1128 results about "Ai systems" patented technology

A system and method for extending AI-enhanced decision platforms with deontic and normative reasoning capabilities that enhance adjustably autonomous decision-making through a novel integration of symbolic and neural approaches. The invention uses hierarchical and fuzzy deontic logic implementations alongside connectionist AI / ML to manage obligations, permissions, and prohibitions while maintaining observer awareness to achieve goals while incorporating knowledge across multiple expert domains. The system employs dynamic event and spatio-temporal knowledge graphs along with debate mechanisms, enabling high-assurance automated reasoning while preserving explainability through neuro-symbolic integration. In at least one embodiment, the invention operates through a federated distributed computational graph architecture that allows for arbitrary scaling while maintaining coherence, consistency and supporting compound workflows. The invention provides a framework for AI systems to make logically consistent, ethically-aware decisions by combining deontic reasoning with multi-agent coordination, token space communications and knowledge, including on intermediate results, enabling automated decision-making for a variety of applications.

An advanced model management platform for optimizing and securing generative artificial intelligence systems such as large language models (LLMs) and diffusion models. The platform incorporates various techniques to address the limitations of current generative AI systems, such as hallucination, lack of validation, security vulnerabilities, and inadequate model management. The system employs reinforcement learning algorithms for model optimization, retrieval augmented generation (RAG) for hallucination mitigation, domain-specific validation against expert knowledge, model distillation and similarity scoring for security, adversarial training for robustness, and attention mechanism search and model blending for advanced management and neuro symbolic AI routine combinations. By integrating these techniques, the platform significantly improves the performance, reliability, and security of generative AI across a wide range of tasks and domains leveraging the best elements of symbolic and connectionist techniques alongside automated planning and modeling simulation.

A multi-layer artificial intelligence system includes a foundation layer comprising at least one general-purpose large language model (LLM); an expert array layer comprising a plurality of specialized reasoning models; and a meta-reasoning model configured to coordinate operations between the foundation layer and the expert array layer to generate a reasoned analysis.

The method provides for securely harvesting and distributing trusted metadata from devices to artificial intelligence (AI) systems. It enables use of cryptographic hashes and signatures on data for supply chain provenance. It is an agentless method to enhance application security by design, and data protection with data authenticity and confidentiality in device to upstream services communications and data sharing. It helps securely harvest, filter, and forward device metadata to webhooks for AI / ML driven data analytics.

A composite AI system and method for advanced reasoning and automation that integrates symbolic knowledge graphs and algorithms with non-symbolic, or connectionist, models such as neural embeddings. A hierarchical architecture enables dynamically distributed, cooperative reasoning through layperson and expert-led challenge-based verification, model blending, model fitness and retraining and selection, comprehensive feedback loops at individual model or model blend or process flow with or without supervision, and specialized routing of processing to account for various operational risk, regulatory, legal, privacy, or economic considerations. Models, datasets, knowledge bases, simulations and simulation components, and embeddings are iteratively refined using knowledge graph elements and model, process, simulation or flow / process optimal hyperparameters which are recorded and tracked. Extraction of symbolic representations from connectionist models links them to curated ontologies of facts and principles.

A method for developing a generative AI system may include constructing a plurality of generative AI systems, wherein constructing the generative AI systems includes executing at least one modeling blueprint; providing a plurality of queries to each of the generative AI systems, the queries being part of an evaluation dataset; during processing of the queries by each generative AI system, monitoring values of one or more quantitative metrics; providing, for display by a user device, data indicating the values of the quantitative metrics for each generative AI system; and providing, for display by the user device, a recommendation regarding use or non-use of at least one generative AI system included in the plurality of generative AI systems.

The disclosure presents a multi-agent AI system utilizing specialized Large Language Models (LLMs) to automate and enhance software development workflows. This system integrates a memory-augmented generative pre-trained transformer (MemGPT) agent for dynamic context management, a Critic Agent for semi-adversarial quality feedback, and other specialized agents for task delegation and execution. The MemGPT agent interacts with an embedding storage to manage extended contextual information, enabling the system to handle complex software projects with enhanced accuracy and efficiency. This innovative approach significantly reduces manual intervention, streamlines the development process, and improves software quality, offering a robust solution to the challenges of modern software development environments.

An artificial intelligence driven system of systems may include a layered architecture for providing transaction support to various types of enterprises. A governance layer implements automated governance and policy enforcement through specialized governance modules utilizing generative AI technology. An enterprise layer supports enterprise functions by integrating management and control platforms with digital infrastructure. An offering layer creates and manages system offerings via content generation, personalization, and smart product modules. A transactions layer enables automated transaction orchestration through API integration, execution, and fulfillment modules. An operations layer manages AI systems through generation, training, verification and orchestration modules. A network layer provides adaptive networking capabilities through routing, protocol selection and communication modules. A data layer processes fused data from multiple sources using machine learning and AI systems. A resource layer manages computing, storage, and other resources through specialized resource modules.

Examples of the present disclosure describe systems and methods for automatically detecting and repairing reliability issues in operating systems and applications using a generative artificial intelligence (“AI”) system. In examples, a generative AI system receives a request to evaluate a detected issue in a software service or application. In response, the system analyzes error information associated with the detected issue to build an error context for the software code that caused the detected issue. The error context is used to identify the location of the software code file that comprises the software code. The error context and the software code file are used to identify a prompt. The prompt, the error context, and / or the identified software code are provided as input to a language model. The language model provides an output that is responsive to the user request and may perform actions to further evaluate or repair the detected issue.

An adapter to a base model of an artificial intelligence (AI) system is disclosed. The adapter includes a connector to connect the adapter to the base model such that during an operation of the AI system at least some portion of data transformed by the base model is propagated from the base model to the adapter and back from the adapter to the base model. The adapter includes a non-linear modifier to modify the data received from the base model non-linearly before returning the modified portion of the data back to the base model, and an AI trainer to tune the non-linear modifier of the adapter by propagating training data through the base model and the adapter and updating weights of the non-linear modifier of the adapter for given weights of the base model to optimize a loss function. Further, weight matrices for the base model and the adapter are jointly constructed by an additional module, which efficiently uses a pool of parameters to allocate to save memory requirement for adaptation of the AI system.

Various embodiments include systems and methods for generating a prompt for a generative artificial intelligence (AI) models. A processing system including at least one processor may be configured to recognize a user of the computing device, obtain user context information from a source of physical context information in the computing device, receive a user prompt for the large generative AI model (LXM), select a user profile from among a plurality of user profiles based on the user, the user context information and the user prompt, generate an enhanced prompt based on the user prompt and information included in the selected user profile, and submit the enhanced prompt to the LXM.

Disclosed are apparatuses, systems, and techniques that evaluate suitability of prompts for language model (LM) processing for improved quality and security of LM outputs. The techniques include determining prompt verification score(s) that include a first subset of tokens and a second subset of tokens, and obtaining, using an LM, the individual prompt verification score characterizing a likelihood that the second subset of tokens occurs, in the prompt, together with the first subset of tokens. The techniques further include determining, using the prompt verification score(s), whether the prompt is to be provided to the LM.

Computer-implemented methods and systems make a generative AI system more explainable. A programmed computer system grows a generative AI system by adding one or more explainable network elements to the generative AI system. Each explainable network element can be trained to discriminate two or more explainable sets of training data items for the generative AI system. After adding the one or more explainable network elements, training of the generative AI system can be updated with the one or more explainable network elements added. Then the programmed computer system can determined whether continued growth of the generative AI system is required.

A robotic surgical system includes a surgeon consol coupled to a patient console and coupled to one or more surgical instruments. The surgeon consol is used by a surgeon to perform a surgical procedure. A surgeon computer is coupled to or at the surgeon console. The surgeon consol is coupled to the one or more surgical instruments. A surgical robot is coupled to a robotic surgery control system and a feedback loop. The robotic surgery control system includes or is coupled to an artificial intelligence (AI) system. The feedback loop receives data from one or more sensors at the robotic surgical system. The data is analyzed by the robotic surgery control system, and in response operation of the robotic surgical system is adjusted as needed. The surgical control system or the AI system uses intraoperative data describing a surgical procedure being performed. The feedback loop receives data from one or more sensors of the robotic surgical system regarding performance of at least a portion of the robotic surgical system. The data is analyzed by the robotic surgical control system. In response to analysis, operation of the robotic surgical system is adjusted as needed. The robotic surgical control system or AI system extracts one or more programmed steps used by the surgeon for positioning at least one of the surgical instruments during the surgical procedure.

A robotic surgical system. a surgeon console operatively coupled to a patient console and one or more surgical instruments. A surgeon computer is coupled to or integrated with the surgeon console, the surgeon computer further operatively connected to the one or more surgical instruments; A surgical robot is coupled to a robotic surgery control system and a feedback loop. The robotic surgery control system includes or is coupled to an artificial intelligence (AI) system. A feedback loop is further configured to receive performance-related data from the one or more sensors, the data analyzed by the robotic surgery control system or the AI system to dynamically adjust the robotic system's operation as needed. A data extraction module retrieves, from the robotic surgery control system or the AI system. one or more programmed steps executed by the surgeon for positioning at least one of the surgical instruments during the surgical procedure.

A generative artificial intelligence (AI) system includes a generative AI model configured to generate outputs based on a training data set. The AI system additionally includes a secure data vault system. The secure data vault system additionally includes a sandbox system storing the generative AI model and operatively coupled to the generative AI model to send inputs to generate the outputs from the generative AI model, wherein the sandbox system comprises an execution environment configured to restrict execution of the generative AI model to a predefined memory address range. The secure data vault system further includes a secure network service communicatively coupled to the sandbox system and configured to authenticate a connection to an external system and to download from the external system an update package for the generative AI model when the connection is authenticated.

An AI-driven system for personalized advertising in real time, where: ◯ an analytics unit to monitor and analyze user behavior in real time across multiple digital platforms such as websites, mobile applications, social media, and smart devices; the unit collects data on user engagement, browsing patterns, time spent, and content preferences to enable targeted, personalized advertising; ◯ a prediction module that predicts preferences and interests of a user, operatively connected to the user interaction data collection unit, wherein the prediction module uses machine learning models such as deep learning, recurrent neural networks (RNNs) and transformer-based architectures to predict interests of users based on historical interactions and inferred preferences; ◯ an emotion and sentiment analysis unit that assesses the user's mood in real time through computer vision, natural language processing (NLP) and voice analysis, whereby the analysis of facial expressions, voice pitch and linguistic mood is used to determine emotional states and receptivity to advertising content; ◯ an embodiment of a context awareness component in operational communication with the emotion analysis and mood unit, in some cases further augmented by various environmental and situational data such as the device type and its physical location, date and time, and the content processed in the device, processing methods, etc., in establishing adaptability and automatic ad placement to be as relevant as possible to the user and their status as prescribed; ◯ Use reinforcement learning algorithms and generative AI models to drive advertising with personalization engines. Creative elements, messaging, and presentations are dynamically adjusted in real time based on user responses to ensure advertising is personalized and always optimized for best performance; o a privacy-focused AI system with federated learning, differential privacy methods, and on-device AI processing to reduce targeted advertising while complying with international data protection laws such as the General Data Protection Regulation (GDPR) and California consumer privacy laws; o an operationally adapted ad delivery mechanism to engage with real-time bidding (RTB) networks, programmatic advertising exchanges and demand-side platforms (DSPs) and place advertisements through digital advertising networks, which guarantees the delivery of tailored advertising to the most relevant audience in real time; and o a contextual feedback loop in which the machine learning models used in the preference and interest prediction module and in advertising personalization The engine is continuously updated to reflect the latest user engagement data, improving personalization over time and optimizing advertising performance.

The application includes systems and methods for phenotyping. A request is received to identify a target population having a phenotype. Predefined characteristics associated with the phenotype are obtained. Using a retriever model, a set of subjects is identified as potential members of the target population by searching databases. Medical information is obtained by searching a second set of one or more databases and providing corresponding information to an artificial intelligence (AI) component. Natural language instructions are provided to the AI component to provide context to the AI component to determine whether a respective subject in the set of subjects has at least one of the one or more predefined characteristics. A subset of subjects is identified by the AI system to be, or to have a high likelihood of being, a member of the target population.

A computer system may have one or computers and one or more data storage devices storing instructions, which when executed by the one or more computers implements a characterization manager, comprising: a test data database storing a plurality of test data sets; the characterization manager configured for selecting one or more test data sets from the test data database and apply the selected test data sets to a Generative AI system to derive from the Generative AI system an output; an output analyzer for processing the output to generate characterization data describing one or more facets of the output.

In various examples, systems and methods are disclosed relating to language model jailbreak detection using length-perplexity metrics. A system can identify a prompt for a language model—such as an LLM, VLM, etc.—and generate a perplexity score for the prompt. The system can determine, based at least on the perplexity score and a length of the prompt, that the prompt is indicative of a jailbreak attempt for the large language model. The system can restrict the prompt from input to the large language model—or block an output generated based on the prompt from being shared—responsive to determining that the prompt is indicative of the jailbreak attempt.

Aspects of the present disclosure relate to automatically updating a software application to ensure compliance with an updated data source. Embodiments include providing an embedding of a first version of a data source and an embedding of a second version of the data source to a comparison engine configured to compare the embedding of the first version of the data source and the embedding of the second version of the data source and generate a data source difference summary. Embodiments further include providing an embedding of a software application code module and the data source difference summary to a code update engine trained to generate an updated version of the software application code module based on the embedding of the software application code module and the data source difference summary. Embodiments further include updating code of the software application using the updated version of the software application code module.

A platform for dynamically generating application experiences. The platform comprises a design management system, an agent orchestration system, an analytics system, a model management system, a user management system, and databases for storing design elements and templates. The design management system provides a portal for application owners / designers to create UX / UI designs, allowing them to select design elements from a set of categories or templates. The platform gathers existing websites / applications to identify common design patterns, stored in a design catalogue database, and suggests historical interfaces for design exploration. It enables the generation of templated applications that integrate with legacy systems. The agent orchestration system parses user specifications, selects generative AI systems, and generates UX / UI content based on the specifications. The analytics system collects and analyzes data to provide insights for improving UX / UI design and optimizing website performance. The model management system trains and maintains generative AI models used for content generation.

Techniques are provided for personal data and AI system integration. It is determined to respond to a user prompt. An AI system is provided a user prompt description, a database description describing a user database comprising user data associated with the user, and instructions to provide a query for relevant data in the user database that the AI system can use to answer to the user prompt. A query is received from the AI system and executed against the user database to generate a result set. The result set is submitted to the AI system. The answer is received from the AI system based on the user prompt description and the result set. A response is generated for the user based on the answer from the AI system.

A system and method including receiving a prompt specifying at least one task type; determining a system prompt based on the received prompt, the system prompt including artificial intelligence (AI) system configuration details corresponding to the at least one task type; pre-processing the system prompt to generate a pre-processed prompt including code referenced in the system prompt; transmitting, as an input prompt, the pre-processed prompt to an AI system; receiving, in response to the AI system executing the pre-processed prompt, a result from the AI system; and storing a record of the result from the AI system in a data repository.

Disclosed are systems and techniques for training personalized language models. The techniques include applying a plurality of first machine learning models to a first input prompt. Each of the plurality of first machine learning models generates a respective reward value of a first plurality of reward values. The techniques include applying a second machine learning model to the first plurality of reward values to obtain first reward value embeddings; applying a third machine learning model to the first reward value embeddings and the first input prompt to obtain a first output response; calculating a first loss based on a comparison between the first output response and the first input prompt; and causing the second machine learning model to be modified based on the first loss.

An AI-driven system for automated dispute resolution employs natural language processing to analyze claims and arguments, extracting semantic relationships to construct a structured data model. A reasoning module evaluates this model against a database of precedents and legal principles, generating decision scores for potential outcomes. The user interface presents visual representations of the analysis, allowing decision-makers to interactively explore and modify inputs. A decision recommendation module proposes resolutions based on criteria such as novelty, legal sufficiency, and compliance with jurisdictional laws.

The invention discloses a power proxy service system and method based on artificial intelligence, and the method comprises the steps: collecting power data in real time through an intelligent electric meter and a sensor, and uploading the power data to a cloud platform through the Internet of Things for preprocessing and marking; predicting the power load by using time sequence analysis, regression, SVM and LSTM methods in combination with weather, season and holiday factors; power grid load dispatching is optimized through reinforcement learning or a genetic algorithm, and automatic allocation is achieved; the sensor monitors the state of the power equipment in real time, predicts the fault risk and gives an alarm in advance; the system provides energy-saving suggestions according to historical power consumption data of a user, and adjusts an equipment operation mode in real time; the intelligent customer service server pushes personalized electricity consumption suggestions based on natural language processing; an encryption technology and multiple identity authentication are adopted to guarantee data security, regular security audit and vulnerability repair; according to the electric power proxy service system and method based on artificial intelligence, integration with an AI system and construction and optimization of an intelligent power grid and renewable energy technology are promoted.

Described herein is an Autonomous Conversational AI system, which does not require any human configuration or annotation, and is used to have multi-turn dialogs with a user. A typical Conversational AI system consists of three main models: Natural Language Understanding (NLU), Dialog Manager (DM) and Natural Language Generation (NLG), which requires human provided data and configuration. The system proposed herein leverages novel Conversational AI methods which automatically generates conversational AI configuration from any historical conversation logs. The automatically generated configuration contains Auto-Topics, Auto-Subtopics, Auto-Intents, Auto-Responses and Auto-Flows which are used to automatically train NLU, DM and NLG models. Once these models are trained for given conversation logs, the system can be used to have dialog with any user.