57 results about "Real world data" patented technology

Various examples relate to translating image labels from one domain (e.g., a synthetic domain) to another domain (e.g., a real-world domain) to improve model performance on real-world datasets and applications. Systems and methods are disclosed that provide an unsupervised label translator that may employ a generative adversarial network (GAN)-based approach. In contrast to conventional systems, the disclosed approach can employ a data-centric perspective that addresses systematic mismatches between datasets from different sources.

Systems and methods for generating simulation data based on real-world dynamic objects are provided. A method includes obtaining two- and three-dimensional data descriptive of a dynamic object in the real world. The two- and three-dimensional information can be provided as an input to a machine-learned model to receive object model parameters descriptive of a pose and shape modification with respect to a three-dimensional template object model. The parameters can represent a three-dimensional dynamic object model indicative of an object pose and an object shape for the dynamic object. The method can be repeated on sequential two- and three-dimensional information to generate a sequence of object model parameters over time. Portions of a sequence of parameters can be stored as simulation data descriptive of a simulated trajectory of a unique dynamic object. The parameters can be evaluated by an objective function to refine the parameters and train the machine-learned model.

The invention provides a scene text image super-resolution method based on mixed prior. The method comprises a hybrid prior extraction module (HPE), a degradation perception branch utilizes a constraint enhancement mechanism to capture a structure degradation mode specific to a text image, and a semantic text branch utilizes cross-modal fusion to align semantic and visual features; the feature fusion module (MFM) is used for fusing image features and prior knowledge; according to the knowledge distillation strategy, the teacher network extracts rich structure and semantic features from a high-resolution image, and the student network predicts fine-grained feature representation through hierarchical constraint learning. According to the method, the problem of low utilization efficiency of structure and semantic information in the super-resolution process is solved. Wide experiments on a TextZoom data set, a real world data set and four identification benchmark test data sets show that the super-divided text image has clearer textures and structures, and the objective indexes of the method are superior to those of most existing methods.

The invention discloses an internal medicine drug curative effect evaluation method based on big data analysis of an electronic health record, and the method comprises the steps: extracting basic health data, diagnosis and treatment time sequence data and drug intervention data from the electronic health record, and carrying out the time-space alignment to generate a dynamic feature set; subgroups are obtained based on disease typing standard hierarchical clustering, and historical data and real world data are fused through transfer learning to construct a subgroup curative effect reference matrix; collecting data after medication in real time, and generating an evaluation vector containing short-term physiological response, middle-term symptom improvement and long-term prognosis risk through deep learning; dynamically matching the evaluation vector with the reference matrix, and introducing an individual weight coefficient to correct deviation; taking the deviation correction value as input, constructing a self-adaptive evaluation model through reinforcement learning, and performing iterative optimization; and generating an individualized report containing the curative effect level, the medication suggestion and the risk early warning, and quantifying the curative effect level through a fuzzy comprehensive evaluation method. According to the method, individual differences are accurately captured, full-cycle dynamic evaluation is realized, and the curative effect evaluation accuracy and the clinical decision-making efficiency are improved.

The invention provides a road network trajectory generation method and system based on pre-training, and a medium. The method comprises the following steps: S1, carrying out pre-training based on simulation data to obtain a pre-trained autoregression Transform model; step S2, based on real data, carrying out fine adjustment on the auto-regression Transform model after pre-training; and S3, generating a road edge trajectory through autoregressive reasoning by the finely adjusted model. According to the invention, a large amount of data generated by a simulator is used for training and generating a model, and then the model is aligned with observation results of the real world. The generative model provides a higher fidelity than a simulator. Different from a model which only depends on real world data, the method is more effectively popularized to the road network of the whole city range. Besides, as long as a simulator running on the urban road network can be accessed in the pre-training step, a trajectory generation model can be pre-trained for the city, and the trajectory generation model is used as a basic model further aligned with a real world observation result.

Artificial intelligence (AI) / machine learning (ML) model drift detection and correction for robotic process automation (RPA) is disclosed. Information is analyzed pertaining to input data for an AI / ML model to determine whether data drift has occurred, analyze information pertaining to results from execution of the AI / ML model to determine whether model drift has occurred, or both. When, based on the analysis of the information, a change condition is found, a change threshold is met or exceeded, or both, the AI / ML model is retrained. The retrained AI / ML model may then be deployed to provide better predictions on real world data.

Disclosed is a method for managing digital twins of a plurality of physical assets. The system comprises a digital platform, database and a plurality of processors. The processors import real world data from the physical assets to the database, process the real world data to generate calibration data, map a plurality of digital twins to the digital platform, each digital twin for simulating a corresponding physical asset, predict simulation data by the digital twins, compare the simulation data with the calibration data to assess performance of the digital twins, determine a set of low-performance digital twins based on the performance of the digital twins, and apply an optimization model to update the digital twins.

The invention relates to the technical field of automobile intelligent driving, in particular to an intelligent network connection automobile digital twinning evaluation method and system for extreme scenes. The evaluation method comprises the following steps: constructing a knowledge graph; generating an extreme scene; the automatic driving system is tested in a virtual environment generated by the digital twin test platform based on an extreme scene; predicting a safety risk score in real time, and if the safety risk score exceeds a safety threshold, sending an intervention instruction to the digital twin test platform; performing anomaly detection on the full-quantity test log, deriving a scene and injecting the scene into a scene library if a performance inflection point is found; and calculating a root cause based on the weight vector, the system fault cause and effect graph and the test data, and generating a diagnosis result. According to the method, extreme scenes can be covered, the system can be scored from multiple dimensions, the performance bottleneck can be accurately positioned, and the closed loop of the test scene can be realized. According to the system, two-way closed loop and common evolution of physical test data and a virtual test environment are realized through a cloud side end architecture, and continuous synchronization and two-way interaction with real world data are realized.

Embodiments of the present disclosure relate to region partitioning with unit merging using a spanning tree. Location-based parallel reality games may use regions to determine how to disperse virtual elements, locate a virtual experience, and / or define game goals. To determine a region of a geographic region, a server divides the geographic region into cells. The server allocates real-world data to each of the cells, and constructs a graph of nodes and edges based on the cells. Each node corresponds to a cell, and each edge connects nodes corresponding to adjacent cells. The server segments the graph into contiguous segments based on the real-world data. The server defines a region of the geographic region based on the contiguous segments and stores the defined region in a data store. The server may hierarchically segment the region into higher order regions until each region satisfies a standard set.

The application discloses a prognosis risk prediction model construction system and method based on chronic disease real world data, comprising a multi-source real world data acquisition and access module, a data standardization and quality control module, a multi-dimensional feature engineering and screening module, a comorbidity feature fusion and data set construction module, a prognosis risk prediction model training and optimization module, a model multi-dimensional verification and evaluation module, a model deployment and risk stratification output module; a special multi-source real world data acquisition and quality control system for chronic liver disease, diabetes and hypertension is constructed, data standardization processing is realized in combination with a chronic disease clinical diagnosis and treatment guideline, through multi-dimensional missing value, abnormal value processing and data deduplication integration, the quality and availability of the real world data are effectively improved, the core problem of disorderly and low-quality real world data in the prior art is solved, and a high-quality data source basis is provided for model construction.

A system includes a user device that can be used by a user to enter a virtual environment and at least one processor coupled to the user device. The processor is configured to record a plurality of real-world data interactions performed by the user and determine a real-world behavior of the user based on the recorded data interactions. The processor receives a request by the user to perform a data interaction in the virtual environment. The processor verifies whether the requested data interaction is in accordance with the recorded real-world behavior of the user. When the requested data interaction is not in accordance with the real-world behavior of the user, the processor verifies the data interaction in the real-world environment and allows the user to perform the data interaction in the virtual environment upon successful verification of the data interaction.

Examples including a system described herein implement a novel liquid time constant neural network (LTC-NN) based architecture to recover an underlying model of physical dynamics from real world data. The automatic differentiation property of LTC-NN nodes overcomes problems associated with low sampling rate, the input dependent time constant in the forward pass of the hidden layer of LTC-NN nodes creates a massive search space of implicit physical dynamics, the physics model solver based data reconstruction loss guides the search for the correct set of implicit dynamics, and drop out in dense layer ensures extraction of the sparsest model. Further, to account for perturbation timing error, the LTC-NN based architecture of the system utilizes dense layer nodes to search through input shifts that results in the lowest reconstruction loss.

The invention discloses a medical instrument adverse event recognition method and system based on real world data, and relates to the technical field of monitoring analysis, and the method comprises the steps: data input and paragraph analysis, obtaining of medical text data input by a target user, preprocessing of the medical text data, and obtaining of medical instrument adverse events. Performing text structure and paragraph analysis on the processed medical text data, and identifying text content data corresponding to different stages; carrying out adverse event entity identification, carrying out entity identification on the analyzed text content data, and confirming medical entity data corresponding to a target user; adverse event extraction: extracting perioperative period adverse events according to the medical entity data corresponding to the target user; and similarity matching and filtering: matching the perioperative period adverse events with preset dictionary set entries so as to confirm a similarity evaluation coefficient, comparing the similarity evaluation coefficient with a preset similarity evaluation threshold, and outputting an identification result based on a comparison result. The method has the effect of improving recognition.

The present disclosure relates to a method and apparatus for providing an off-label indication in an off-label indication provision system, and the method for providing an off-label indication may include collecting real world data from health care big data, collecting drug-related information, converting the drug-related information and the real world data to international standard terms, generating relationship information by analyzing an indication relevant to an active ingredient based on the drug-related information and the real world data that are converted to the international standard terms, filtering an indication with low relevance to the active ingredient from the relationship information, and providing an off-label indication based on the filtered relationship information.

The application discloses a follow-up content processing method, system, storage medium and electronic equipment. The hospital data of a patient is obtained through a preset follow-up mode, the hospital data and the hospital data obtained in advance are integrated through a preset integration mode, multi-dimensional patient health data is obtained, the multi-dimensional patient health data is used for representing multi-dimensional patient health data in a real world environment in a complete follow-up cycle, and a corresponding scientific research report is generated according to the multi-dimensional patient health data. Based on the above, the follow-up mode of online consultation dialogue, intelligent follow-up, telephone follow-up, incentive follow-up and the like is supported in the follow-up process of the patient who leaves the hospital, the doctor and the patient are facilitated to communicate, the electronic medical records, scientific research follow-up records, home equipment data and the like of the patient outside the hospital are integrated to form complete real world data and generate a scientific research report, the doctor is provided with scientific research and clinical decision support, the clinical data management efficiency is improved, and the scientific research implementation cost is reduced.

Location-based parallel reality games can use regions to determine how to disperse virtual elements, position virtual experiences, and / or define game objectives. In order to determine the regions of a geographic region, the server divides the geographic region into cells. The server assigns real-world data to each of the cells and builds a graph of nodes and edges based on the cells. Each node corresponds to a cell, and each edge connects nodes corresponding to adjacent cells. The server divides the graph into continuous segments based on the real-world data. The server defines regions of the geographic region based on the continuous segments and stores the defined regions in a data repository. The server can hierarchically divide the regions into higher-order regions until each region meets a set of criteria.

The invention discloses a dual-channel multi-scale network traffic anomaly detection method, and belongs to the technical field of network security. Aiming at the problem that an existing method cannot comprehensively analyze time and space features of network traffic to carry out anomaly detection, firstly, all features of network traffic data are divided into space features and time features, the space features are extracted and expanded through hole convolution of multiple different scales, space information in different distances is captured, and the time and space features are extracted and expanded through hole convolution of multiple different scales; the outputs of a plurality of dilated convolution blocks are combined, fusion is carried out through a full connection layer and time features, the time features distribute different weights for each time step in a sequence through BIGRU modeling time sequence dependency, an attention mechanism, and capture of important time sequence features is enhanced; then fusion of the two channel features is completed through a fusion layer; and finally, mapping to an output space through a linear layer, and generating probability distribution of each category. Experimental results show that a good result is obtained on a real world data set.

To support efficient use of RWD (RealWorldData).SOLUTION: The computer system is accessibly connected to a first database that stores clinical data acquired at a clinical site and including information on a treated patient as an item, and a second database that stores non-clinical data acquired for research purposes and including information on a treated patient group as an item. The computer system selects a predetermined number of pieces of clinical data from the first database, generates comparison data by aggregating the selected pieces of clinical data, executes statistical analysis for analyzing a difference between items using the non-clinical data and the comparison data having the same treatment content, and records a result of the statistical analysis.SELECTED DRAWING: Figure 9

Disclosed is a method (100) and a system (200) for generating test scenarios to validate the behaviour competencies of autonomous vehicles. The method involves receiving a behavioural competency defined in natural language pertaining to a given operation of the autonomous vehicles. This competency is parsed into objects, representative of the Operational Design Domain (ODD), and events, representative of the Object and Event Detection and Response (OEDR). These objects and events are then transformed into a data structure (300). Subsequently, this data structure is mapped to a hierarchy of search queries representing relationships and interactions among the objects and events. The hierarchy of search queries is provided to a scenario extraction tool (10), which leverages the hierarchical queries, extracts relevant scenarios from real-world data, to validate behaviour of the autonomous vehicles for the given operation thereof.

The application discloses a cold start user recommendation method, system and device based on heterogeneous transfer learning, which comprises the following steps: using feature enhancement technology to combine source domain and target domain data into an enhanced matrix, then using an autoencoder to map the enhanced matrix to a latent feature space, performing feature matching and distribution alignment processing in the space, and finally reconstructing user features. Then, a solving model is established according to the reconstructed user features, that is, the solving model can be solved through matrix feature decomposition, thereby improving the recommendation accuracy for cold start users. In addition, the application also extends the model to a neural network, and the effectiveness of the model is verified through experiments on multiple real world data sets, and the performance index is excellent. The application can effectively utilize auxiliary source domain information to assist the recommendation task of the target domain, thereby providing more accurate and personalized recommendations for cold start users.

The application discloses a point of interest check-in sequence generation method based on a diffusion model, and belongs to the technical field of spatiotemporal data mining and deep learning. Data preprocessing is performed to clean and smooth a real world data set, so as to ensure data quality and consistency. Spatiotemporal lossless coding is performed to convert check-in sequences of different lengths into check-in vectors of equal lengths, and the original sequence information is retained by coding through a spatial frequency vector and a time bucket vector. A diffusion model is established to construct a spatial diffusion module and a time diffusion module, and spatiotemporal features are captured by using a forward diffusion process and a backward reconstruction process. A conditional U-shaped network is introduced into the diffusion module, and a denoising network is proposed to capture complex spatiotemporal correlations by modeling through a self-attention mechanism. A contrast learning strategy is used to further capture the spatiotemporal correlations of the check-in sequence by using ternary contrast learning, and the connection between the time and space diffusion modules is strengthened.

The invention discloses an intersection pedestrian-left-turn vehicle conflict risk factor quantification method based on causal machine learning. The method specifically comprises the following steps: 1, extracting pedestrian-left-turn vehicle conflict data; 2, matching the pedestrian-left turning vehicle conflict data with a signal control type Ttype and a safety influence factor; 3, constructing a directed acyclic graph; 4, on the basis of a directed acyclic graph, using a dual robust learning algorithm to construct causal inference models under different signal control types, and mining factors related to pedestrian-left turn vehicle conflicts from safety influence factors as conflict risk factors; and the heterogeneity causal effect of different signal control types on the pedestrian-left turn vehicle conflict risk is estimated. According to the method, confusion factors can be effectively identified and processed, and the robustness and generalization ability of the model facing real world data are improved.

A system for AI-augmented, metaverse-integrated dynamic training and operational visualization. Dynamic safety simulations are provided in a virtual environment. The simulations are based on real-world data and adapt over time using machine learning. The safety simulations may provide safety training scenarios for the oil, mining or construction industries. The simulations may include digital twins of oilfield equipment. Preferably, hazard scenarios are generated from historical and real-time data. Real-timed operational data can be collected by IoT devices, processed by AI, and visualized in a VR / AR / XR metaverse environment. A metaverse-based remote collaboration tool allows teams to interact and collaborate in a shared virtual environment. Regulatory compliance training is delivered within the metaverse, including virtual scenarios based on legal and environmental guidelines. Training results and operational data are stored and managed securely using blockchain technology.

The invention provides a method and a system for constructing a clinical knowledge graph based on real world data. The method comprises the following steps: acquiring electronic health archives, medical insurance data, medical literatures, medical equipment data, patient report outcome and public health data, and carrying out cleaning, desensitization, medical term code mapping and structured conversion on the data; schema adaptive to the clinical field is designed, and entities and core relations of patients, diseases, drugs, symptoms, inspection and treatment schemes and the like are defined; entity, relation and attribute extraction is carried out by adopting a rule method in combination with machine learning, and knowledge fusion is completed through entity alignment, confidence fusion and conflict resolution; and the fused knowledge is stored in a knowledge base, and hidden knowledge is reasoned and mined by adopting rules, embedding or a graph neural network, is finally used for clinical decision support, drug alert and disease research, and is continuously updated along with new data and user feedback, so that the quality and practicability of the graph are improved.

A system and method for providing multi-source, real-time, and context-aware real-world data for machine learning algorithms in artificial intelligence applications, including providing a server and connecting the server and multiple interconnected elements therebetween via a network. Each connected element includes one or more sensing mechanisms. The server includes a memory and a processor. The memory stores a persistent virtual world system, including virtual copies of real-world entities created and edited via a virtual copy editor and updated with multi-source sensing data captured by the sensing mechanisms. Each virtual copy includes data and instructions of the multi-source sensing data. The processor can be set to prepare the data to generate a machine learning data set, then execute a machine learning algorithm on the data set, while generating a trained machine learning model for overall inference of new data and optimizing a system with new world entities.

The invention discloses a personalized robust recommendation defense method based on a dynamic reward mechanism, and the method comprises the steps: obtaining a real world data set related to a recommendation system, carrying out the cleaning of the data set, filtering invalid interaction data, retaining an effective user-article interaction pair, carrying out the normalization of scoring data, and dividing the scoring data into a training set, a verification set and a test set; constructing a robustness and fairness dual-objective influence evaluation mechanism, and quantifying an influence value of each user-article interaction sample on the model; the disturbance resisting amplitude is dynamically adjusted according to different user behavior characteristics; designing a reward mechanism integrating embedded interaction, behavior similarity and optimal batch, and guiding the model to dynamically balance defense and recommendation quality; and based on the filtered data set, training a model in combination with personalized adversarial disturbance and a multi-dimensional reward function. According to the method, pollution of poisoning samples to the model is effectively reduced, the adaptability of the model to heterogeneous user behaviors is improved, the attack resistance of the system is remarkably enhanced, and the method has wide applicability and practicability.

The application discloses a kind of chronic disease auxiliary drug curative effect evaluation and personalized recommendation method, comprising the following steps: step one: real world data acquisition, step two: data standardization and annotation, step three: curative effect evaluation model construction, step four: patient population stratification, step five: personalized drug recommendation, step six: data update and model iteration;The application is aimed at the clinical characteristics of three kinds of chronic diseases, liver disease, diabetes and hypertension, and constructs a multidimensional real world database and a targeted curative effect evaluation model, realizes the personalized and accurate recommendation of the auxiliary drug of the three kinds of chronic diseases, breaks through the limitation of single disease drug recommendation, effectively improves the clinical curative effect of auxiliary drug, reduces the risk of adverse drug reactions, and provides scientific support for the clinical rational use of drugs for the three kinds of chronic diseases.

The invention provides an electric power data virtual acquisition method based on a stochastic differential equation, and the method constructs a diffusion model network structure with a continuous time distribution modeling capability aiming at the problem that data missing is easy to occur in a new energy load data acquisition process. The method comprises the following steps: firstly, masking an input sequence through a random mask strategy in a training process so as to simulate a potential data missing scene, and carrying out supervised training on observed data; and then accurate virtual acquisition of missing values is realized through learning conditional probability distribution. On the basis, a stochastic differential equation (SDE) is adopted, noise is slowly injected, complex data distribution is smoothly converted into known prior distribution, and reverse time SDE of a time correlation gradient field which only depends on disturbance data distribution is adopted, and the prior distribution is converted into data distribution by slowly removing noise. Experimental verification on two real world data sets shows that the method is superior to an existing method in the aspect of virtual acquisition accuracy, and the superiority of the method is proved.

Methods and systems are provided for digitally replicating a real-world infrastructure to simulate the behavior of a real-world object, the methods and systems supporting the ability to extend a wireless network by providing services implemented in the network, and supporting optimization of network usage and digital representation accuracy. In one embodiment, the method includes instantiating one or more digital representation (D-Rep) instances corresponding to a digital replica of the real world object included in the real world infrastructure to form a digital infrastructure (D-Inf), and generating one or more digital representation (D-Rep) instances corresponding to a digital replica of the real world object included in the real world infrastructure. The method further includes providing a communication plane to provide a service to the D-Inf. The method further includes connecting to the real world object using the communication plane to collect real world data defining a state of the real world object, and associating the real world data with the D-Rep instance; the behavior of the real-world object is simulated by the D-Rep instance using a simulator that can be accessed by the D-Inf instance using the communication plane.

To provide a system capable of optimizing events to increase the number of smart phones acquired by mapping real world data into digital space and simulating sales forecasts, effective measures, and event planning in a virtual space according to the market conditions of each store.SOLUTION: The system includes: means of mapping real-world data in a digital space; means of simulating sales forecasts and effective measures tailored to the market conditions of each store, and event planning in a virtual space; and means of staffing at the right times by simulating congestion level from traffic data in the virtual space.SELECTED DRAWING: Figure 1