Machine learning-based patent quality metric
A machine-learning based artificial intelligence device for finding an estimate of patent quality, such as patent lifetime or term is disclosed. Such a device may receive a first set of patent data and generate a list of binary classifiers. A candidate set of binary classifiers may be selected and using a heuristic search, for example an artificial neural network (ANN), a genetic algorithm, a final set of binary classifiers is found by maximizing iteratively a yield according to a cost function, such an area under a curve (AUC) of a receiver operating characteristic (ROC). The device may then receive patent information for a target patent and report an estimate of patent quality according to the final set of binary classifiers.
1. A machine-learning based artificial intelligence device used is estimating patent quality, the device comprising:
a patent data retriever configured to receive a first set of patent data, the first set of patent data comprising at least one of patent application data and patent data for a plurality of patent applications and patents, wherein the first set of patent data includes, for each patent application and patent of the plurality of patent applications and patents:
references cited information associated with references cited in a respective patent application or patent;
cited by information associated with references that cite the respective patent application or patent; and
classification information associated with one or more patent classifications corresponding to each respective patent or patent application;
a classifier configured to generate, using an automated processor applying a machine learning algorithm, a set of features based on the first set of patent data, and
a user information manager configured to receive target patent information associated with a target patent and to provide the estimate of patent quality associated with the target patent according to the set of features.
2. The machine-learning based artificial intelligence device of claim 1 , further comprising:
a quantitative data scalar configured to normalize data included in the first set of patent data, wherein the normalized data is used by the classifier to generate the set of features.
3. The machine-learning based artificial intelligence device of claim 2 , wherein the quantitative data assigns weights to data items included in the first set of patent data and the weights data items are used by the classifier to generate the set of features.
4. The machine-learning based artificial intelligence device of claim 1 , wherein the first set of patent data includes raw data extracted from the patent application data and the patent data and derived data derived based on the raw data.
5. The machine-learning based artificial intelligence device of claim 1 , wherein the derived data includes group data associated with a first group of patents of the plurality of patents based on the raw data associated with each of the patents in the first group of patents.
6. The machine-learning based artificial intelligence device of claim 5 , wherein the first group of patents includes all patents in the plurality of patents.
7. The machine-learning based artificial intelligence device of claim 5 , wherein the first group of patents includes less than all patents in the plurality of patents.
8. A system comprising the device of claim 1 and a second device communicatively connected to the machine-learning based artificial intelligence device over a network, the second device comprising:
a second automated processor:
a user interface receiving the target patent information for the target patent;
an estimate requester requesting from the machine-learning based artificial intelligence device, the estimate of patent quality for the target patent; and
a user interface providing, to a user, information indicating the estimate of patent quality.