Understanding Advanced Patent Classification Systems

Intelligent resource management system that uses AI to optimize procurement of machine resources like compute, storage, and network capacity. The system interprets resource requirements and uses machine learning to predict future needs and make forward purchases in resource markets. It aggregates data from internal and external sources to configure purchases and timing. The system acquires resources at the best value based on cost parameters.

More accurate patent searching and analysis using AI, specifically natural language understanding (NLU) and machine learning (ML) techniques, to improve search results and avoid missing relevant patents. The method involves analyzing patent claims and relevant text from a reference document using AI systems to determine the meaning of claim elements and search for matches to rank patents based on how well their claims match the reference document.

A method to objectively assess patents using AI. The method involves obtaining information about the target patent and the corporation that owns it, generating input signals from the obtained data, feeding these signals into pre-trained neural networks to classify the patent and corporate, comparing the network outputs to stored comparison values to assess the patent and corporate, and providing the assessment results.

A platform for conducting patent searches and analyzing patent value using a combination of AI, machine learning, and blockchain technology. The platform leverages natural language processing to improve patent search relevance by analyzing similarities between claim limitations and prior art specifications. It also uses AI algorithms to rank prior art based on relevance to specific claim elements. The platform further provides tools for highlighting, weighting, and customizing search parameters.

Automated method of evaluating an attribute of patent contents using an artificial neural network to evaluate patents. The evaluation factors are selected based on the technology class of the patent. The attribute evaluation feature value is calculated using input scores and predetermined connection weights. The weights are limited based on class to avoid vanishing gradients. This allows differentiated automated patent evaluation for different technical fields.

Automatically classifying patents via machine learning to save time and resources. The method involves learning from a patent database to establish a basic classification model. When a user searches for patents, it uses their classification input to predict their personalized classification standard. This combines with the basic model to classify the remaining unclassified patents. It leverages transfer learning to customize the basic model using the user's classification pattern.

Automatically generating patent applications with improved patentability using AI and prior art. It takes invention text, determines its patent classification, finds similar patents, extracts details not in the original text, and adds those to the invention description. This expands the invention scope and increases patentability.

Patent evaluation method that leverages natural language processing and complex network algorithms to objectively evaluate the depth and breadth of patented technologies and predict the expected life of patents. The method involves collecting patent documents, generating technical points, clustering patents into global industries, and comparing patents with technologies in the global industry to evaluate their value.

A system for mapping, ranking, and visualizing patents and patent portfolios to analyze patent value, coverage, and related concepts. It uses data structures and analytics to organize patents by concepts like scope, technology category, and ranking. This allows interactive charts to be generated showing relationships between patent claims, concepts, rankings, and metadata like filing date and owner. The system also enables features like automated prior art citation management within portfolios.

A patent analysis system that calculates scores to determine the quality and value of patents in a way that is both automated and consistent across a large patent portfolio. The system calculates scores for individual claim elements and overall patents and then compares those scores against peer patents to provide rankings.

Optimizing patent literature searches by taking a user's search formula and expanding it to a higher-quality search by adding relevant search terms and operators. The system receives a user's search formula, classifies it into groups based on operators, adds additional relevant search terms to each group, combines the groups with operators to create a final optimized search formula, and provides that to the user. This expands and improves the user's initial search.

Patent evaluation system that determines patentability of an invention idea. The system uses an automated process to compare an invention sentence with existing patent sentences using an edit distance measure. The comparison looks for similar sentences in a patent sentence database. The determination of patentability is based on multiplying the reciprocal of the edit distance with the length index of the invention sentence and a content rate of the keyword.

Leveraging structural equation modeling to evaluate the quality and value of patents. The method involves generating an evaluation model using statistical analysis to determine the factors and weights that impact patent quality. The model is built by surveying experts to rate the importance of various factors. It then uses structural equation modeling to analyze the relationships between these factors and build an evaluation model. This model can be used to evaluate patents by inputting their data.

System for performing patentability searches and analysis using machine learning and pre-filing analysis to improve patent quality and success rates for inventors. The system allows users to submit concept descriptions, claim terms, or draft patent applications for analysis. It conducts searches of patent and non-patent literature databases, identifies relevant prior art, and provides results to the user. The system also identifies the likely patent examiner and art unit for the application and considers frequently cited references.

Protecting the copyright of a 3D object model by distorting the original model through voxel rotation obfuscation. The method involves generating an original 3D object model, calculating voxel sizes, generating a unique key, and using that key to determine voxel rotation parameters. The voxels in the rotation range are rotated to distort the model. Only authorized users with the decryption key can access and use the model.

An apparatus and method for forecasting patent disputes. It extracts keywords from the claims and background of two patent documents and calculates similarity between them using those keywords. The claim and background similarities are combined to give a cooperative similarity score, which represents the probability that the documents are infringing on each other.