# AI System for Analyzing Mixed Financial Information > This patent describes an AI system that combines different types of financial data, like stock prices, news articles, and market sentiment, to make better predictions and create new financial scenarios. - **Patent:** US 12327190 - **Original title:** Multimodal financial technology deep learning core with joint optimization of vector-quantized variational autoencoder and neural upsampler - **Owner:** Atombeam Technologies - **Granted:** 2025 - **Status:** Active - **Times cited:** 14 - **Field:** finance, ai_ml, software, telecommunications ## What it does This system processes various kinds of financial information, such as stock prices (time-series data), news articles (textual data), market mood (sentiment data), and company reports (structured tabular data) (Claim 2). It uses specialized AI tools, called 'modality-specific codeword generators' (Claim 1), to convert each data type into a unique digital code. These codes are then blended together by a fusion module to understand their relationships (Claim 1). A 'VQ-VAE encoder' (Claim 1) compresses this combined information into a smaller, discrete code, which is then rebuilt by a 'VQ-VAE decoder' (Claim 1). A 'neural upsampler' (Claim 1) then enhances the reconstructed data, adding back details that might have been lost during compression. All these parts are 'jointly trained' (Claim 1) simultaneously using a 'joint loss function' (Claim 1) to ensure they work together perfectly. For example, a financial firm could use this to predict stock movements by combining historical prices, company news, and social media sentiment, and then generate new, realistic crisis scenarios to test investment strategies. ## What it does NOT cover - Does not cover systems that process only one type of financial data, as it specifically requires 'multimodal data' (Claim 1). - Does not cover systems that do not use a 'Vector-quantized Variational Autoencoder (VQ-VAE)' for data compression (Claim 1). - Does not cover systems that lack a 'neural upsampler' specifically designed to recover information lost during compression (Claim 1). - Does not cover AI models where the VQ-VAE and neural upsampler are trained separately, as it requires 'jointly train[ing]' them with a combined loss function (Claim 1). - Does not cover general multimodal AI systems that are not specifically applied to 'financial data' (Claim 2). - Does not cover systems that do not encode each data modality into a 'codeword-based representation' (Claim 1). ## The clever bit The truly clever part is the 'joint training' (Claim 1) of the VQ-VAE and the neural upsampler, which not only compresses and reconstructs diverse financial data but also actively recovers lost information and allows for exploring the 'latent space' (Claim 13) to generate new, realistic financial scenarios. This enables a deeper understanding and proactive testing of financial models. ## Real-world examples 1. AI-driven financial trading platforms 2. Advanced risk management software for banks 3. Economic modeling tools for market analysis 4. Synthetic data generation for financial stress testing 5. Algorithmic investment strategy development ## Why it matters This technology matters because it allows financial institutions to process and understand complex, diverse data more effectively than traditional methods. By combining different data types and enhancing their quality, it can lead to more accurate financial forecasting, better risk assessment, and smarter decision-making. The ability to generate new, synthetic financial scenarios also provides a powerful tool for robust model testing and developing new strategies without relying solely on historical data. ## Frequently asked questions ### What does AI System for Analyzing Mixed Financial Information cover? This patent describes an AI system that combines different types of financial data, like stock prices, news articles, and market sentiment, to make better predictions and create new financial scenarios. ### Who owns patent US 12327190? Atombeam Technologies owns this patent, granted in 2025. ### When does this patent expire? This patent is expected to expire on September 17, 2044, when the invention enters the public domain. ### What is patent US 12327190 cited by? This patent has been cited by 14 later patents that build on its ideas. ### What problem does this patent solve? This technology matters because it allows financial institutions to process and understand complex, diverse data more effectively than traditional methods. By combining different data types and enhancing their quality, it can lead to more accurate financial forecasting, better risk assessment, and smarter decision-making. The ability to generate new, synthetic financial scenarios also provides a powerful tool for robust model testing and developing new strategies without relying solely on historical data. ### What does this patent NOT cover? Does not cover systems that process only one type of financial data, as it specifically requires 'multimodal data' (Claim 1). **Full plain-English explainer:** https://patentbrief.org/patent/us/12327190/multimodal-financial-technology-deep-learning-core-with-joint-optimization-of-ve **Original patent:** https://patents.google.com/patent/US12327190 --- _Source: PatentBrief — https://patentbrief.org. Patent facts are from public records; the plain-English explanation is PatentBrief's._ ## Related patents Semantically similar inventions in the PatentBrief corpus: - [How AI Analyzes Financial Data Across Different Timeframes](https://patentbrief.org/patent/us/20250307927/multi-scale-temporal-attention-processing-system-for-multimodal-deep-learning-wi) — This patent describes an AI system that processes various types of financial data, like stock prices and news, by looking at it simultaneously through quarterly, weekly, and daily lenses, and then combining these views, especially adapting to market changes. - [How an AI System Answers Financial Questions Using Specialized Bots](https://patentbrief.org/patent/us/12307349/systems-and-methods-of-large-language-model-driven-orchestration-of-task-specifi) — This patent describes an AI system where a large language model (LLM) directs specialized machine learning agents to answer natural language questions about financial data, then refines the answers using an adversarial AI. - [How Computers Rank Financial News for Analysts](https://patentbrief.org/patent/us/11922469/automated-news-ranking-and-recommendation-system) — This patent describes a computer system that automatically collects financial news, groups similar stories, and ranks them for financial analysts using advanced text analysis and machine learning. - [How Cloud Systems Automatically Create and Train AI Data Models](https://patentbrief.org/patent/us/11615208/dall-e-text-to-image-generation) — A cloud-based system that generates fake, privacy-safe data to train AI models, ensuring they remain accurate while protecting sensitive personal information. - [How AI Systems Learn to Predict and Act Simultaneously](https://patentbrief.org/patent/us/11170293/alphago-policy-and-value-networks) — A method for training AI models that combines supervised learning for prediction with reinforcement learning for decision-making in a single, coordinated system.