artificial intelligence (AI) knowledge data server from an internet-of-things (IOT) device over one or more computer networks, a specific computer message that includes a specific set of IOT device-generated data items;   identifying, based at least in part on the specific set of IOT device-generated data items, one or more knowledge data units from among a plurality of knowledge data units maintained in a knowledge data repository, wherein the plurality of knowledge data units in the knowledge data repository is generated at least partly through machine learning with a machine learning model implemented by a computing device;   using a plurality of sets of IOT device-generated data items including the specific set of IOT device-generated data items to generate a plurality of samples and a corresponding plurality of observed values;   generating a prediction mapping that maps the plurality of samples to the corresponding plurality of observed values;   updating the one or more knowledge data units in the knowledge data repository with one or more specific prediction values predicted by the prediction mapping; and   causing the one or more knowledge data units to be used by an AI knowledge data query processor implemented using one or more computer devices to generate knowledge data responses to knowledge data query requests from client computing devices.   
     
     
         9 . The non-transitory computer readable medium of  claim 8 , wherein the plurality of samples and the corresponding plurality of observed values are maintained as historical data at the AI knowledge data server. 
     
     
         10 . The non-transitory computer readable medium of  claim 8 , wherein the prediction mapping is used to predict a preferred value for a knowledge data property in the one or more knowledge data units. 
     
     
         11 . The non-transitory computer readable medium of  claim 10 , wherein the preferred value for the knowledge data property is generated using one or more machine learning methods that comprise one or more of: regression-based machine learning methods, classification-based machine learning methods, decision-tree-based machine learning methods, or random-forest-based machine learning methods. 
     
     
         12 . The non-transitory computer readable medium of  claim 10 , wherein the preferred value for the knowledge data property is generated by minimizing an objective function measuring prediction accuracy. 
     
     
         13 . The non-transitory computer readable medium of  claim 8 , wherein the prediction mapping is used to update an existing knowledge data unit in the knowledge data repository. 
     
     
         14 . The non-transitory computer readable medium of  claim 8 , wherein the prediction mapping is used to generate a new knowledge data unit to be stored in the knowledge data repository. 
     
     
         15 . An apparatus, comprising:
 one or more computing processors;   a non-transitory computer readable medium that stores computer instructions which, when executed by the one or more computing processors, cause the one or more computing processors to perform:
 receiving, by an artificial intelligence (AI) knowledge data server from an internet-of-things (IOT) device over one or more computer networks, a specific computer message that includes a specific set of IOT device-generated data items; 
 identifying, based at least in part on the specific set of IOT device-generated data items, one or more knowledge data units from among a plurality of knowledge data units maintained in a knowledge data repository, wherein the plurality of knowledge data units in the knowledge data repository is generated at least partly through machine learning with a machine learning model implemented by a computing device; 
 using a plurality of sets of IOT device-generated data items including the specific set of IOT device-generated data items to generate a plurality of samples and a corresponding plurality of observed values; 
 generating a prediction mapping that maps the plurality of samples to the corresponding plurality of observed values; 
 updating the one or more knowledge data units in the knowledge data repository with one or more specific prediction values predicted by the prediction mapping; and 
 causing the one or more knowledge data units to be used by an AI knowledge data query processor implemented using one or more computer devices to generate knowledge data responses to knowledge data query requests from client computing devices. 
   
     
     
         16 . The apparatus of  claim 15 , wherein the plurality of samples and the corresponding plurality of observed values are maintained as historical data at the AI knowledge data server. 
     
     
         17 . The apparatus of  claim 15 , wherein the prediction mapping is used to predict a preferred value for a knowledge data property in the one or more knowledge data units. 
     
     
         18 . The apparatus of  claim 17 , wherein the preferred value for the knowledge data property is generated by minimizing an objective function measuring prediction accuracy. 
     
     
         19 . The apparatus of  claim 15 , wherein the prediction mapping is used to update an existing knowledge data unit in the knowledge data repository. 
     
     
         20 . The apparatus of  claim 15 , wherein the prediction mapping is used to generate a new knowledge data unit to be stored in the knowledge data repository.