364 results about "Active data" patented technology

The invention relates to the technical field of risk assessment, in particular to an AI enterprise financial risk dynamic assessment method and system. The method comprises the following steps: obtaining enterprise multi-dimensional financial data, operation activity data, industry environment data and macroeconomic index data, carrying out cleaning, standardization and time sequence alignment processing, and integrating the data into a financial risk assessment multi-dimensional feature matrix; constructing a dynamic weight distribution model based on the financial risk assessment multi-dimensional feature matrix, endowing differentiated weights, and generating a time sequence weighted feature vector; risk level mapping and comparative analysis are carried out on the time sequence weighted feature vectors, risk points exceeding a threshold value are identified, and feature sources of the risk points are traced; and constructing a risk conduction path map based on the risk points and feature sources thereof, simulating risk evolution trends under different intervention measures, and evaluating and generating a dynamic evaluation report containing risk early warning levels, key influence factors and intervention measure suggestions. According to the invention, the enterprise financial risk assessment efficiency can be improved.

The invention discloses an open-pit mine slope risk prediction method and system based on multi-source data, and relates to the technical field of intelligent geological engineering, and the method comprises the steps: collecting geological data, displacement monitoring data and environmental activity data of an open-pit mine slope, carrying out the preprocessing, and constructing a three-dimensional digital twinborn body; carrying out fusion calculation on the preprocessed displacement monitoring data and environmental activity data through a physical information neural network, predicting a displacement value and a stress value of the strip mine slope, and obtaining full-field physical quantity prediction data; according to the strip mine slope slip crack surface damage evolution path, the stability risk levels of the whole strip mine slope and different areas in the strip mine slope are judged, high-risk areas are positioned, and a strip mine slope risk prediction report is generated. According to the method, the damage evolution path of the slip crack surface of the strip mine slope is dynamically deduced, so that space-time continuous modeling of the damage evolution process, early recognition of the slope instability precursor and accurate insight of the risk evolution trend are realized.

The invention discloses a soil heavy metal distribution prediction method and system based on machine learning, and the method comprises the steps: obtaining topographic factor land use industrial activity data, carrying out the fusion remote sensing information processing, and determining a multi-source data set; performing standardization processing according to the multi-source data set, and performing space-time registration if the scale difference after standardization processing exceeds a preset threshold value to obtain data in a unified format; key features are extracted according to the unified format data, and a dimension reduction feature set is obtained through principal component analysis; a random forest model is constructed according to the dimension reduction feature set, parameters are optimized, and a heavy metal content prediction model is determined; inputting the sampling finite point location data into a heavy metal content prediction model, judging an industrial activity influence area, and obtaining a preliminary distribution estimation result; based on the preliminary distribution estimation result, high-resolution grid data are obtained by fusing topographic factors for the space complex region; and generating a pollution distribution diagram according to the high-resolution grid data, judging a low-prediction-precision region, and obtaining a final optimized layer.

The invention discloses a child activity data desensitization processing method and system based on differential privacy, and relates to the technical field of privacy data protection, and the method comprises the steps: carrying out the time synchronization and unit normalization of multi-source data from a wearing device and an environment sensor, and building a unified multi-dimensional time sequence matrix; then, introducing a change point detection method to dynamically segment the time series data, so that the data is divided into event segments with clear behavior semantics; a sensitivity scoring mechanism is designed, factors such as activity types, time, places and behavior frequencies are comprehensively considered, privacy risk quantification is performed on each event segment, adaptive privacy budget allocation is implemented based on a scoring result, and key protection of sensitive data segments and efficient utilization of conventional data segments are realized; after differential privacy noise is injected, time sequence consistency correction and cross-feature correlation correction are combined. Therefore, differentiated and refined protection of the child activity data is realized, and privacy protection and data availability are effectively balanced.

The invention discloses an AI-based distributed big data intelligent storage management method, and relates to the technical field of storage management. The method comprises the steps of generating an initial feature matrix by obtaining observation data of all storage devices in a distributed storage cluster, and inputting the initial feature matrix into a pre-training life prediction model to obtain residual life; equipment with the service life lower than a first safety threshold value is judged as high-risk equipment, and data of the high-risk equipment is included in a to-be-migrated source data set; the devices with the service life higher than a second safety threshold value are included into a to-be-migrated target device set; and generating a migration plan according to the source and target data sets and executing migration. By predicting the residual life of the equipment, advanced identification and active data migration of the high-risk equipment are realized, the data loss risk is reduced, and the utilization rate of the health equipment and the overall cluster storage resource efficiency are improved.

A dynamic grid allocation system for power distribution in the development of integrated circuits in the sub-five-nanometer range, wherein the system comprises the following: a placement processor unit configured to receive a synthesized netlist comprising a variety of standard cells and macros, each associated with switching activity data derived from simulation or synthesis activity profiles, and to generate a spatial cell placement arrangement by grouping cells into microzones based on activity correlation, time sensitivity, and connection proximity; a power density calculation unit coupled to the placement processor unit and configured to calculate the local power density and instantaneous current demand for each microzone based on the spatial distribution of switching operations, capacity load, and effective switching frequencies; a dynamic network generation unit coupled to the power density calculation unit and configured to generate a multilayer power distribution network with variable network topology, where the width, spacing, via density and metal layer assignment of the power network are adaptively determined as continuous functions of the localized power density and power demand calculated for each microzone; a topology control processor configured to monitor voltage drop and electromigration data obtained from signoff analyses or predictive models in real time and dynamically adjust the power grid topology parameters to ensure compliance with predefined reliability thresholds for voltage drop and electromigration; a predictive current modeling unit configured to receive historical switching and voltage data, train a predictive model for transient current peaks, and provide predictive power boost instructions to the dynamic grid generation unit before power integrity violations occur; and A feedback synchronization controller is communicatively connected to the placement processor unit and the topology control processor, whereby the feedback synchronization controller continuously exchanges updated power density information and placement constraints, so that cell placement and network topology adapt together in real time, thereby minimizing routing congestion, ensuring a uniform voltage distribution, and guaranteeing compliance with electromigration and IR drop regulations under various activity conditions.

The invention relates to the technical field of intelligent tourism management, and discloses a tourist behavior dynamic modeling method based on space-time big data, which comprises the steps of collecting and preprocessing multi-source positioning data, inputting the multi-source positioning data into a multi-source positioning fusion engine, and combining statistical optimization and deep learning model fusion to obtain a high-precision positioning model. Track reconstruction and time sequence aggregation are carried out on continuous position points of tourists based on a high-precision positioning model, a structured activity data graph is generated, activity data of the tourists at all positions are obtained, activity preference characteristics are extracted through an association rule mining and clustering algorithm, and a Markov chain and a spatio-temporal evolution model are combined to predict a tourist flow trend. And forming a flow prediction result, and generating a visual dynamic decision support by using the prediction result. According to the invention, visual and dynamic decision support is provided, the crowd congestion is relieved, and the operation safety of the scenic area is guaranteed.

The invention relates to the technical field of data acquisition and treatment, and discloses a multimodal compatible global real-time full-amount active data acquisition and treatment method, which comprises the following steps: acquiring data source connection information of a regional medical platform, identifying potential data sources in a region, and constructing a feature portrait; matching an acquisition strategy for each data source and generating an acquisition task configuration; data acquisition is carried out, data of different data forms are analyzed, and data formats are unified; performing data cleaning, standardization and quality verification; carrying out sensitive field identification, and carrying out desensitization and encryption processing on sensitive information; performing association key extraction and entity recognition disambiguation; performing multi-source data intelligent association integration; matching the classified storage strategy and carrying out persistence processing, recording a processing process and carrying out interface development; according to the method, data cleaning, standardization, quality verification and privacy desensitization are pre-embedded into an acquisition process through a streaming collaborative governance mechanism, so that integrated processing of acquisition and governance is realized.

Methods, systems, and apparatus for training a smaller machine learning model through contrastive learning. The method includes obtaining data specifying a larger machine learning model, wherein the larger machine learning model has been trained through contrastive learning; obtaining a training dataset comprising a plurality of training examples; and training the smaller machine learning model on the training dataset, the training comprising, at each of a plurality of training iterations: generating a batch for the training iteration that comprises a subset of the plurality of training examples, the generating comprising selecting the subset of training examples according to performing an active data selection procedure based on respective contrastive losses of the larger machine learning model on one or more candidate batches that each include a respective subset of training examples from the training dataset; and training the smaller machine learning model on a contrastive loss function using the batch.

The invention discloses a vehicle software upgrading information management method and device, equipment and a program product, and relates to the technical field of information management. The method comprises the following steps: acquiring upgrading information of various types of vehicle software, the system comprises a software upgrading management system file, a software upgrading project process recording file, software upgrading configuration information and software upgrading compliance information. Vehicle type authentication information and first information sharing activity data generated inside a vehicle management party and second information sharing activity data generated between the vehicle management party and an external software upgrade related party in a vehicle software upgrade life cycle; carrying out storage management on the various types of vehicle software upgrading information; and in response to the consulting request for the at least one type of vehicle software upgrading information, generating a consulting record for the at least one type of vehicle software upgrading information. The management comprehensiveness of the vehicle software upgrading information can be improved.

The invention discloses a dynamic carbon factor prediction and carbon budget management system and method based on machine learning, and the method comprises the steps: collecting activity data through a data collection terminal, and enabling the activity data to comprise energy consumption data and logistics data; performing behavior recognition and standardization processing on the collected unstructured data, and outputting structured activity data; outputting a dynamic carbon factor value by using a carbon factor prediction model based on the situational features; combining the activity data with the dynamic carbon factor, checking the total carbon emission amount, and comparing the total carbon emission amount with a preset carbon budget target or industry standard to generate a checking report; when the over-emission risk is detected, simulating different carbon reduction strategies through a carbon budget optimization algorithm, and generating an optimization suggested path; and continuously training the model by using user feedback and monitoring data, updating carbon factors and optimizing logic.

Artificial intelligence (AI) techniques for connection networking are described. A method comprises receiving an input vector by a multi-tower machine learning (ML) model for a content delivery system of a connection network system, generating a set of user embeddings from a first vector of the input vector by a first tower of the multi-tower ML model based on the activity data associated with users of the connection network system, generating a set of campaign embeddings from a second vector of the input vector by a second tower of the multi-tower ML model based on the textual description of the content delivery campaign, generate a metric based on a subset of the user embeddings and a subset of the campaign embeddings, selecting audience user identifiers based on the metric, and sending content items for the content delivery campaign to electronic devices of the audience user identifiers.

Methods, devices and monitoring systems are described that include a hub in communication with sensors that aggregate activities in an enclosure, such as a building. The hub identifies when those activities are occurring more or less often than expected and classifies the activity to piece together and learn the user's or individual's daily activity. Additional satellite devices may be added that increase the range and capacity of the sensors for collecting more information and activity within the building. In this manner, the monitoring systems use a redundant array of sensors to consistently monitor activities occurring in or around a building to create a trail and heatmap of events and activities that the monitoring system's hub classifies, verifies with other sensors, learns, and then correctly processes.

Systems and methods associated with mind / brain-computer interfaces are disclosed. Certain implementations may include or involve processes of collecting and processing brain activity data, such as those associated with the use of a brain-computer interface that enables, for example, decoding and / or encoding a user's brain functioning, neural activities, and / or activity patterns associated with thoughts, including sensory-based thoughts, determining user attention and / or intentions during interactions within virtual environment and in other applications. Consistent with various aspects of the disclosed technology, systems and methods herein include and / or involve features and functionality enabling hands-free selection of UI elements in virtual environment or on other media.

The invention discloses a termite invasion prediction method and system based on deep learning, and belongs to the technical field of pest monitoring and artificial intelligence crossing. According to the method, termite activity data at multiple monitoring points are collected, a multi-dimensional feature system including environment, time and historical activity dimensions is constructed, key features are screened by using a random forest algorithm, and the key features are input into a Ridge regression model subjected to cross validation optimization for training, so that high-precision prediction of the number of termites is realized. And constructing a dynamic prevention and control decision model in combination with a prediction result, and optimizing attractant purchase, monitoring point maintenance and emergency killing strategies by taking minimization of accumulated prevention and control cost as a target. According to the method, the problems of hysteresis and low prediction precision of a traditional monitoring method are effectively solved, a driving mechanism behind termite activity fluctuation can be accurately speculated, the short-term change trend of the number of termites can be predicted in advance, active early warning and accurate prevention and control of termite invasion are realized, and the method has remarkable economical efficiency and practicability.

An apparatus may include a policy acquisition circuit configured to interpret a set of data collection policies, each specifying at least one requested vehicle property and a policy type, including on-demand policies. A policy processing circuit may determine property request values for the requested vehicle properties. A parameter acquisition circuit may interpret vehicle parameter values based on the property request values and policy types, and discontinue evaluation of a policy upon completion of its data collection cycle. The apparatus may deactivate the fulfilled policy and, through a parameter provisioning circuit, selectively transmit vehicle parameter values in accordance with the active data collection policies.

A risk analysis system is configured to collect and monitor sensor data associated with a user to generate an insurance policy or recommend products / services that may be better suited for the user based on the user's gameplay data, fitness data, streaming data, outdoor activity data, location data, etc. The risk analysis system is configured to correlate all the sensor data and control operations of devices to discourage behavior that may increase risk of an accident or other suitable insurance liabilities.

Various methods and processes, apparatuses or systems, and media for enabling consistent access enforcement across downstream data platforms triggered via an active data catalog are disclosed. A processor implements an active data catalog; causes the active data catalog to receive metadata updates corresponding to a line of business including properties that may be used to control access enforcement across the downstream data platforms; executes a certification process to certify the metadata updates including the properties that may be used to control access enforcement; stores the certified metadata updates onto the active data catalog; updates the active data catalog with the certified metadata updates along with certification details data; and distributes the certified metadata to the downstream data platforms thereby enabling consistent access control enforcement.

The invention discloses a meeting place people flow analysis, statistics and prediction system, and relates to the technical field of intelligent people flow management, and the system comprises a face recognition verification terminal, a people flow statistics terminal, a prediction control terminal, an early warning prompt module, an emergency control module, a data storage module and a visualization module. Statistical errors caused by repeated entering and exiting are avoided, the number of people in the museum is calibrated in real time, the problems of identity confusion and insufficient precision existing in traditional manual statistics and single sensor counting are solved, the accuracy and reliability of people flow statistics are improved, and a high-quality data basis is provided for subsequent prediction and control. Historical activity data, real-time reservation information and environment variable factors are fused, a prediction model is constructed to pre-judge the peak period and the peak scale of people flow in advance, the management and control lagging risk caused by a traditional afterward response mechanism is reduced, and intelligent conversion from passive interception to active dredging is achieved in combination with a gate flow limiting and shunting guide strategy.

The invention discloses an intelligent real-time monitoring system and an early warning method for a steel structure construction process, and particularly relates to the technical field of intelligent manufacturing equipment industry process monitoring and early warning. The method is used for solving the problem that an existing early warning method based on a static digital twinborn model is high in false alarm rate or reduced in sensitivity due to long-term evolution mismatch of a model and an entity structure. According to the method, sensor monitoring data and model theoretical data are compared in real time, an abnormal fluctuation mode is recognized, and whether the abnormal fluctuation mode is derived from construction stage conversion or not is judged; when the systematic deviation is confirmed, extracting and analyzing construction activity data associated with the systematic deviation to calculate causal association strength; when the association strength exceeds a threshold value, analyzing association characteristics of the characteristic parameters and the deviation at the current construction stage; and finally, dynamically adjusting the rigidity parameter distribution of the digital twin model according to the correlation characteristic, and performing accurate safety state evaluation and early warning by using the adjusted model, thereby realizing the self-adaptive tracking of the model on the real state of the structure and improving the early warning accuracy.

The invention discloses an aging gait detection method and system based on a millimeter wave radar, and the method comprises the following steps: S10: employing the millimeter wave radar to collect the data of the activities of a human body going up and down stairs; s20, performing Fourier transform on the activity data after sampling to obtain signal frequency spectrum and target distance information; wherein the continuous Chirp signals of which the intervals are fixed values are stored as row vectors, and receiving frequency responses of targets at different distances can be obtained by performing 1D-FFT on each row; performing fast Fourier transform on a plurality of Chirp signals of the same distance unit to obtain target speed information, namely a time-Doppler graph; and S30, constructing a YOLOv11 model, constructing a data set by the time-Doppler maps, carrying out classification training by using the YOLOv11 model, carrying out batch classification prediction on the new time-Doppler maps, and finally outputting the prediction accuracy.

The application discloses a kind of teaching and learning behavior data support under causally driven dynamic organization method and system of teaching resources, and the method comprises the following steps: obtaining online teaching and learning behavior data, the online teaching and learning behavior data include teaching activity data, student learning data and online education resource information;According to the online teaching and learning behavior data, resource access dynamic time sequence causality is modeled, and the causality information of online education resource access is determined;According to the causality information, the online education resource access heat is predicted by neural network;According to the online education resource access heat obtained by prediction, the file level teaching and learning behavior data support under causally driven dynamic organization process of teaching resources is constructed, to realize the causally driven dynamic organization of teaching resources under teaching and learning behavior data support.The application can effectively improve the education user data access efficiency, and can be widely applied in the field of computer technology.

The present disclosure provides techniques for recommending targeted information. One example method includes receiving user data indicative of one or more attributes of one or more users and activity data indicating past actions by the one or more users in association with particular content items, identifying, using a first machine learning model, a topic based on the activity data, identifying, using a second machine learning model, a subset of attributes of the one or more attributes of the one or more users that are associated with the topic, generating a prompt based on the topic and the subset of attributes associated with the topic, and generating, based on the prompt using a large language model (LLM), content to provide to a user having the subset of attributes associated with the topic.

The present invention provides an information processing device, an information processing method, and a program that can encourage actions that contribute to the realization of a sustainable society. [Solution] The information processing device according to this disclosure includes data collection means for collecting an individual's activity data by receiving said activity data from another device that stores said activity data, data analysis means for analyzing the individual's implementation of sustainable behaviors, which are actions that contribute to the realization of a sustainable society, based on said activity data, and information output means for outputting information that shows the results of said analysis.

The invention provides a blue space degradation diagnosis method and system, computer equipment and a medium, and belongs to the field of ecological environment monitoring, and the method comprises the steps: obtaining a remote sensing image, climate data and human activity data of a to-be-diagnosed blue space, and extracting water body images of the to-be-diagnosed blue space at a plurality of time points through the remote sensing image; calculating a multi-class landscape form index of each grid in the water body image; clustering the water body image based on the multi-class landscape form index of each grid to obtain a blue space combination mode corresponding to each grid; inputting the climate data, the human activity data and the landscape form index into a random forest model to obtain a contribution degree; and based on the contribution degree, screening from the climate data, the human activity data and the landscape form index to obtain a water body change driving factor, and determining a degradation diagnosis result of the blue space to be diagnosed. The blue space combination mode constructed by the method can reflect the structural difference of the blue space, and the accuracy of degradation diagnosis of the blue space is guaranteed.

This invention provides a method for predicting individual mortality rates based on activity data from wearable devices, comprising the following steps: acquiring multi-source characteristic data of the target individual, wherein the multi-source characteristic data includes at least activity data and baseline characteristic data, the activity data being collected by the wearable device worn by the target individual over a continuous monitoring period, and the baseline characteristic data including at least one of demographic characteristics, health characteristics, living environment characteristics, and lifestyle characteristics; processing the activity data to calculate an average activity data feature value representing the overall activity level of the target individual; inputting the average activity data feature value and the baseline characteristic data together into a trained nonlinear machine learning prediction model, and the prediction model outputting a predicted mortality risk value for the target individual within a preset future time window. This invention integrates the average activity data feature value with traditional baseline characteristic data, enabling risk assessment to be updated synchronously with an individual's daily activity level.

A device may receive physical activity data for a subject, wherein the physical activity data comprises raw acceleration data. A device may derive a plurality of metrics from the raw acceleration data, wherein the plurality of metrics comprise a plurality of pattern-related metrics. A device may input the plurality of metrics into a deployed machine learning model. A device may be configured to perform receiving, from the deployed machine learning model, a physical activity score. A device may calculate a risk score for at least one disease or condition based on the physical activity score.

This invention relates to the field of smart fisheries technology, specifically to a visual recognition-based automatic fish feeding control method, which includes the following steps: A pan-tilt-zoom camera, equipped with an infrared / enhanced light source, is installed at a suitable location to cover the fish feeding area, continuously acquiring water surface images and videos to obtain fish feeding activity data; noise reduction is performed using mean, median, and Gaussian filters; a target detection model is selected; the fish feeding status is determined to initiate feeding operations; the decision results drive the operation of the feeding equipment; alarm thresholds are set; operation logs are recorded; and a strategy report is generated using a big data algorithm, resulting in feeding operations, monitoring footage, and the strategy report. This invention solves the problem in traditional aquaculture where the lack of effective monitoring methods makes it difficult to accurately obtain fish feeding data, hindering the achievement of intelligent and efficient aquaculture.

A system for a website, includes a processor and a unit running on the processor to capture interactions between a user of the website and at least one third party application embedded as an instance in a page of the website and to use the interactions to update a contact record associated with a user. The unit includes a data extractor to extract contact related information from the interactions; and a data merger to merge at least two contact records where the at least two contact records have an association with the same identified user and to merge the extracted contact related information to that of an existing contact record for the identified user according to predefined merging rules.