IP Innovation Trends & Future Directions

Predicting industrial development trends in a target area using publicly available data like enterprise addresses, policy support, and disclosures. The method involves identifying high-quality enterprises in the area based on published data, classifying them by industry, and analyzing their size and intellectual property to predict industry trends. This leverages artificial intelligence techniques like support vector machines and gradient boosting trees to analyze publicly available data and identify advantageous industrial chains and trends in the target area.

Source

Analyzing technical line changes in a field based on patent data to understand technology development trends, predict future directions, and help companies make informed innovation strategies. The method involves processing patents to extract key entities, relationships, and time points. It then analyzes time series trends, builds roadmaps, assesses future technology, fuses data, predicts trends, and generates comprehensive reports.

Source

A method and system for predicting disruptive patents using intelligent models. The method involves identifying potentially disruptive technology themes from patent data using machine learning algorithms, scoring the themes using a disruptive technology measurement model, and selecting the top 10% with highest scores for further analysis. It combines SVM-LDA, indicator system construction, and cosine similarity algorithms to improve accuracy in identifying disruptive technologies in complex, uncertain environments.

Source

A patent value evaluation method that combines traditional methods and machine learning to provide more accurate and reliable evaluation results for patents. It captures patent information and potential citation relationships through network data retrieval, determines stage-based weights, uses association rule mining, self-learning, and feedback to classify and value patents based on correlation matrices. This provides more comprehensive, dynamic, and real-time patent value evaluation.

Source

Method for analyzing patents to provide recommendations for optimizing technical protection strategies. The method involves preprocessing the patent data using NLP techniques, extracting text features using deep learning, and then generating reports on technical adaptability, potential infringement, and optimized protection strategies. It leverages techniques like statistical analysis, neural networks, and optimization algorithms to comprehensively understand patent technology, market adaptability, and infringement risks.

Source

Using deep learning and natural language processing (NLP) to predict the economic value of patents. The method involves leveraging unstructured patent text in addition to structured patent features to develop more accurate and scalable patent valuation models. It uses deep learning architectures like bidirectional long short-term memory (LSTM) networks to process the patent text and extract insights. The text features are combined with structured patent data like claims, citations, and classifications to train the models. The resulting deep learning models outperform traditional regression-based methods for patent valuation.

Source

A method and device for predicting promising technologies using an autoregressive integrated moving average (ARIMA) model. The ARIMA model is used to identify time series patterns and predict future technology trends. The method involves identifying an appropriate ARIMA model for the time series of technology data, normalizing the data if needed, and using the identified model to make predictions.

Source

Method for analyzing the industrial feasibility of patents using patent data to determine if a patent has practical application potential. The method involves analyzing patents based on industry terms, citations, transfers, and values to train a model that can predict the feasibility of new patents. It determines average metrics like citations and transfers for patents in different stages (inception, development, application) to train a model. This model is then used to analyze new patents and provide feasibility scores based on the metrics.

Source

Method for analyzing the subject content and popularity evolution of patented technologies by leveraging the International Patent Classification (IPC) system. The method involves using a topic modeling technique called Partial Latent Dirichlet Allocation (pLDA) to extract technical topics from patent documents. The pLDA model is modified to take into account the IPC classification level and abstract text of the patent. By setting the IPC level for topic mining, it allows fine-grained analysis of technical topics at different levels. In subject evolution analysis, word clouds are used to show the subject content under IPC classifications over time. The topic intensity and trend are calculated to determine the hotness trend of topics under IPC classifications.

Source

Method for analyzing technology trends using patent data and classification systems to identify detailed technologies and their convergence, and objectively quantify technology development trends. The method involves extracting patent classification systems, configuring a matrix, clustering to form detailed technology groups, identifying technologies within each cluster, and applying time series analysis to track development trends.

Source

Patent valuation method using data mining and heterogeneous knowledge association to accurately measure patent value. The method involves representing patents and external entities in a heterogeneous knowledge network where patents are connected to external entities like market trends. Machine learning is then used to analyze the network to determine patent value based on the interconnectivity between patent and external entity features.

Source

Predicting future innovation at the company level based on big data and predictive analysis using machine learning techniques that explore the usefulness of company financial data, newspaper articles, social media data, and patent indicators.

Source

Extracting promising technologies through big data analysis using LSTM recurrent neural networks. The method involves cyclically analyzing past patent data with LSTM to predict future promising technologies. LSTM improves prediction accuracy by adding cell state values to the hidden state of recurrent neural networks.

Source

Analyzing enterprise technology using patent big data to provide targeted competitor analysis reports. The method involves collecting patent data for each enterprise, analyzing it to extract label data, then customizing analysis based on target enterprise instructions. Data dimensions like invention trends, patent types, and legal status are analyzed to provide insights into technological development, innovation, talent, competition, cooperation, and technology transfer.

Source

A method for screening high-value patents using big data and AI to efficiently identify patents with potential for converting into valuable innovations. The method involves steps like setting up a patent database, cleaning and transforming the data, training AI models, and evaluating patents based on factors like patent family size, cited patents, litigation, claims, inventors, and innovation teams. This allows rapid screening of large numbers of patents to identify those with potential for significant innovation impact.

Source

A machine learning-based patent evaluation method that provides detailed and quantitative patent value assessment using multiple categories subdivided based on split points. The method involves extracting quantitative information like bibliographic data and transfer fees from patents, embedding the textual data to convert it into numerical form, training patent classification models with the preprocessed data and split points, and using these models to evaluate the value of a target patent based on its embedded text and quantitative data. The models divide the patents into categories based on split points derived from sorting the training data by transfer fees.

Source

A patent big data analysis method and system for optimizing enterprise technology using patent databases to identify technology trends and hotspots. The method involves screening technology words based on frequency and applicant importance, calculating growth rates, and ranking to optimize enterprise technology choices. The system extracts features like word combinations, part of speech, length, symbols, and co-occurrence with technical terms.

Source

Automatic method for predicting technology trends without manual analysis of large datasets. The method involves identifying industry and technology information from intellectual property content, determining the technologies under each industry, and constructing the technology iteration path for each industry. This path shows how technologies evolve over time. By analyzing the iteration paths, the current technology in a target industry is used to predict the emerging technology after it. This automated approach improves efficiency compared to manually searching for trends. It can also predict attributes like maturity and emergence of new technologies.

Source

Method, device, equipment and storage medium for predicting technology trends based on patent information. The method involves converting patent subject data into a time series set, calculating trend-related features from the set, analyzing the features to determine technical development trend intensity, and using it to predict future patent subject trends.

Source

Deep learning method to evaluate potential value of patents. The method involves preprocessing patent documents, embedding the words to convert them into dense vectors, applying topic modeling to extract latent topics, and calculating topic weights and word probabilities. These values are combined with technology trend and prospect data to estimate patent potential.

Source

Extracting patent technology evolution context by analyzing patent texts using semantics and graph theory to understand the evolution and development process of patented technologies. The method involves converting patent claims into semantic associations between words, constructing a global association network between words across time and space, calculating weights for words based on network strength, and extracting patent technology evolution context by analyzing the weighted associations between words.

Source

Using AI to recommend high-risk patents for technology transfer and matching them with optimal recipients. The method involves applying machine learning to patent data to predict patent risk, then identifying patents owned by universities or research institutions with high risk. These patents are recommended for transfer to companies with high relevance and need. The AI also generates technical strategy content to support the transfer. The goal is to increase commercialization success by matching high-risk patents with optimal users.

Source

Semi-automated determination of patent valuation using machine learning and dynamic representations. The method involves generating a database containing layers of information like megatrends, indicators, ontology, codes, devices, etc. from various sources. This dynamic representation of patents is used as input for a machine learning model to predict patent valuation. The model optimizes using historical and present structured/unstructured data and expert knowledge.

Source

Estimating rates of improvement for any technology domain using a method that decomposes patents into technological domains. The method involves selecting and comparing US and international patent classifications for each patent to find overlaps. If an overlap contains enough patents, it's considered a technology domain. Rates of improvement are calculated for each domain. This allows searching for and obtaining improvement rates of specific technologies by inputting keywords. The method provides accessible systems for finding and estimating improvement rates of technologies.

Source

Method to predict future technological knowledge flows between fields using patent data and graph neural networks. The method involves extracting growth, diffusion, and absorption metrics for each tech field over time. These metrics are then passed through modules to generate vectors representing the tech field's diffusion and absorption capacity. These vectors are input into a tech flow tracking module to predict future capacity vectors. By matching the capacity vectors, probabilities of knowledge flow between tech fields are determined. This leverages patent citation networks and hierarchical classification to accurately predict future tech knowledge flows.

Source

Diagnosing and predicting the science and technology capabilities of countries and companies using patent and research paper data. The method involves collecting patent and paper data for a technology, calculating variables from the data for each country or company, generating diagnosis models using machine learning, and using the models to diagnose and predict technology strengths and weaknesses.

Source

Artificial intelligence-based system and method for assisting product development that provides a comprehensive approach for evaluating and guiding product development based on factors like technical feasibility, market demand, intellectual property protection, and cultural relevance. The system uses AI techniques like natural language processing, trend analysis, patent search, and TRIZ theory to analyze product ideas and provide insights and recommendations for improvement. It leverages databases of trends, patents, and cultural factors to assess product potential and identify areas for optimization. The AI system can also suggest new product ideas based on emerging trends and technologies.

Source

A method and device to predict novelty and inventiveness of patent texts using natural language processing techniques like topic modeling and BERT. The method involves processing the patent text and authorized patents using topic models and BERT to extract features like keyword topic distributions and semantic representations. These features are concatenated and fed through a fully connected layer with an activation function to calculate a probability of novelty/inventiveness for the patent text.

Source

Predicting future innovation at the enterprise level using machine learning techniques and big data analysis. The method involves collecting patent, R&D, and financial data for companies over a period. This data is classified into feature sets and used to train machine learning models like logistic regression, naive Bayes, neural networks, support vector machines, and deep belief networks to predict future innovation. The goal is to find predictors among financial, news, and patent data that can accurately forecast a company's innovative success.

Source

Using machine learning techniques like naive Bayes, neural networks, and support vector machines to predict future innovation at the enterprise level based on analyzing a company's financial data, news articles, social media, and patents. The method involves collecting data like patent counts, assignees, inventors, citations, and structural relationships, as well as financial metrics, for a set of companies over time. This data is then classified into feature sets and fed into machine learning models to predict future innovation.

Source

Analyzing intellectual property data using a method that visually displays the relevance and connection of patented technologies over time. The method involves calculating similarities between technologies using cosine similarity based on their patent data. This creates a matrix diagram showing the relationships between all technologies applied for by an organization over a specified time period. It allows understanding of the organization's technological development and patent layout as a whole, and identifying hotspots and gaps in specific fields.

Source

Artificial intelligence-based patent valuation system that estimates the sales of patented products using deep learning to more accurately evaluate patent values. The system uses financial, size, and sales growth rate data for industries and companies to train a deep learning model. It then calculates rising and falling periods for products based on the model. This allows estimating sales for patented products more accurately than using static growth rates. The sales estimates are used to calculate patent values. The system also provides a patent valuation interface for devices to input patent details and receive valuations.

Source

A method to build an intellectual property data analysis system that allows efficient processing and analysis of unstructured intellectual property data. The method involves extracting keywords from both unstructured and structured intellectual property data to create a general-purpose intellectual property data system for patent keyword analysis. It converts unstructured data into structured format through pre-processing and analysis steps. This enables semantic interoperability between textual IP sources and allows building a knowledge base system for retrospective and forward-looking research of IP data, technical field analysis, and competitor analysis.

Source

Method and apparatus for analyzing technological paradigms in a specific domain by quantifying the influence of patents on each other through citation relationships. It calculates a persistence value for each patent that indicates how long its knowledge lasts. Patents with high persistence are technological breakthroughs. By identifying patents with persistence above a threshold, it finds past and future paradigms.

Source

Enterprise intellectual property management system that leverages big data and machine learning algorithms to optimize patent strategies. The system uses big data capture, screening, and identification techniques to analyze patent trends and potential value. It then applies SVM optimization algorithms to predict rational patent layouts for companies based on their fields of interest. This helps enterprises make more informed patent decisions by leveraging data analysis and machine learning instead of relying solely on experience or declarations. The system also uses blockchain for secure data transmission.

Source

Method for analyzing and processing patent data to understand the dynamics of companies' technological activities. The method involves collecting patent data, quantitative analysis of the data to extract 9 metrics, and qualitative analysis of the data to identify technological trends, company trends, and specific right status. The quantitative metrics include number of patents, citations, families, and international applications, as well as scientific relevance, technology life cycle, and patent implementation rate. The qualitative analysis involves manual review of important patents to understand the technology, strategy, and competitive landscape. Combining quantitative and qualitative analysis provides a comprehensive view of patent data.

Source

A patent analysis system that collects, analyzes, and applies patent data. The system allows users to search, index, and analyze patents to gain insights into technology trends, competitor strategies, and potential infringement risks. It provides features like keyword searching, indexing classification, chart visualization, and report generation. The system allows users to save and reuse search results, as well as apply the analyzed patents to tasks like innovation and infringement analysis.

Source

Blockchain-based system for analyzing and managing intellectual property data to help companies leverage IP information for research and development. The system allows enterprises to register, search patents, and analyze metrics like authorization probability, rates, and growth. It uses blockchain nodes for patent storage and analysis modules like business field selection, similarity, and direction analysis. The system aims to provide companies with IP insights to encourage innovation and competition.

Source

Predicting the success rate of patent application authorization using a method, system, and electronic device that combines natural language processing and graph convolutional neural networks. The method involves: (1) building a heterogeneous network of patent applications, applicants, companies, and related patents; (2) filtering patent text to extract abstracts and claims; (3) training separate models for document vectors and graph node features; (4) fusing the vectors and network data to predict authorization success.

Source

A machine learning system for predicting technology transfer based on patent data. The system collects patent data, processes numerical data, and applies text processing techniques like topic modeling to extract technical topics from unstructured text. It ensembles the numerical and topic data to generate a technology transfer prediction model. This system can accurately predict technology transfer rates compared to other models.

Source

An intellectual property big data information service platform that collects, analyzes, and provides access to large volumes of intellectual property data to enable better decision making, innovation, and risk management. The platform has modules for data collection, big data analysis, and retrieval applications. It aims to leverage the exploding growth of intellectual property applications and associated data to provide insights, optimization, and services for intellectual property management, search, and analysis. The platform converts raw IP data into valuable information with high reference value for business decision making.

Source

A patent analysis system and method to set research and development directions using patent analysis algorithms. The system involves collecting raw patent data, preprocessing to remove noise, building a database, classifying standard patents, analyzing to identify key patents (core patents), and setting R&D directions based on core patent insights.

Source

Training a machine learning-based patent search system to improve accuracy of technical searches, like novelty evaluations, by leveraging recursive nesting of blocks like claims and specifications in patent documents. The system converts natural language blocks into graphs where nodes are extracted words with relationships like meronymy. The graphs are trained using pairs of blocks from the same patent document. This allows the system to better compare concepts across documents by capturing their internal recursive structure.

Source

A research and development assistance system using patent data to suggest new ideas and overcome patent obstacles. The system analyzes patent documents using text mining to extract technical elements. Association rules are generated from these elements to identify combinations and strengths. Weak rule combinations are presented as R&D suggestions. Strong rule combinations are used to infer patent invalidations.

Source

Accurately predicting the technology focus of high-tech companies in the future by analyzing patent data. The method involves modeling the competitive relationship between companies, the collaborative relationship between technologies, and the dynamic interaction between companies and technologies to estimate the probability of a company developing a particular technology. It uses techniques like recurrent neural networks and paired training to improve accuracy compared to prior methods.

Source

Discovering follow-up development opportunities for a company based on similar companies' technologies. The method involves calculating a preference for patent classes using patent frequency, finding similar companies based on preference similarity, and recommending classes with high correlation for the original company. It analyzes characteristics like heterogeneity, competition, and growth potential to guide R&D.

Source

A method to analyze and manage patent databases using specific keywords, application years, provinces, and offices to identify technology research and development directions, companies, and patent concentrations. The method involves retrieving patent documents based on keywords, counting applications by province and year, identifying technology areas through keywords, mapping companies to locations, and quantifying patent concentrations by province and technology. This provides automated analysis of patent databases to determine technology focus, company locations, and patent densities by region and field.

Source

Using machine learning to automatically analyze public information and track statuses related to it, in order to predict patentability of new ideas. The system scrapes patent publications and other public info to generate a patentability model using vectorized text and image data. It applies this model to vectorized versions of new idea disclosures to predict patentability. This allows companies to evaluate new ideas with a quantitative metric of patentability based on analysis of public data.

Source

Method for forecasting the potential impact and commercial value of a patent using prior indicators that confirm the invention and technical features of the patent. The method involves calculating variables based on technical classification elements and applying deep learning to predict future citation counts. It also involves using variables like number of claims, inventors, and back citations to predict if the patent is standard tech or transfers. By leveraging prior patent data, this method provides more accurate and insightful patent impact forecasts compared to just analyzing citation histories.

Source

Intelligent processing of intellectual property information to proactively understand technology development and patent layout. The method involves using semantic vector analysis to recommend classification numbers for new inventions based on similarity to existing patent classifications. It involves building a classification number index with semantic vectors, generating patent and solution vectors, and calculating similarity to find recommended classifications for new inventions. This provides guidance for patent applications and technology direction.

Source