92 results about "Intelligence system" patented technology

The invention relates to the technical field of management and control systems, in particular to a digital intelligence system applied to collaborative management and control of water-power engineering construction participating units, which comprises a project data management module covering water-power engineering construction full life cycle management, extracting multi-source information data from various subsystems, and constructing a project view and a project management information base; the project risk analysis module is used for constructing an intelligent risk analysis model for risk analysis and generating a dynamic evaluation result, a graded early warning notification and an auxiliary decision scheme; the project collaborative management module is used for processing graded early warning notification and auxiliary decision-making schemes by using a multi-layer perceptron model, and generating finalizing service achievements and management process records; and the project document management module is used for performing compliance automatic checking and processing on the electronic documents needing to be archived, and dynamically updating and optimizing the project management information base. Through the closed-loop management and control system, the cooperative management and control efficiency of water-power engineering construction participation units is improved.

Methods, systems, and computer storage media for providing a data analysis pipeline using a data analysis pipeline engine in a data intelligence system are described. A data analysis pipeline refers to a structured sequence of data processing steps that support transforming raw data into meaningful insights or actionable outcomes. The data analysis pipeline engine is an unsupervised learning pipeline based on clustering, topic modeling, and Large Language Models (LLMs). For example, the data analysis pipeline can use advanced machine learning techniques to automatically categorize emails into semantically similar clusters, enabling the data intelligence system to quickly identify and prioritize potentially high-risk emails for further investigation. The data analysis pipeline employs AI agents for context-aware graph induction relevance assessment. The AI agents employ induction and deduction loops to build and refine a data feature hypergraph (e.g., vulnerability hypergraph) that encompasses identified relevant data providing a holistic view of a contextual landscape.

Systems, methods, and apparatus are disclosed for omnimodal sensing, data fusion, and autonomous decision-making across physical and digital domains and further integrates a Multimodal Diagnostic System (MDS) and Impairment Recognition and Intervention System (IRIS) with defense architecture or a system architecture that can be compliant with the Modular Open Systems Approach (MOSA) and Sensor Open Systems Architecture (SOSA) to ensure interoperability. The system can utilize real-time multisensory fusion, cryptographic provenance via blockchain, and resilient magnetoelectric communication to support mission-critical decision-making across manned and unmanned platforms in denied or contested environments.

A threat intelligence system utilising language models to generate queries for external threat intelligence systems, receive and filter responses, and generate alerts and reports using further language models.

Methods, systems, and computer storage media for providing a modular cybersecurity platform are described. The modular cybersecurity platform is implemented using a modular cybersecurity engine that operates based on an analytical framework for dynamic data analysis and data management in a data intelligence system. In particular, the analytical framework is based on complementary modular components that are designed to interoperate in the modular cybersecurity engine. The modular cybersecurity engine includes a modular distributed system, a credential detection system, and a credential semantic graph system. The modular cybersecurity engine supports cybersecurity and sensitive data management scenarios that can empower investigators in various investigations, and provide automated flows that are highly scalable and support different types of functionality (e.g., priority embedding pipeline, credential scanning, and credential semantic graph analysis). The utility of the modular cybersecurity engine is demonstrated by its wide-ranging application in addressing complex cybersecurity challenges and sensitive data management tasks.

A model verification system and associated method for employing a multi-party verification technique to verify machine learning models and generative AI systems. The models and associated systems can be deployed in an enterprise and require verification to ensure that cohorts are properly verifying the models and systems and evaluation to ensure that the models and systems operate responsibly and achieve intended outcomes. A dynamic, multi-stakeholder blinded verification process can be employed for the continuous verification and evaluation of machine learning models and the systems that use them. This helps promote unbiased, reproducible verification, evaluation and assessments by preventing potential biases from cohorts form part of the verification process.

An anthropomorphic AI control system including a plurality of sensors configured to collect industrial input data. The control system also includes an artificial intelligence-enabled edge-deployed computing device configured to analyze and fuse multimodal input data and generate an output through anthropomorphic computing. The computing device includes a cognitive module performing real-time decision-making at the sensor edge and a controller to manage industrial process actuators across operational domains. In management of industrial fluid flow, the control system may include AI-enabled fluid characterization modules to calculate the Reynolds number and incorporate compliance with AGA3 and AGA8 standards.

The invention provides a software supply chain risk component calling identification method, and belongs to the technical field of basic safety. The method comprises the following steps: loading components in a Java Web application, and dynamically capturing a loaded component list; storing the component list locally and sending the component list to an external intelligence system, acquiring risk component information, and generating a risk calling interface signature according to the risk component information; a preset instrumentation rule file is loaded based on the risk calling interface signature, and accurate monitoring of the risk interface is realized through dynamic method matching and byte code enhancement; screening risk interfaces triggered during operation according to cross comparison of static data and dynamic calling data, and marking high-risk components which must be repaired and risk components which can be postponed to be repaired; the risk report generation module generates repair suggestions and priority reports. According to the method, the accuracy of risk assessment is fundamentally improved, meanwhile, the unnecessary repair cost is remarkably reduced, and an efficient and innovative technical solution is provided for supply chain risk management.

Methods, systems, and computer storage media for providing iterative data processing optimization using an iterative data processing optimization engine in a data intelligence system are described. Iterative data processing refers to handling data where the processing steps are repeated multiple times, across multiple views or modalities, to train machine learning models, filter and score data or generate output. The iterative data processing optimization engine employs expectation step machine learning models that are simple but with fast language models to efficiently and effectively probe and analyze data, while iteratively refining maximization step machine learning models that are optimized and fast to approximate the probing mechanism of the expectation step machine learning models more efficiently, for example, using metadata, external information, and compressed representation. The iterative data processing optimization engine can operate based on an agentic framework using lightweight artificial intelligence (AI) agents to perform model fitting, featurization, and report generation autonomously.

A system is disclosed herein for attributing user affective responses to discrete elements within an experience. Software agents extract token instances from sensor data, while a response decomposition module allocates portions of measured affective response to tokens based on user attention. A token library stores token-response associations across users and domains, enabling prediction of responses in new contexts. An orchestration module coordinates agents and library updates, with privacy managers ensuring local processing of raw data. The system distinguishes tokens of interest from background elements, supporting cross-domain learning and overcoming limitations of static, siloed affective measurement systems.

Methods, systems, and computer storage media for providing entity-specific data analysis using an entity-specific data analysis engine in a data intelligence system are described. The entity-specific data analysis engine can be an LM-based system that supports generating and communicating entity-specific data analysis output. In operation, a dataset associated with an entity is accessed. A bidirectional volumetric analysis output is generated based on executing a plurality of bidirectional volumetric analysis operations against the dataset. A plurality of probe questions and a plurality of data analysis axes associated with a focus area are generated for analyzing the bidirectional volumetric analysis output. Using the bidirectional volumetric analysis output, the plurality of probe questions, and the plurality of data analysis axes, an entity-specific data analysis output is generated, based in part on identifying false positive trends in the dataset and defining rules to filter out the false positives from the entity-specific data analysis output.

A question answering system is configured to extract answers to queries from a collection of data. The system includes an extractive stage configured to receive a query and to determine one or more answers to the query from the collection of data and one or more generative large language model stages configured to pre-process the query before it is provided to the extractive stage and / or to post-process the answers to the query. The collection of data includes a number of document segments and the extractive stage is configured to attribute at least some of the one or more answers to corresponding sub-parts in the document segments.

A system and method for implementing experiential manifold cognition that extends persistent cognitive machines beyond discrete thought caching to continuous geometric representation of experience. The system maintains an experiential manifold comprising a differentiable manifold with Riemannian metric tensor encoding semantic relationships, compression pressure field governing memory consolidation, and potential field encoding goals and attention. Input data is projected onto the manifold through adaptive geometric diffusion preserving semantic structure. The system executes geometric transformations including metric evolution, geodesic computation, and curvature estimation. During non-interactive periods, autonomous evolution occurs through trajectory recombination and selective pruning. A user interface enables visualization and direct manipulation of manifold geometry, translating navigation into geodesic traversal and edits into metric modifications. The system maintains persistence across sessions and enables controlled federation between multiple manifolds through consent-bounded synchronization. Applications include persistent narrative worlds, collaborative cognitive spaces, and experiential intelligence systems that learn through geometric evolution.

Methods, systems, and computer storage media for providing a data analysis pipeline using a data analysis pipeline engine in a data intelligence system are described. A data analysis pipeline refers to a structured sequence of data processing steps that support transforming raw data into meaningful insights or actionable outcomes. The data analysis pipeline engine is an unsupervised learning pipeline based on clustering, topic modeling, and Large Language Models (LLMs). For example, the data analysis pipeline can use advanced machine learning techniques to automatically categorize emails into semantically similar clusters, enabling the data intelligence system to quickly identify and prioritize potentially high-risk emails for further investigation. The data analysis pipeline employs AI agents for context-aware graph induction relevance assessment. The AI agents employ induction and deduction loops to build and refine a data feature hypergraph (e.g., vulnerability hypergraph) that encompasses identified relevant data providing a holistic view of a contextual landscape.

The present invention discloses a blockchain-based edge intelligence system resource management method, comprising a system controller sensing the current user device artificial intelligence task information and the system's current wireless environment information; at the same time, the system controller senses the computing resource information of the user device, edge server and cloud server; uploading relevant information from the corresponding device to the system controller via a wireless connection; inputting the current artificial intelligence task information and the system's current wireless environment information into a trained optimization model deployed in the system controller, calculating the user device transmission power control, artificial intelligence task data volume control, user device artificial intelligence task offloading decision based on the current state, and the computing resource allocation to be used in the reasoning process and block generation process of the artificial intelligence task, and transmitting the calculation to each computing entity for execution; the present invention utilizes task offloading and computing resource allocation algorithms to improve system efficiency and user experience.

Various techniques for providing a DNS automated intelligence solution are disclosed. In some embodiments, a DNS Automated Intelligence System (DAISy) is disclosed that includes a system designed to create threat intelligence for use in protective DNS, or DNS Detection and Response systems which control access to internet resources at a DNS resolver. The disclosed DAISy solution includes the ingestion of raw source data, the curation and refinement of this source data into specialized data sets used for identifying threats, active processes to increase visibility into internet domain names, and can also include human-in-the-loop acceleration that allows for rapid automation, and a modular incorporation of DNS-specific signatures for identification of suspicious domain names. The disclosed DAISy solution is self-sustaining, automated, and incorporates human guidance. Moreover, it is effective for scaling the detection of malicious and suspicious domains, which is not possible with existing traditional approaches to DNS security.

The invention provides a malicious external connection event detection method and device of a host. The method comprises the steps that multiple pieces of destination address information are collected in a server log of the host; the destination address information comprises a destination IP and / or a destination domain name; the destination IP is used for indicating IP addresses requested to be accessed by a plurality of servers of the host; the destination domain name is used for indicating websites requested to be accessed by a plurality of servers of the host; the server log is generated through a log generation system deployed in the host; determining malicious destination address information in the multiple pieces of destination address information; the malicious destination address information refers to destination address information successfully matched with a malicious address in the threat intelligence system; determining an alarm object according to the malicious destination address information; and outputting the malicious external connection event alarm information to the alarm object. According to the invention, the detection coverage can be improved, and the detection cost can be saved.

A threat intelligence system utilising language models to generate queries for external threat intelligence systems, receive and filter responses, and generate alerts and reports using further language models.

Systems and methods for utilizing nursing intuition to support early clinical intervention are provided. The systems and methods may include a vector database stored on one or more memory devices, the vector database comprising one or more vector embeddings positioned in a vector field, wherein each of the one or more vector embeddings is indicative of medical data of one or more individuals, and wherein the positioning of the one or more vector embeddings in the vector field is based on the similarity of the one or more vector embeddings to each other. The systems and methods may also include at least one machine learning model. The machine learning model may be trained to establish a likelihood of clinical deterioration of one or more individuals based on the vector database.

Aspects of the disclosure relate to software systems of a tracking system (100) configured to process data from tracking tags ( 102, 104) affixed to assets to be tracked. The software systems may be used to process data such as payloads, interact with various systems including client facing systems, and make predictions regarding tracked assets. The predictions may provide information regarding the status of the tracked, assets during trips. Tire predictions regarding the trips may include destinations of the assets during the trips, events occurring during the trips, conditions of the assets during the trip, estimated, time of arrival at the one or more destinations. etc. The software systems may be robust such that these predictions may be made with minimal or no information pertaining to the trips beyond payloads from tracking tags (102, 104) affixed to the assets to be tracked.

A medical intelligence system generates medical assistance data determined to be relevant to an ongoing medical procedure. A state inference engine obtains medical video data and / or sensor data from sensors during the medical procedure and generates recognition data indicative of a state of the medical procedure. A medical procedure intelligence engine accesses a knowledge graph populated from multiple disparate sources and determines, based on a medical intelligence model, the medical assistance data based on the recognition data and the information in the knowledge graph. The knowledge graph and the medical intelligence model may be updated as additional knowledge and medical data is learned. The medical intelligence system may generate information such as, for example, video clips or instructions relating to a next step in the medical procedure, billing codes or descriptions of the medical procedure for medical records, and / or other data characterizing performance of the medical procedure.

The present application describes systems and methods for populating a DNS cache of a recursive DNS server using information gathered by a threat intelligence system. The threat intelligence system may collect some or all DNS responses from one or more recursive DNS servers as the one or more DNS servers process various received requests. Since the threat intelligence engine has access to this DNS data, the DNS data may be used to seed a DNS cache of a recursive DNS server.

Examples of the present disclosure are directed to systems and methods for using router identifier information to mitigate denial of service attacks in an autonomous system (AS). Each router of the AS may be assigned a router identifier (ID) that is unique to the AS and may be periodically changed. The ingress router first receiving the packet within a particular AS may insert its router ID into the packet. A threat intelligence system may sample packets of traffic received by the AS and examine the inserted ingress router IDs in making a threat determination. If a distribution of detected ingress router IDs from sampled packets does not match an expected distribution of ingress router IDs, one or more threat mitigation actions may be invoked.

Systems and methods for mitigating DNS amplification attacks are provided. In one example, a threat intelligence system collects data about the requests received by a DNS server, and / or responses generated by the DNS server. The threat intelligence system triggers a threat mitigation action upon detecting evidence (in one or more forms) of a DNS amplification attack. The threat mitigation action may include filtering DNS responses generated by the DNS server. The filtering rule may indicate that a DNS response in which the payload size is above a threshold payload size is to be dropped. In examples, the payload threshold size is dynamically set by the threat intelligence system using a machine learning model to minimize the filtering of DNS responses for valid DNS queries, while maximizing filtering of DNS responses for malicious DNS queries.

Methods, systems, and computer storage media for providing iterative data processing optimization using an iterative data processing optimization engine in a data intelligence system are described. Iterative data processing refers to handling data where the processing steps are repeated multiple times, across multiple views or modalities, to train machine learning models, filter and score data or generate output. The iterative data processing optimization engine employs expectation step machine learning models that are simple but with fast language models to efficiently and effectively probe and analyze data, while iteratively refining maximization step machine learning models that are optimized and fast to approximate the probing mechanism of the expectation step machine learning models more efficiently, for example, using metadata, external information, and compressed representation. The iterative data processing optimization engine can operate based on an agentic framework using lightweight artificial intelligence (Al) agents to perform model fitting, featurization, and report generation autonomously.

System and methods are disclosed relating media intelligence for a company relating to a topic and / or theme. In some examples, media intelligence parameter data and company historical data can be received, which can be used to generate a subject search parameter. The subject search parameter can include one or more phrases, words, sentences, and / or categories for the topic and / or theme. Data for the topic and / or theme from a number of private and / or media data sources can be queried based on the subject search parameter. The queried data can be aggregated to provide aggregated data. The aggregated data can be filtered to provide filtered data. The filtered data can indicate a position of the private and / or media data sources on the topic and / or theme. A recommendation can be provided for the topic and / or theme using a machine learning model.

The invention relates to the technical field of digital intellectualization, in particular to a digital intellectualization system for plasma cell disease and related health management of an AI model, and the system comprises a boundary recognition module which is used for recognizing a sample boundary; the sample boundary comprises a first-class sample boundary and at least one second-class sample boundary associated with the first-class sample boundary; the sample segmentation module is used for segmenting the sample data according to the sample boundaries and generating data blocks, and comprises a second-class boundary identification sub-module used for identifying second-class sample boundaries between two adjacent first-class sample boundaries and a second-class boundary identification sub-module used for identifying second-class sample boundaries between two adjacent second-class sample boundaries; the data block segmentation sub-module is used for segmenting the sample data into data blocks according to the second-class sample boundary; the data block is marked with a first index tag; and the association identification sub-module is used for identifying at least two data blocks belonging to the two adjacent first-class sample boundaries as associated data blocks. According to the invention, the accuracy and efficiency of response can be improved, and potential response risks are effectively avoided.

Various embodiments of devices and methods for deploying and managing threat sensors in a malware threat intelligence system are described. In some embodiments, the system includes multiple threat sensors deployed at different network addresses and physically located in different geographical areas within a provider network for detecting interactions from sources. In some embodiments, a threat sensor deployment and management service determines a deployment plan for the multiple threat sensors, including a deployment plan for a threat data collector associated with each threat sensor. The threat data collectors may be of different types, such as using different communication protocols or ports, or providing different types of responses to inbound communications. Different threat sensors may have different lifetimes. The service deploys the threat sensors based on the plan, collects data from the deployed threat sensors, adjusts the deployment plan based on the collected data and the lifetime of the threat sensors, and then performs the adjustments.

A recursive symbolic intelligence system is disclosed that employs continuously evolving symbolic nodes represented as multi-dimensional vectors with physical, cultural, and optionally functional sub-components. The system implements a mathematically defined recursive update function s(i)(t+1)=α·s(i)(t)+β·f(adj)({s(j)(t)})+γ·f(input)(v(i)), wherein α, β, and γ are tunable weighting factors; f(adj), aggregates contributions from semantically and topologically adjacent nodes; and f(input), processes incoming multi-modal input including text, audio, video, and sensor data. A tamper-evident ledger configured with a cryptographic hashing function such as SHA-256 records each symbolic update, and a scheduling module employing a multi-armed bandit algorithm together with a meta-learning engine utilizing covariance matrix adaptation evolution strategy dynamically optimizes processing resources and hyper-parameters. This system provides a continuous, adaptive, and auditable framework for dynamic knowledge representation applicable to domains such as autonomous systems, adaptive content generation, and symbolic legacy encoding.