Self-learning connected-device network

Abstract

A connected-device network can continually learn from abstract sensory data (e.g., speech processing, cognitive inference, and/or computer vision image segmentation) and can generate never-seen-before data in real time. In one aspect, the network devices extract important correlations in the sensor data based on network data collected at different time slice and/or locations. Further, underlying relationships in a set of data can be detected as the sensor data transverses through different layers of the network. Moreover, the network devices can provide logic in different layers to help classify the sensor data early in the detection process (e.g., instead of waiting for it to reach its final destination).

What is claimed is: 
     
         1 . A method, comprising:
 receiving, by object node equipment comprising a processor:
 sensor data captured via sensor equipment that communicates sensor data via a mobility network, and 
 metadata about the sensor equipment that has been identified to be of threshold likely interest to a customer, according to a defined likelihood criterion; 
   based on the metadata, classifying, by the object node equipment, the sensor data, resulting in classified sensor data; and   based on the classified sensor data, validating, by the object node equipment, the classified sensor data.   
     
     
         2 . The method of  claim 1 , wherein a function of the object node equipment was instantiated as a virtualized network function in a service slice enabled via the mobility network for validation of the sensor data, and wherein the virtualized network function was selected for validation based on the metadata. 
     
     
         3 . The method of  claim 2 , wherein the virtualized network function comprises a layer used to classify the sensor data received in the service slice, and wherein subsequent virtualized network functions instantiated after the virtualized network function are able to be instantiated in successive service slices, other than the service slice, enabled via the mobility network. 
     
     
         4 . The method of  claim 1 , wherein the metadata comprises:
 first metadata representative of a sensor data collection capability of the sensor equipment, and   second metadata representative of a position of the sensor equipment.   
     
     
         5 . The method of  claim 1 , wherein, in response to determining that the object node equipment has not classified the classified sensor data in accordance with a defined success criterion, the sensor data was reclassified based on a determined label for the sensor data. 
     
     
         6 . The method of  claim 5 , wherein a second object node was instantiated to reclassify the sensor data based on the determined label for the data. 
     
     
         7 . The method of  claim 1 , further comprising, employing, by the object node equipment, feedback data to update the object node equipment. 
     
     
         8 . The method of  claim 1 , wherein the sensor equipment comprises Internet of things equipment. 
     
     
         9 . A system, comprising:
 a processor; and   a memory that stores executable instructions that, when executed by the processor, facilitate performance of operations, comprising:
 receiving sensor data captured via a sensor device that is part of a mobility network and metadata about the sensor device that was identified to be of threshold likely interest to a customer, according to a defined likelihood criterion, 
 based on the metadata, classifying the sensor data, resulting in classified sensor data, and 
 based on the classified sensor data, validating the classified sensor data. 
   
     
     
         10 . The system of  claim 9 , wherein the metadata about the sensor device comprises a location of the sensor device. 
     
     
         11 . The system of  claim 9 , wherein the system was instantiated in a service slice enabled via the mobility network for validation of the sensor data, and wherein the system was selected for validation based on the metadata. 
     
     
         12 . The system of  claim 9 , wherein the metadata comprises:
 first metadata representative of a sensor data collection capability of the sensor device, and   second metadata representative of a position of the sensor device.   
     
     
         13 . The system of  claim 9 , wherein the operations further comprise:
 receiving an indication that the sensor data was not classified in accordance with a defined success criterion, and   reclassifying the sensor data based on a determined label for the sensor data.   
     
     
         14 . The system of  claim 9 , wherein the operations further comprise, based on feedback data provided for the classified sensor data, updating the system. 
     
     
         15 . The system of  claim 9 , wherein the sensor device comprises an Internet of things device. 
     
     
         16 . A non-transitory machine-readable medium, comprising executable instructions that, when executed by a processor of network equipment, facilitate performance of operations, comprising:
 receiving sensor data captured via an Internet of things device connected via a network and metadata about the Internet of things device;   based on the metadata, classifying the sensor data, resulting in classified sensor data;   receiving an indication that the classified sensor data was not classified in accordance with a defined success criterion,   reclassifying the sensor data based on a determined label for the sensor data, resulting in reclassified sensor data; and   based on the reclassified sensor data, validating the reclassified sensor data.   
     
     
         17 . The non-transitory machine-readable medium of  claim 16 , wherein the network comprises a mobility network. 
     
     
         18 . The non-transitory machine-readable medium of  claim 16 , wherein validating the sensor data comprises instantiating a virtualized network function in a service slice enabled via the network for validation of the sensor data, and wherein the virtualized network function was selected for validation based on the metadata. 
     
     
         19 . The non-transitory machine-readable medium of  claim 16 , wherein the metadata comprises:
 first metadata representative of a sensor data collection capability of the Internet of things device, and   second metadata representative of a position of the Internet of things device.   
     
     
         20 . The non-transitory machine-readable medium of  claim 16 , wherein the operations further comprise employing feedback data to update the reclassified sensor data.