1083 results about "Usage data" patented technology

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.

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.

Systems and methods are disclosed herein for compressing a prompt. In an example system, an importance score listing is obtained that includes a score indicative of an importance of a plurality of dataset keywords. From the importance score listing, a keyword importance score is identified for a plurality of keywords in a current text fragment, such as a text fragment to be compressed. A set of placeholders in an abstract prompt template is populated based on the current text fragment. The current text fragment is compressed based on the importance of the plurality of keywords in the current text fragment to generate a compressed text fragment. In an example, the compressed text fragment is included in the prompt for transmission to a computing entity, such as a large language model of a generative question-answering system.

Systems and methods of the disclosure include: identifying, by a cloud resource management system, a cloud resource consumption model associated with one or more cloud resources; generating, by the cloud resource management system, a sequence of instructions implementing a smart contract based on the cloud resource consumption model; sending, to a distributed ledger network, the smart contract; receiving, by the cloud resource management system, cloud resource usage data associated with the one or more cloud resources; and causing, by transmitting a message reflecting the cloud resource usage data to the distributed ledger, the smart contract to be executed.

The invention provides a dynamic spectrum prediction method based on a time sequence knowledge graph, a medium and equipment. The method comprises the following steps: constructing a communication spectrum coordination knowledge graph framework structure fusing static knowledge and dynamic knowledge; constructing a knowledge embedding model based on a cyclic evolution network, and realizing semantic representation of entities and relationships thereof in an electromagnetic spectrum space; through a knowledge fusion method, static knowledge embedding and dynamic knowledge embedding are fused with historical communication node frequency data so as to realize feature interaction of a static knowledge graph and a dynamic knowledge graph, and features of communication nodes in a frequency domain are extracted at the same time; constructing a space-time diagram convolutional neural network model, extracting space correlation characteristics between nodes, capturing a time evolution rule of node attributes, and dynamically predicting communication frequency; according to the method, the characteristics of the communication node frequency are effectively extracted from the communication semantic relationship, and the prediction precision of the communication frequency is remarkably improved.

The invention discloses an enterprise-level cloud computing resource dynamic allocation and management system and an implementation method thereof, and relates to the technical field of computing resource management. According to the invention, cloud resource use data is collected and processed in real time through the resource state sensing and preprocessing module, and a load change rule is accurately extracted in combination with the load analysis and period detection module, so that intelligence and adaptive adjustment of resource allocation are realized, and the resource utilization efficiency and the service response speed are remarkably improved; meanwhile, by recording an operation log, generating a trust certificate and dynamically adjusting the access authority, the credibility and transparency of the resource allocation process are enhanced by using a block chain technology and a zero-knowledge proof protocol, and data tampering and trust crisis are effectively prevented.

The invention relates to the technical field of Internet of Things data management, in particular to an intelligent terminal identity authentication and data security management method, system and device based on a block chain and a medium, and the method comprises the steps: generating a unique identity label and a public and private key pair of an intelligent terminal device, a fog node and a user, packaging a digital certificate, and writing the digital certificate into a block chain network; the intelligent terminal equipment initiates a registration request, and the blockchain network distributes a hosting fog node to the intelligent terminal equipment after verification is passed; the intelligent terminal device generates data, constructs a data fingerprint, sends the data fingerprint to the block chain network for storage, encrypts the data, and sends the data to the hosting fog node for storage; a user initiates an authentication request, and a temporary access token is generated after verification is passed; and establishing a secure communication channel by using the temporary access token, obtaining the required encrypted data stored by the fog node, decrypting to obtain the required data, and verifying the integrity of the required data by using the data fingerprint. According to the invention, the overall security and reliability of data management of the Internet of Things system can be significantly improved.

The invention provides a charging pile cluster power coordination method, device and equipment and a storage medium, relates to the technical field of charging pile optimization, and is applied to a charging pile power distribution system which comprises a plurality of charging piles. The method comprises the following steps: acquiring current state data, historical use data and position data of each charging pile in different time periods, and determining corresponding priority weight data according to the position data and the historical use data; based on a preset prediction model, obtaining use probability data of the corresponding charging pile according to the historical use data and the corresponding current state data; obtaining corresponding power reference data according to the power grid dispatching plan data, the current state data and the use probability data; and obtaining a power adjustment strategy of each charging pile according to the current state data, the priority weight data and the power reference data based on a deep reinforcement learning model. According to the method, the prediction model and the deep reinforcement learning technology are combined, and intelligent and efficient power coordination is realized.

A method can include rendering a graphical user interface to a display; receiving data; responsive to determining boundary locations for formations in the subsurface environment using the data, automatically rendering the boundary locations in the graphical user interface; responsive to determining extended boundary locations in the subsurface environment for a region beyond an end of the borehole using the boundary locations, automatically rendering the extended boundary locations in the graphical user interface; responsive to determining a target location in the region using the extended boundary locations, automatically rendering the target location in the graphical user interface; and, responsive to generation of a trajectory from an end of the borehole location to the target location, automatically rendering the trajectory in the graphical user interface.

System and methods are provided for achieving data standardization and normalization through an Agnostic Data Format (ADF) architecture. ADFs systems and processes provide a transformative bridge, enabling disparate data sources to converge into a unified and standardized format within the Real-Time Data Mesh (RTDM) framework. This dynamic process utilizes Artificial Intelligence (AI) and Machine Learning (ML) algorithms to interpret and align diverse data attributes. The ADF management system, integrated into a dynamic event-driven architecture, allows vendors to interact with RTDM by translating and standardizing their data. The synchronized data integrates canonically, incorporating real-time updates and collaborative decision-making across the distribution platform. This innovative approach enhances operational efficiency, enables data-driven decision-making, and provides users improved ability to use data within the distribution ecosystem.

The invention discloses a mobile phone data line performance test and fault prediction method and system, and belongs to the technical field of electronic product detection and fault prediction. The power-on resistance, the voltage stability, the charging current response and the data transmission rate of a target data line are collected, and under the conditions of different bending angles, insertion and extraction cycles and environment temperatures, the data transmission rate of the target data line is calculated; acquiring stress response data, and extracting multi-dimensional stress principal component characteristics; the electrical property and stress data are fused, a performance degradation correlation model is established, and coupling modeling of data line internal structure damage and electrical property degradation is achieved; historical use data are input, analogue simulation is carried out through the model, and residual performance indexes are generated; judging whether a fault risk exists or not according to a set threshold value, and outputting early warning information if the fault risk is lower than the threshold value; meanwhile, a fault position and a mode type are inferred in combination with an internal characteristic spectrum of the model; the method has high prediction precision, strong structural adaptability and good expansibility, and is suitable for quality control and intelligent diagnosis of consumer electronic cable products.

The invention relates to the technical field of computers, in particular to a containerized scene fault prediction and self-healing method and device, equipment and a storage medium. The containerized scene fault prediction and self-healing method comprises the following steps: obtaining resource use data related to a container in real time by using a sliding window, carrying out noise filtering on the resource use data, generating time sequence characteristics, and obtaining preprocessed data; analyzing the preprocessed data by adopting an isolated forest model to obtain an abnormal score, and judging whether a node of the container has a fault risk or not according to the abnormal score; and carrying out corresponding self-healing operation on the fault node according to the fault type by adopting a pre-constructed self-healing strategy. By analyzing the container resource data, the fault nodes and the types of the fault nodes can be effectively identified, the self-healing operation is pertinently executed, the resource utilization rate is effectively increased, and the core service continuity is guaranteed.

The invention relates to the technical field of scientific research instrument management, in particular to an intelligent supervision method and system for a scientific research instrument, and the method comprises the following steps: extracting instrument reservation task information and constructing a timetable, collecting and analyzing control instruction abnormal behaviors to generate risk information, collecting power trend data to recognize an operation state, and carrying out management. And collecting an identity instruction and power information to construct a use record, and analyzing power fluctuation and load degree to generate a maintenance cycle evaluation value. According to the method, dynamic sorting and conflict screening of the reservation requests are realized by combining the task dependency relationship and the priority information, the risk level is evaluated by using the user instruction behavior characteristics, the real-time identification of the operation risk is realized, the accuracy of the operation state identification is enhanced by using the power fluctuation trend analysis, and the user experience is improved. A structured binding relationship of use data is established in combination with the identity and the device number, the information tracing integrity and the data tracing efficiency are improved, and the prejudgment capability of the maintenance period is optimized by using the combined evaluation of the operation load and the power trend.

Methods, systems, and apparatus for verifying quantum randomness. In one aspect a computing device receives data from a quantum computer. The data includes a timestamp, a binary-valued vector, and a predicted response to a challenge string. The predicted response to the challenge string is generated using a regression model that has been trained to fit LPN instances as a linear function, where the LPN instances are constructed using a physically unclonable function. The computing device determines a parity of a random number output by a public source of randomness at a time specified by the timestamp and performs either a generation round or a test round based on the parity to verify the randomness of a bit generated by the quantum computer. The generation round uses the data to verify a preimage of the binary-valued vector and the test round uses the data to verify an equation.

The invention discloses a data fine-grained access control method, system and device and a medium, mainly relates to the technical field of access control, and is used for solving the problems of identity and attribute separation, low strategy updating efficiency and insufficient auditing capability in the existing scheme. Comprising the steps that a data user generates a distributed digital identity document containing at least one role attribute through a distributed digital identity system, and the distributed digital identity document is subjected to uplink storage after being audited by a registration mechanism; the data provider generates an ABE private key according to the main public key and an access control strategy, encrypts the ABE private key by using the DID public key of the data user, and sends the encrypted ABE private key to the data user; the data user obtains an ABE private key by using the DID private key; decrypting the ABE ciphertext on the block chain by using the ABE private key to obtain a symmetric key; and obtaining the original data in the trusted data space through symmetric key decryption.

The invention provides a timed task execution optimization method and system. The method comprises the following steps: forming a timed task execution optimization system architecture; determining a corresponding calculation factor to obtain a dynamic priority score; predicting the to-be-predicted task data by using the task prediction model to obtain a task execution time prediction value; analyzing the to-be-executed task queue, calculating the average waiting time, determining a multiple factor according to the task priority and the system load state, and identifying the task with the task execution time prediction value larger than the dynamic threshold value in the to-be-executed task queue as a long task; performing automatic fragmentation processing on the long task, generating a fragmentation result, determining a scheduling sequence based on the dynamic priority score and the task execution time prediction value, and generating a scheduling decision; and performing resource availability evaluation on the resource use data to obtain a node resource evaluation result, and allocating execution resources for the selected task. According to the method, the problems of efficiency and reliability of the timed task execution system in a high-load scene are solved.

The invention relates to the technical field of intelligent manufacturing and industrial big data application, in particular to a production and manufacturing information management system and method based on big data integration. The method comprises the following steps: carrying out multi-dimensional characteristic parameter acquisition on wood in a production and manufacturing process, and constructing a wood digital characteristic model; importing the wood digital characteristic model into an enterprise big data platform to carry out enterprise-level data integration, and carrying out distributed storage and retrieval system construction to form a wood characteristic parameter map; wood deformation data are obtained and extracted from the finished product use data, characteristic-deformation correlation analysis is conducted, and a characteristic deformation correlation table is obtained; and carrying out deformation risk analysis according to the characteristic deformation association table to obtain a wood deformation sensitivity index. According to the method, the big data system throughout the full life cycle of the wood is constructed, so that high stability and high quality of products are guaranteed from the source while the resource utilization rate is maximized.

A system, method, and computer-program product includes obtaining, via an application programming interface (API), a test object that includes application usage data of a deployed AI application for a target time span, executing, in real-time by one or more computer processors, one or more application behavior tests that assess an operational behavior of the deployed AI application, detecting, by the one or more computer processors, that a misbehavior occurred in the deployed AI application during the target time span and one or more deviant features contributing to the misbehavior in response to executing the one or more application behavior tests, and returning, by the one or more computer processors, the one or more deviant features contributing to the misbehavior to a subscribing entity associated with the deployed AI application.

Techniques for constraining the results of a generative language model to valid information using knowledge-grounded documentation. A generative language model may generate invalid results, including compound entities and incorrect entity relations. The techniques include, for a given user inquiry, determining a set of documented information, from a particular knowledge base, that corresponds to the user inquiry. The techniques further include determining a subgraph from a knowledge graph representing the knowledge base, as well as determining a trie data structure representation of the set of documented information. The user inquiry and subgraph are provided as input to a trained generative language model for generating a response to the user inquiry. The techniques include using the trie data structure to validate that the generated response corresponds to real information from the set of documented information.

The invention relates to a cross-domain few-sample fault diagnosis method based on a geometric perception coordinated penalty prototype network, and belongs to the technical field of fault diagnosis, and the method comprises the following steps: S1, dividing samples through employing vibration monitoring signals in a data set; s2, obtaining respective support sets and query sets through source domain samples and target domain samples, and generating meta-tasks used in training and testing stages; s3, extracting input sample features by using a feature extractor; s4, mining an internal geometric structure of the data by using an adaptive manifold mapping module (AMMM), and converting sample features to manifolds; s5, calculating to obtain a coordination penalty prototype HPP; s6, classification is carried out through a dynamic high-sensitivity distance DHSD, loss is calculated, model parameters are updated through back propagation, and training of the GAHPPN is completed; and S7, quickly adapting to the meta-task of the target domain through the trained GAHPPN model, and diagnosing the health state of the target domain sample.

Data retrieval via secure database query generation is disclosed, including: receiving, via a user interface, a user submitted request for data associated with a business context; generating a prompt to an initialized database query generation model specific to the business context based at least in part on the user submitted request; providing the prompt to the initialized database query generation model; determining a database query based at least in part on an output from the initialized database query generation model; and querying a database for matching data using the database query, wherein the matching data comprises a set of data values fetched from one or more tables of data.

Aspects of the subject disclosure may include, for example, accessing device usage data that can be generated when end user devices connect with the network; and analyzing the device usage data according to identification information of the deployable cell site, which enables determining or estimating a location of the deployable cell site. In one embodiment, this analysis can be based on device usage reports and network performance data. A performance report and / or location map can be generated for an area associated with the deployable cell site. Other embodiments are disclosed.

The present disclosure provides a method of facilitating intelligent budget governance for a cloud resource. Further, the method may include receiving a budget data. Further, the method may include receiving a usage data. Further, the method may include determining a group budget status based on the budget data and the usage data. Further, the method may include calculating a threshold variance representing a deviation of the group budget status from a predefined budget threshold. Further, the method may include generating a control intent data representing a scheduled action on the cloud resource based on the threshold variance and a time policy. Further, the method may include storing each of the budget data, the usage data, the group budget status, the threshold variance, and the control intent data. Further, the method may include transmitting the control intent data to the cloud account system.

The invention relates to the technical field of engineering digital management, in particular to an engineering project digital asset management method and management platform. The method comprises the following steps: performing engineering digital asset quality evaluation processing on engineering digital asset data to generate engineering digital asset quality evaluation data; performing engineering digital asset collaborative application heterogeneity feature analysis based on the historical engineering digital asset application data to generate engineering digital asset collaborative application heterogeneity feature data; carrying out the optimal distribution strategy analysis of the full-life-cycle engineering digital asset application on the full-life-cycle engineering digital asset application data through the engineering digital asset collaborative application heterogeneity feature data, and generating a full-life-cycle engineering digital asset application optimal distribution strategy; and based on the engineering digital asset quality data and full-life-cycle engineering digital assets, applying an optimal distribution strategy to execute engineering digital asset intelligent management operation. According to the invention, intelligent operation and maintenance optimization management of engineering project digital assets is realized.

In some aspects, systems and methods are described herein for determining rightsizing adjustments to a cluster of cloud servers using a multi-dimensional operating ratio. The system collects usage data from a cloud server, comprising multiple dimensions of cloud computation usage. The system then processes the usage data using a cleansing process to generate processed usage data, wherein the cleansing process comprises outlier removal and seasonality adjustment. The system compares the processed usage data against a benchmark to generate a workload metric. The workload metric corresponds to values in the multiple dimensions of the cloud computation usage, indicating a distance from the expected usage data. Based on the workload metric and using a predictive model, generating expected capacity needs. Based on the expected capacity needs, determining a set of rightsizing changes, wherein the set of rightsizing changes comprises changes to capacities of the cloud server.

The invention discloses a multi-model intelligent management scheduling method and system. The method comprises the following steps: receiving a to-be-registered model and corresponding metadata, and executing integrity check to generate an integrity check result; generating a model identifier for the to-be-registered model according to an integrity check result, and storing the model identifier into a model storage warehouse; receiving a deployment request, and extracting a target model file and target metadata according to the deployment request; selecting a target computing node according to the target metadata; configuring a running environment according to a deployment environment requirement, and combining the target model file with the running environment to obtain a container mirror image; creating a containerized operation instance based on the container mirror image, and configuring a network access endpoint; predicting the page view of the network access endpoint to obtain predicted page view data; and adjusting the number of the containerized operation instances according to the predicted page view data and the system resource use data. By implementing the technical scheme, the problems of hysteresis and lack of perspectiveness of resource adjustment based on a real-time system load are solved.

The invention discloses a resource management method and device, electronic equipment and a storage medium. The method is applied to a cloud platform and comprises the following steps: acquiring mean value sequence data of historical resource use data of the cloud platform; the mean value sequence data comprises a mean value of all virtual machine resource use data in the cloud platform at each moment; extracting trend features and periodic features of the mean value sequence data; performing data reconstruction based on the trend features and the periodic features to obtain time sequence data; loading a time sequence prediction model in the cloud platform, inputting the time sequence data into the time sequence prediction model for prediction, and obtaining a prediction result in a future preset time period; and generating early warning information under the condition that the prediction result meets the early warning condition. According to the resource management method and device, the future trend of resource use data is predicted, the resources are managed in time, the problem that the system cannot respond in time when the service load is suddenly increased is solved, and the flexibility of resource management is improved.

The invention provides a cluster scheduling method and system, and relates to the technical field of cloud computing, the cluster scheduling method comprises the following steps: collecting resource usage data of each node and Pod, the Pod running on the node, and the resource usage data being used for representing the usage conditions of a memory and a CPU; in response to a Pod scheduling request, determining a resource estimated usage amount of a Pod to be scheduled, a resource usage amount of each node and a total amount of distributable resources of the nodes according to the resource usage data, and screening a first set of the nodes of which the resource usage rates are lower than a first usage rate threshold according to the three, and screening a second set of the nodes of which the newly-built offline Pod data does not exceed a threshold value of the number of the newly-built offline Pods in the first set. The cluster utilization rate can be improved, and the scheduling stability is ensured.

An autonomous machine learning (ML) system and methods are provided that are configured to intelligently cluster categorical data based on embeddings created by prompting a large language model (LLM). The system includes a processor and a computer readable medium operably coupled thereto, the computer readable medium comprising a plurality of instructions stored in association therewith that are accessible to, and executable by, the processor, to perform embedding generation operations which include accessing a data set for categorical data, determining a row of the data set, generating a data container corresponding to the row and an instruction to the LLM that requests an embedding for the row, prompting the LLM to create the embedding using the data container, reducing a dimensionality of the embedding, and outputting the reduced dimensionality embedding to an ML training application executing for training an ML clustering model.

The invention relates to the technical field of inventory optimization, in particular to a multilevel guarantee-based maintenance resource optimization method, which comprises the following steps of: determining a resource allocation quantity based on a guarantee system and a guarantee resource total number, and determining a maintenance function of each base station in combination with spare part historical use data; determining the annual average demand quantity of the superior replacement unit based on the base-level replacement unit, and further determining a superior supply channel mean value and a superior expected stockout number; determining a basic-level supply channel mean value and a basic-level expected stockout number based on the annual average demand quantity, the maintenance function and the superior expected stockout number so as to determine the availability of each basic-level equipment and the total availability, and constructing a resource allocation optimization model based on the total availability and the resource allocation quantity. And performing calculation based on the model to obtain the maximum total availability, the maintenance resource allocation quantity and the inventory configuration. According to the method, dynamic allocation of resources can be guaranteed, and the problem of marginal effect decline existing in single-way improvement is solved, so that the availability level is improved.