Methods and systems for valuing patents with multiple valuation models

A system for valuing patents comprising:

• at least one processor that
• receives information associated with a particular industry from at least one data source, wherein the information corresponds to an analysis related to intellectual property of the particular industry;
• executes machine learning logic to utilize a neural network to recognize successful model combinations of a plurality of cognitive patent valuation models using the information as input, wherein utilizing the neural network includes analyzing each of the plurality of cognitive patent valuation models under a cognitive analysis of the neural network to determine and apply weighting parameters of each of the plurality of cognitive patent valuation models according to a predefined input goal, and wherein an output of the neural network is a ranked list of the plurality of cognitive patent valuation models according to the predefined input goal;
• analyzes a plurality of patents with a first patent valuation model and at least a second patent valuation model of the plurality of cognitive patent valuation models selected from a library of computer models containing the plurality of cognitive patent valuation models, wherein the first patent valuation model has a first number of the parameters respectively weighted at a first weight and the at least a second patent valuation model has a second number of the parameters respectively weighted at a second weight, the second number different than the first number and the second weight different than the first weight;
• detects a selection of a filter of the results of said analysis of the plurality of patents with the first patent valuation model and the at least a second patent valuation model;
• generates a list of at least some of the plurality of patents based on said analysis of the plurality of patents with the first patent valuation model and the at least a second patent valuation model and the selected filter of the results of said analysis of the plurality of patents with the first patent valuation model and the at least a second patent valuation model;
• and
• uses feedback data associated with the list of at least some of the plurality of patents to automatically and iteratively update the neural network over time to improve an accuracy of the neural network in recognizing the successful model combinations of the plurality of cognitive patent valuation models.

A computer program product for valuing patents by one or more processors, the computer program product comprising a non-transitory computer-readable storage medium having computer-readable program code portions stored therein, the computer-readable program code portions comprising:

• an executable portion that receives information associated with a particular industry from at least one data source, wherein the information corresponds to an analysis related to intellectual property of the particular industry;
• an executable portion that executes machine learning logic to utilize a neural network to recognize successful model combinations of a plurality of cognitive patent valuation models using the information as input, wherein utilizing the neural network includes analyzing each of the plurality of cognitive patent valuation models under a cognitive analysis of the neural network to determine and apply weighting parameters of each of the plurality of cognitive patent valuation models according to a predefined input goal, and wherein an output of the neural network is a ranked list of the plurality of cognitive patent valuation models according to the predefined input goal;
• an executable portion that analyzes a plurality of patents with a first patent valuation model and at least a second patent valuation model of the plurality of cognitive patent valuation models selected from a library of computer models containing the plurality of cognitive patent valuation models, wherein the first patent valuation model has a first number of the parameters respectively weighted at a first weight and the at least a second patent valuation model has a second number of the parameters respectively weighted at a second weight, the second number different than the first number and the second weight different than the first weight;
• an executable portion that detects a selection of a filter of the results of said analysis of the plurality of patents with the first patent valuation model and the at least a second patent valuation model;
• an executable portion that generates a list of at least some of the plurality of patents based on said analysis of the plurality of patents with the first patent valuation model and the at least a second patent valuation model and the selected filter of the results of said analysis of the plurality of patents with the first patent valuation model and the at least a second patent valuation model;
• and
• an executable portion that uses feedback data associated with the list of at least some of the plurality of patents to automatically and iteratively update the neural network over time to improve an accuracy of the neural network in recognizing the successful model combinations of the plurality of cognitive patent valuation models.