Distributed processing systems

Abstract

A distributed processing method is disclosed herein for evaluating student work product. The distributed processing system includes a server, a database server, and an application server that are interconnected via a network, and connected via the network to a plurality of independent processing units. The independent processing units can include an analysis engine that is machine learning capable, and thus uniquely completes its processing tasks. The server can provide one or several pieces of data to one or several of the independent processing units, can receive an analysis results from the one or several independent processing units, and can update the result based on a value scoring the machine learning of the independent processing unit.

What is claimed is: 
     
         1 . A distributed processing method for evaluating student work product, the method comprising:
 receiving at at least one server a signal encoding a processing task;   separating a one or several groups of data from the processing task;   sending a first one of one or several groups of data to a first evaluator device and to a second evaluator device;   receiving a first score for the first one of one or several groups of data from the first evaluator device;   receiving a second score for the first one of the one or several groups of data from the second evaluator device;   retrieving an accuracy parameter comprising a first component for standardizing the first score and a second component for standardizing the second score;   calculating a combined score of the first one of the one or several groups of data based on a combination of the first score, the second score, and the accuracy parameter; and   updating the accuracy parameter, wherein updating the accuracy parameter comprises updating the first component of the accuracy parameter and generating an updated accuracy parameter.   
     
     
         2 . The method of  claim 1 , wherein the at least one server is further configured to select a group of evaluators to process the processing task. 
     
     
         3 . The method of  claim 2 , wherein the at least one server comprises a stored management guideline comprising one or several rules for a completion of an analysis of the processing task. 
     
     
         4 . The method of  claim 3 , wherein the stored management guideline specifies a number of reviews for one or more of the one or several groups of data in the processing task. 
     
     
         5 . The method of  claim 1 , wherein at least one of the evaluator devices comprises a cloud computing device. 
     
     
         6 . The method of  claim 1 , wherein the at least one server further performs the actions of:
 incrementing a count when the first one of the one or several groups of data is sent to one of the evaluator devices; and   comparing the count to a threshold value to determine whether to send the first one of the one or several groups of data to an additional one of the plurality of evaluators.   
     
     
         7 . The method of  claim 6 , wherein the at least one server further performs the actions of selecting an additional one of the plurality of evaluators after determining to send the first one of the one or several groups of data to an additional one of the plurality of evaluators. 
     
     
         8 . The method of  claim 7 , wherein the at least one server further performs the actions of receiving an additional electric signal from the additional one of the evaluator devices, and wherein the additional electric signal comprises an additional score generated by the additional one of the evaluator devices of the first one of the one or several groups of data. 
     
     
         9 . The method of  claim 1 , wherein the at least one server further performs the actions of updating the accuracy parameter with respect to the first one of the evaluator devices, wherein the updating compares the combined score of the first one of the one or several groups of data to the first score and the accuracy parameter to generate a result, and incrementing or decrementing the first component of the accuracy parameter based on result. 
     
     
         10 . The method of  claim 1 , wherein updating the accuracy parameter further comprises retrieving an index function, wherein the index function generates an accuracy parameter update value for the first component of the accuracy parameter according to a difference between the first score and the combined score. 
     
     
         11 . The method of  claim 10 , wherein the first component of the accuracy parameter is incremented or decremented by the accuracy parameter update value. 
     
     
         12 . The method of  claim 1 , wherein the at least one server further performs the actions of:
 selecting one or several of the evaluator devices for scoring of a potential bounding piece, wherein one of the several of the evaluators are selected based on an accuracy parameter retrieved by the at least one server, wherein the accuracy parameter identifies a degree to which one or several of the evaluators have accurately scored a one or several previous data groups; and   calculating a score of the one of the one or several groups of data of the processing task based on the potential bounding piece and the accuracy parameter.   
     
     
         13 . The method of  claim 12 , wherein the potential bounding piece comprises one of the one or several groups of data and an associated score. 
     
     
         14 . The method of  claim 13 , wherein the at least one server further performs the actions of retrieving the potential bounding piece from memory. 
     
     
         15 . The method of  claim 13 , wherein the at least one server further performs the actions of controlling a generation of the potential bounding piece. 
     
     
         16 . The method of  claim 15 , wherein the at least one server further performs the actions of selecting a selected one or several of the evaluators for scoring of a potential bounding piece, wherein the one or several of the evaluators are selected based on an accuracy parameter retrieved by the at least one server, wherein the accuracy parameter identifies the degree to which one or several of the evaluators have accurately scored one or several previous data groups. 
     
     
         17 . The method of  claim 16 , wherein the at least one server further performs the actions of:
 identifying one of the one or several groups of data as the potential bounding piece;   generating a bounded signal, wherein the bounded signal encodes the potential bounding piece;   sending the bounded signal to the selected one or several of the evaluator devices;   receiving a response signal from the selected one or several of the evaluator devices, wherein the response signal comprises a bounded score of the potential bounding piece generated by the selected one or several of the evaluator devices; and   storing an indicator identifying the potential bounding piece as a bounding piece and storing the bounded score of the potential bounding piece.   
     
     
         18 . The method of  claim 12 , wherein the potential bounding piece comprises a plurality of bounding pieces, wherein some of the plurality of bounding pieces comprise different bounded scores. 
     
     
         19 . The method of  claim 12 , wherein at least one of the evaluator devices comprises a mobile computing device. 
     
     
         20 . The method of  claim 12 , wherein the potential bounding piece comprises a plurality of bounding pieces, wherein all of the plurality of bounding pieces comprise different bounded scores.