Method, System, and Data Storage Device for Automating Solution Prompts Based Upon Semantic Representation

Abstract

Methods, systems, and computer program products for analyzing one or more perceived or technical problems or proposed solutions, and proposing a result are disclosed. In accordance therewith, a query is received as an input, one or more documents that are most closely semantically related to the query are retrieved, a set of concept terms derived from each of the query and the retrieved semantically related documents is obtained, a list of generic Solution Prompts, each of which generic Solution Prompt thereof includes a placeholder for insertion of a word or phrase from the set of concept terms, is provided, and a morphological analysis is applied to combine the list of generic Solution Prompts with the obtained set of concept terms to create a list of Specific Solution Prompts.

What is claimed is: 
     
         1 . A system implementable on a machine comprising at least one processor adapted to communicate with at least one non-transitory computer readable storage media, the machine capable of communicating via an electronic communications network and adapted to analyze at least one or more of a perceived problem, a technical problem, a proposed solution, and a proposed result;
 the system further adapted to track a plurality of solution prompts presented to the user and adapted to track user interactions with each of the solution prompts, the interactions from at least one or more from a group of review, review time, user clicks, and choice of solution candidates; and   the tracking adapted to build a probabilities relationship network between at least one or more of inventive principles, heuristics, separation techniques, and standard solutions at least one or more of sequentially and parallelly.   
     
     
         2 . The system of  claim 1 , wherein a neural-network based semantic analysis of the problem statement is adapted to be presented as a query adapted to provide a mechanism for combining at least one or more of keywords, concepts, and topic descriptions deemed relevant to the technical problem, the system further adapted to provide recommendations for solution prompts leading to specific solutions with the inventive principles, heuristics, separation techniques, and standard solutions. 
     
     
         3 . The system of  claim 2 , wherein user interaction calculations are adapted to include at least one or more of user review, user review time, user clicks, and choice of solution candidates, and wherein a machine learning system determines the presentation rate and the probability of success for solution prompt types. 
     
     
         4 . The system of  claim 3 , wherein the solution prompts are machine generated using at least one or more of inventive principles, heuristics, separation techniques, and standard solutions, wherein the machine generated solution prompts are adapted to adjust how inventive principles, heuristics, separation techniques, and standard solutions are prioritized as the user proceeds with the solution prompts;
 the system further adapted to use a tracking and learning mechanism which links concepts to at least one or more of other solution prompts, inventive principles, heuristics, separation techniques, and standard solutions with probabilities and interactions among the inventive principles, heuristics, separation techniques, and standard solutions coupled with specific related concepts; and   the machine generated solution prompts adapted to be used by machine learning for machine generating subsequent solution prompts.   
     
     
         5 . The system of  claim 4 , wherein the solution prompts presented to the user are tracked to include at least one or more of review, time spent reviewing, user clicks, and the number of new solution candidates created before the user reviews the next solution prompt. 
     
     
         6 . The system of  claim 5 , wherein the system is adapted for the user to review previously presented solution prompts wherein subsequent reviews are tracked to include at least one or more of review, review time, user clicks, choice of solution candidates, and number of new solution candidates created from which to machine generate further solution prompts using at least one or more of inventive principles, heuristics, separation techniques, and standard solutions underlying the further solution prompts and adjusting from which the respective solution prompts were constructed, and adjusts prioritizing inventive principles, heuristics, separation techniques, and standard solutions as the user proceeds. 
     
     
         7 . The system of  claim 6 , wherein the scores of one or more solution prompts are reduced if the user reviews for less time the class of solution prompt from which the respective solution prompt was constructed when compared to the time the user reviews other classes of solution prompts. 
     
     
         8 . The system of  claim 6 , wherein the scores of one or more solution prompts are adapted to be given a better chance to be presented to the user than initially prioritized. 
     
     
         9 . The system of  claim 4 , wherein multiple users and queries may be tracked to create a probabilities relationship network database that links with probabilities of concepts being relevant for at least one or more of solution prompts, inventive principles, heuristics, separation techniques, and standard solutions. 
     
     
         10 . The system of  claim 9 , wherein the knowledge learned from user interactions is applied to other users wherein one type of one or more concepts can lead to at least one or more other concepts. 
     
     
         11 . A method implementable on a machine including communicating with at least one processor at least one non-transitory computer readable storage media, the machine further communicating by way of an electronic communications network and analyzing at least one or more of a perceived problem, a technical problem, a proposed solution, and a proposed a result;
 tracking a plurality of solution prompts presented to the user and tracking user interactions with each of the solution prompts, the interactions from at least one or more from a group of review, review time, user clicks, and choice of solution candidates; and   the tracking further building a probabilities relationship network between at least one or more of inventive principles, heuristics, separation techniques, and standard solutions at least one or more of sequentially and parallelly.   
     
     
         12 . The method of  claim 11 , including analyzing via a neural-network based semantic analysis of the problem statement and presenting as a query providing a mechanism for combining at least one or more of keywords, concepts, and topic descriptions deemed relevant to the technical problem, further providing recommendations for solution prompts leading to specific solutions with the inventive principles, heuristics, separation techniques, and standard solutions. 
     
     
         13 . The method of  claim 12 , including calculating user interactions including at least one or more of user review, user review time, user clicks, and choice of solution candidates, and determining with a machine learning system the presentation rate and the probability of success for solution prompt types. 
     
     
         14 . The system of  claim 13 , including machine-generating the solution prompts using at least one or more of inventive principles, heuristics, separation techniques, and standard solutions, wherein the machine generated solution prompts adjust how inventive principles, heuristics, separation techniques, and standard solutions are prioritized as the user proceeds with the solution prompts;
 tracking and learning links between concepts to at least one or more of other solution prompts, inventive principles, heuristics, separation techniques, and standard solutions with probabilities and interactions among the inventive principles, heuristics, separation techniques, and standard solutions coupled with specific related concepts; and   applying the machine generated solution prompts to machine learning for machine generating subsequent solution prompts.   
     
     
         15 . The method of  claim 14 , including tracking solution prompts presented to the user to include at least one or more of review, time spent reviewing, user clicks, and the number of new solution candidates created before the user reviews the next solution prompt. 
     
     
         16 . The method of  claim 15 , including reviewing with the system previously presented solution prompts wherein subsequent reviews are tracked including at least one or more of review, review time, user clicks, choice of solution candidates, and further prompting from number of new solution candidates created machine-generating further solution prompts using at least one or more of inventive principles, heuristics, separation techniques, and standard solutions underlying the further solution prompts and adjusting from which the respective solution prompts were constructed, and adjusting prioritizing inventive principles, heuristics, separation techniques, and standard solutions as the user proceeds. 
     
     
         17 . The method of  claim 16 , including reducing the scores of one or more solution prompts if the user reviews for less time the class of solution prompt from which the respective solution prompt was constructed when compared to the time the user reviews other classes of solution prompts. 
     
     
         18 . The method of  claim 16 , including giving the scores of one or more solution prompts a better chance to be presented to the user than initially prioritized. 
     
     
         19 . The method of  claim 14 , including tracking multiple users and queries to create a probabilities relationship network database that links with probabilities of concepts being relevant for at least one or more of solution prompts, inventive principles, heuristics, separation techniques, and standard solutions. 
     
     
         20 . The method of  claim 19 , including applying the knowledge learned from user interactions with other users wherein one type of one or more concepts can lead to at least one or more other concepts.