2872 results about "Usage data" patented technology

The embodiment of the invention provides a network flow anomaly monitoring method and device based on a BiLSTM-Att network, and the method comprises the steps: obtaining network flow time sequence data, system resource use data and service call topological data, constructing a multi-modal time sequence feature matrix through employing a sliding time window method, calculating the importance score of each feature in the traffic feature subset, the resource feature subset and the service feature subset through an information gain algorithm, and screening the most discriminative feature based on a score threshold to construct a fusion feature subset; inputting the fusion feature subset into a set bidirectional long short-term memory-attention network, performing multi-level analysis on target features, performing comprehensive evaluation on a detection result by adopting a confidence-based multi-view decision fusion method, and generating a detection report containing an anomaly level, an anomaly type and an anomaly reason; according to the invention, the efficiency and accuracy of network flow anomaly monitoring based on the BiLSTM-Att network can be effectively improved.

Described herein are a system, method, and device for configuring a generative machine learning model using a syntactic interface. A system may include a user interface, a memory, and a processor configured to, using a syntactic interface displayed using the user interface, receive a syntactic interface input from a user; identify an electronic medical record (EMR) by generating an EMR database query as a function of the syntactic interface input, querying an EMR database using the EMR database query, and receiving, from the EMR database, an EMR database response; generate a prompt as a function of the syntactic interface input; generate a first generative model output as a function of the prompt and the EMR using a trained generative machine learning model; and using a conversational interface displayed using the user interface, display the first generative model output to the user.

Systems and methods for enriching raw user text with a database to identify relevant context, wherein generated prompts provide responses to user queries is provided. A method includes receiving a query, wherein the query comprises the raw text, creating a first embedding based on the query, retrieving a plurality of other embeddings, wherein the plurality of other embeddings are complementary to the first embedding, creating a contextual prompt including context from at least one of the plurality of other embeddings, processing the contextual prompt using a trained machine learning model, thereby generating a response to the query, and causing the response to be displayed by a display device.

Systems and methods for generating output data based on a data graph are provided. An output request for the output data based on the data graph is received. The output request comprises one of a natural language request from a target user or an application request from an application of the target user. The data graph has nodes and edges between the nodes. The nodes represent entities associated with an enterprise organization and the edges represent relationships among the entities. A graph data query is generated with a large language model (LLM) using the output request as a first input to the LLM. The graph data query is performed against the data graph to obtain a graph data output that represents a sub-portion of the data graph. The output data is generated with the LLM using the graph data output as a second input to the LLM.

Systems and methods for activity-based device recommendations are disclosed. For example, historical usage data associated with a device may indicate that the device is likely to be associated with a given state at a given time. When the device is not in the anticipated state, a recommendation to transition the device state, for example, may be sent. Additionally, a determination of the activity state associated with the device, such as an active state, an asleep state, and / or an away state may be utilized to determine the recommendation to surface, to determine whether to send a recommendation, and when and / or how to send the recommendation.

A system and method for comprehensive data utilization and tracking comprising an ontological engine which in some embodiments is configured to create and curate various industry-specific ontologies which can be used to provide deeper context to an enterprise's network traffic and data transmission. The system and method further comprise a tagging and tracking engine configured to inspect network packets, apply a first tag associated with an authentication object, apply a second tag associated with an identified ontology, and track the tagged packets as they traverse the enterprise network, generating data utilization tracking information as the packets move through the network. A scoring engine may leverage the data utilization tracking information in combination with user entity and behavior data to compute a risk score associated with data utilization on the enterprise network.

The invention discloses a multi-source three-dimensional model lightweight processing and lossless compression supporting method, system and device and a storage medium, and relates to the three-dimensional technical field, and the method comprises the following steps: carrying out format compatibility check on an imported three-dimensional model, and analyzing the geometric structure, texture characteristics and material attributes of the model; the geometric structure of the three-dimensional model is simplified by adopting a quadratic error measurement algorithm and edge folding, the simplified model is optimized through edge segmentation operation, and a lightweight model is obtained; and compressing geometric data of the lightweight model by using a data compression algorithm, and compressing texture data through predictive coding to complete lossless compression of the three-dimensional model. According to the method, the loading speed and the real-time rendering efficiency are remarkably improved by reducing the size of the three-dimensional model file and optimizing the texture compression algorithm. The lossless compression technique ensures that a high-quality visual effect is kept in the lightweight process, the lightweight model reduces the storage space requirement, and the energy consumption of data transmission and processing is reduced.

The invention provides a multi-kitchen-appliance remote control method and system based on context awareness, and relates to the technical field of smart home, and the method comprises the steps: collecting kitchen environment data and user historical use data, and carrying out the wavelet multi-resolution decomposition and density gradient matrix recognition of abnormal data; the method comprises the following steps: extracting data time sequence features by combining a bidirectional recurrent neural network and performing hierarchical coding, inputting a fused feature vector and a density distribution graph into an improved long-short-term memory network, performing feature propagation by combining a Fisher information matrix and a time-varying association graph, and predicting a kitchen appliance use trend by utilizing a prophet model. And based on a risk assessment model and a Monte Carlo tree search method, in combination with an adaptive exploration mechanism and a multi-target evaluation system, generating and assessing a candidate control strategy, and outputting an optimal kitchen electricity cooperative control strategy.

There is provided a computer-implemented method for ensuring that a large language model (LLM) generates original text, including (i) providing or accessing a database of previous text that the LLM should not generate, wherein the database includes text used to train the LLM; (ii) checking potential continuations generated by the LLM against the database; (iii) when a potential continuation generated by the LLM matches text in the database, adjusting the potential continuation generated by the LLM to no longer match that text in the database, to produce an adjusted potential continuation, and (iv) storing the adjusted potential continuation.

Queries may be made against a non-relational database without impacting the capacities of the non-relational database by enabling performance of queries to a non-relational database via an external query management, backup management, and a non-relational database backup hosted in an external data storage. The query management and backup management of the non-relational database service may split transactional load to the non-relational database and analytical load, and furthermore allow selection of a desired data freshness for queries including various time ranges, such as seconds, minutes, or days.

The disclosed cyber threat detection and deception system leverages metadata information collected by the data storage management system. Using the metadata collected by the data storage management system, the cyber threat detection and deception system analyzes that metadata to detect any anomalies. Once suspicious or abnormal behavior is detected in an asset, the cyber threat detection and deception system creates and deploys a cyber deception plan for that asset. The cyber deception plan is implemented by way of deploying sensors or emulation traps in any number of cyber-threat appliances within the data network. Lures or tokens are configured and deployed on the suspected assets themselves to redirect attackers to the emulation traps.

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 invention discloses a financial data automatic filling method and device, equipment and a storage medium, and belongs to the technical field of big data. The method comprises the following steps: determining a data source corresponding to original financial data by using a pre-trained data classification model; acquiring a data processing rule engine and a target data filling template matched with the data source; performing data cleaning on the original financial data based on a data cleaning rule; performing data analysis on the standardized data by using a data analysis rule; performing association relation extraction on the target data source field and the target filling field by using a data mapping rule, and performing data field mapping according to the field association relation; and according to a data field mapping result, filling the target data source field into the target data filling template to generate a financial data report. The invention further relates to the technical field of block chains, and financial data are stored on the block chain nodes. According to the method and the device, the applicability and the operation convenience of automatic filling and reporting of financial data in a multi-source data scene are improved.

The invention relates to the technical field of computers, in particular to a task scheduling optimization analysis method and system based on big data. The method comprises the following steps: acquiring task related data, task system resource use data and task execution state data in real time in a corresponding distributed big data processing scene among a server, a storage device and a client; performing big data feature mining analysis and task scheduling clustering analysis by using a Hadoop distributed framework to generate task scheduling cluster groups corresponding to similar resource requirements; performing residual execution duration calculation and task emergency accounting on the task calculation nodes corresponding to the distributed big data processing scene to obtain task node scheduling emergency degrees; and performing scheduling priority determination and task scheduling optimization analysis on the corresponding task calculation nodes to generate a task dynamic optimization scheduling scheme. According to the method, the rationality of distributed task resource scheduling can be improved.

The invention provides a project cost management method based on artificial intelligence, and relates to the technical field of project cost, and the method comprises the following steps: 1, data mining and analysis: extracting valuable information from a large amount of historical project cost data through building a data mining model, and analyzing the mined data through a data analysis tool; step 2, automatic measurement and pricing; step 3, constructing a cost prediction model; step 4, risk assessment and early warning; step 5, project progress and cost collaborative management; step 6, intelligent cost control; and 7, intelligent supplier management. By constructing the data mining model and using the neural network algorithm to cooperate with the association rule mining algorithm, deep mining can be effectively performed on the engineering cost data, and meanwhile, the data analysis tool is used to analyze the data, so that the workload of data collection is reduced, and the efficiency of engineering cost management is improved.

Rebalancing in a fleet of storage systems using data science including generating, by the cloud-based rebalancing system, a plurality of workload migration scenarios to address a detected workload imbalance among a plurality of workloads in a fleet of storage systems; determining, by the cloud-based rebalancing system, a plurality of movement vectors for each workload migration scenario, wherein each of the plurality of movement vectors describes a consideration factor for migrating a workload of the plurality of workloads within the fleet of storage systems; and generating, by the cloud-based rebalancing system, at least one rebalancing proposal based on the plurality of movement vectors for each workload migration scenario.

A system and method are provided for communicating security service context within a network. Intermediary nodes located along the path of a data flow apply various security services to the data flow, and keep a record of the security services by generating in-band and out-of-band information. The in-band information is limited, e.g., by the maximum transmission unit (MTU) to short attestations that fit within optional IPv6 extension headers. The out-of-bound information, which is recorded, e.g., in a ledger using an overlay network, provides additional information fully describing the security services. Based on the in-band and out-of-band information (e.g., using the attestations to retrieve the additional information from the ledger), the data flow is either allowed or denied entrance to a particular workload. Applying the security services and generating the in-band and out-of-band information can be performed using data processing units (DPUs) and / or an extended Berkley packet filters (eBPFs).

The invention provides a server resource utilization rate improving method, system and device, a medium and a product, and relates to the technical field of data processing, a machine learning model is trained according to historical resource use data of a server, and a resource prediction model is established; according to the resource prediction model, predicting a resource demand of the server in a target time period, and according to the resource demand, dynamically adjusting a constraint variable of the server; wherein the constraint variable comprises at least one of the following items: a CPU utilization rate constraint and a memory utilization rate constraint, and according to the dynamically adjusted constraint variable, reevaluating the resource demand of each server resource slice, so as to dynamically adjust the resource distribution of each server resource slice according to the reevaluated resource demand; wherein the server resource slices are obtained by dividing server resources based on a resource allocation strategy.

The invention discloses a steel template service life evaluation method based on deep learning, and relates to the technical field of steel template management, and the method comprises the following steps: collecting the use data and image data of a steel template, analyzing and obtaining the physical index data, structural data and material quality data of the steel template, carrying out the preprocessing of the collected data, and obtaining the service life of the steel template; the physical index data comprises the strength, the abrasion and the corrosion of the steel template, and the structural data comprises the three-dimensional geometrical shape and the size data. According to the method, the physical strength, the surface condition and the material attribute of the steel template are comprehensively analyzed based on deep learning, so that the performance difference of different parts caused by factors such as stress distribution, corrosive wear and the like is reflected more meticulously and accurately; and the deep learning algorithm can automatically learn and extract characteristics having key influence on the service life of the steel template from a large amount of multi-dimensional data, so that the accuracy of evaluating the service life of the steel template is remarkably improved.

The invention provides a method and system for preparing a high-temperature anti-aging test board for chip testing, and relates to the technical field of data energy storage and resource scheduling, and the method comprises the steps: designing a schematic circuit diagram and a PCB wiring scheme; a test plate is made of a high-temperature resistant material; bare board verification, electrical performance verification, program setting verification, high temperature verification and junction temperature measurement verification are carried out; using data is recorded, ultrasonic cleaning and drying are carried out, and a performance evaluation model is established through a hardware management system to judge whether maintenance or replacement is needed. According to the invention, the accuracy of chip testing in a high-temperature environment is improved, and the service life of the test board is prolonged.

The invention provides an electricity stealing behavior detection method based on feature fusion and a CNN-LSTM hybrid model, and belongs to the technical field of electric power information technology and deep learning. According to the method, after power load data and user behavior characteristics are subjected to data processing and enhancement, a deep learning model is combined with a self-attention mechanism to process user electricity consumption data, user electricity stealing behavior anomaly detection is carried out, and the electricity stealing risk identification accuracy and calculation efficiency can be remarkably improved. According to the invention, power grid enterprises can be helped to efficiently deal with electricity stealing conditions, and comprehensive and accurate identification of electricity stealing behaviors is guaranteed. By learning user historical load data, integrating time sequence characteristics of user loads and optimizing a data abnormity diagnosis and judgment mechanism, the electricity stealing user detection accuracy is improved, and reliable support is provided for power grid enterprise decision making.

The invention provides an intelligent decision-making method and device for cross-modal data, equipment and a storage medium, and the method comprises the steps: carrying out the blockchain storage of collected multi-modal process data, and generating an on-chain hash certificate; performing cross-modal space-time alignment and feature fusion on the multi-modal process data according to the space-time metadata analyzed by the Hash certificate on the chain to generate a process knowledge graph; constructing an interactive teaching model according to the process knowledge graph; determining a multi-dimensional contribution measurement value according to the use data of the interactive teaching model; and based on the multi-dimensional contribution magnitude and the hierarchical smart contract architecture, determining the data access permission through a community voting mechanism. Through implementation of the scheme, the process knowledge graph and the interactive teaching model, the inheritor operation data and the material response data form a causal association model, a traceable decision basis is provided for accurate reproduction of an endangered process, and meanwhile, the intelligent contract can automatically execute a decision to ensure high efficiency and transparency of the decision process.

This document discloses methods and systems for cohort identification. The methods and systems include improved calculations to perform cohort identification and practical applications of the improved calculations. Specifically, the systems and methods described herein may utilize key components that include enhancements of existing cohort clustering techniques with regard to selecting a number of cohort input dimensions, normalizing input data using a logarithm kernel-function, treatment of categorical data with mutually exclusive and not-mutually exclusive values, methods and visualization tool to determine appropriate number of cohorts, methods and visualization tool to compare cohorts extracted from different input dimensions, and methods to quantify the difference in cohorts. Beyond improvements to the cohort clustering techniques, also disclosed are ancillary tools to prepare input data by joining CRM and product usage data and facilitate subsequent automated action via an API to retrieve cohort results.

The invention discloses a resource dynamic allocation method and system under a micro-service architecture, relates to the technical field of resource allocation, and aims to overcome the defect that an existing dynamic resource allocation scheme cannot meet operation requirements of micro-services, and the adopted scheme comprises the following steps: acquiring resource use data in a service operation process in real time; cleaning and filtering the collected data of the data collection module to generate a standardized time sequence data set; for the time sequence data set, analyzing a resource use trend and predicting a future resource demand by adopting a time sequence model, and then generating an elastic capacity expansion and contraction suggestion in combination with a preset service priority rule to provide data support for subsequent resource scheduling; and on the basis of the elastic capacity expansion and contraction suggestion, carrying out actual allocation operation on the resources in combination with a pre-formulated resource allocation strategy. According to the method, the resource use condition of the micro-service is monitored in real time, and a scientific and reasonable dynamic adjustment strategy is combined, so that flexible allocation of resources is realized.

Techniques for managing cloud computing resources hosting burstable performance instances are described. A host computer system of a provider network executes burstable performance compute instances. Compute capacity usage data is obtained from the host computer system, the compute capacity usage data including a first indication of a first compute capacity used by a first burstable performance compute instance. A first weight for the first burstable performance compute instance is calculated, the first weight being inversely related to the first compute capacity. A scheduler of the host computer system is updated with process prioritization weights, the process prioritization weights including a first process prioritization weight that is based at least in part on the first weight. The scheduler allocates compute capacity based on the process prioritization weights.

Disclosed herein is an extended reality system, and associated techniques, whereby personalized usage data of a user in one or more extended reality environments over a period of time can be collected and provided to a predictive model to determine optimal shortcut assignments for presentation to and subsequent use by the user. Determining the optimal shortcut assignments can involve estimating a plurality of interaction times for the user in the one or more extended reality environments, generating an optimized graphical user interface within the one or more extended reality environments with the optimal shortcut assignments reflected in the optimized graphical user interface, and rendering the optimized graphical user interface in the one or more extended reality environments to the user. The system may collect additional personalized usage data and periodically update the optimal shortcut assignments based on ongoing use of the system by the user.

The embodiment of the invention discloses a hard disk fault prediction method and device, electronic equipment and a storage medium, and relates to the technical field of reliability of data storage systems.The method comprises the steps that hard disk data are obtained, data cleaning and feature selection are conducted on the hard disk data to obtain feature data, and the feature data are stored in a database; performing standardization and normalization on the feature data to obtain a data set, using a long-short term memory network as a deep learning model, designing a model structure, introducing a regularization technology and a dropout layer to construct an initial model, training and optimizing the initial model by using the data set to obtain a trained prediction model, and performing prediction on the trained prediction model. And performing state monitoring, fault early warning and maintenance on the hard disk by using the prediction model. According to the method, efficient and accurate hard disk state monitoring, fault early warning and maintenance are achieved through data preprocessing and the LSTM network deep learning model, and the problems that in the prior art, changes of the running state of the hard disk cannot be accurately captured, and data loss and system crash cannot be prevented are solved.

Systems and techniques for are described herein. A natural language input is received that requests a data update via a user interface. The input is evaluated using AI and a large language model to determine update intent. A data update policy is selected and an update command is generated. A virtual data container is created with a subset of data, where the update is executed. The modified data is displayed for user review. Upon confirmation, the update is executed in the main data structure and the virtual container deleted.

The invention relates to the technical field of task scheduling, in particular to a container computing-oriented dynamic scheduling system and method, and the system comprises a resource state modeling module which obtains CPU, memory and network bandwidth parameters and analyzes multi-node resource characteristics based on resource use data of nodes in a container cluster. According to the invention, through dynamic resource modeling, analysis of probability change of multi-node resources and accurate prediction of resource fluctuation, a scheduling system can rapidly deal with dynamic resource adjustment, real-time resource comparison is combined, refined load optimization and reallocation are executed, global resource balance is enhanced, resource waste and node overload conditions are avoided, and the scheduling efficiency is improved. In the task scheduling process, matching is carried out based on the priority of tasks and resource multi-dimensional data, scheduling intelligence and high efficiency are ensured, loads are monitored in real time, task distribution is flexibly adjusted, the loads are prevented from being concentrated in a few nodes, task migration among the nodes is optimized, the bottleneck is eliminated, and the system stability and the overall performance are remarkably improved.

A method by a first node (111) for handling data. The first node (111) obtains (204) one or more first sets of data corresponding to one or more first features used in a first predictive machine learning, ML, model. The data is annotated with an indication. The indication indicates a respective representation of a distribution of the data. The obtaining (204) is performed before the data are used to train the first ML model. The first node (111) determines (205) whether there has been a change in a respective representation of the distribution of the data, before the data are used to train the first ML model. The first node (111) determines (206) whether to send the data and sends (207) a second indication of the data to a third node (113) in response to the determining (206).