1142 results about "Real time prediction" patented technology

A real-time predictive intelligence platform comprises: receiving from a user through a meta API definitions for predictive intelligence (PI) artifacts that describe a domain of an online transaction system for least one business entity, each of the PI artifacts including types, component modules and behavior bundles; exposing an entity API based on the PI artifacts for receiving entity events from the online transaction system comprising records of interactions and transactions between customers and the online transaction system; responsive to receiving an entity event through the entity API, executing the component modules and behavior bundles to analyze relationships found between past entity events and metrics associated with the past entity events, and computing a probabilistic prediction and/or a score, which is then returned to the online transaction system in real-time; and processing entity event replicas using modified versions of the PI artifacts for experimentation.

A method and system for real-time prediction of power usage for a change to another performance state provides input data for power management decision-making processes or for display to system operators. The unit(s) for which power usage is predicted may be a single processor in a uni-processor system or may extend up to the level of facilities within a complex of processing facilities. The method and system gather real-time data on the power consumption of the unit(s) and create a model, such as a regression model, of power versus performance. A resulting power usage change required by a prospective nominal performance state change is shown as display data, or is transmitted to a power budgeting controller to inform the controller as to potential changes that can enhance system operation, such as managing tradeoffs of power allocated to various sub-units of a processing system.

An apparatus optimizes a hybrid power system with respect to long-term characteristics of the hybrid power system. The apparatus includes a real-time controller of the hybrid power system and a processor. The processor cooperates with the real-time controller and is structured to input current measurements of information from the hybrid power system and hybrid dynamics information including continuous dynamics and discrete time dynamics that model the hybrid power system. The processor provides online optimization of the hybrid power system based upon the input, and outputs a power flow reference and a number of switch controls to the real-time controller based upon the online optimization. The processor is further structured to provide at least one of: real-time forecasts or real-time prediction of future information operatively associated with the hybrid power system as part of the input, and real-time processing of the online optimization.

The invention discloses a convolutional neural network structure-based traffic flow prediction method. The method comprises the following steps of 1) establishing a traffic flow data set and preprocessing the data set: establishing the traffic flow data set according to obtained traffic flow data, preprocessing the data set, constructing a data set sample matrix, and dividing the data set into a training set and a test set; 2) establishing a single-layer conventional convolutional neural network, removing a pooling layer, constructing a feature extraction network of a road traffic flow matrix,adding a sigmoid nonlinear regression layer to a full connection layer, and constructing a road traffic flow nonlinear regression prediction network; and 3) training the convolutional neural networkand realizing real-time prediction of short-term traffic flow: defining a model objective function, taking the training set as an input of a convolutional neural network model, solving an optimal parameter of the model to finish model training, and performing real-time traffic flow prediction on the test set by utilizing the trained convolutional neural network model. The short-term prediction accuracy of the traffic flow is improved.

The invention is directed, in part, to method of using self-reported health data in online communities to predict significant health events in life-changing illnesses to improve the lives of individuals and to improve patient self-management. The invention provides a method for providing real-time personalized medical predictions for an individual patient. The method includes: providing a database containing patient information for a plurality of other patients including one or more attributes for each patient in the database; constructing a model of a disease based on disease progressions for the plurality of patients; receiving a request from the individual patient, the patient associated with one or more attributes; and making a real-time prediction for the individual patient based on the mode and the individual patient's attributes.

A system and method for maximizing the standby time of mobile communication devices that have WiFi or other high energy-consuming network interfaces, by predicting in real time actionable silent periods (ASPs) of the interface and shutting the interface down during these ASPs. Standby times are significantly increased, resulting in longer periods of operation before battery charging is required, while keeping minimal the probabilities of missing incoming data packets when the interface is turned off.

In a plasma reactor having an electrostatic chuck, wafer voltage may be determined from RF measurements at the bias input using previously determined constants based upon transmission line properties of the bias input, and this wafer voltage may be used to accurately control the DC wafer clamping voltage.

The invention relates to a wind turbine generator fault early warning method based on data mining. A method based on the minimal redundancy of maximum weight is adopted to select a fault feature signal and carry out dimensionality reduction on the fault feature signal, so that decision accuracy is guaranteed, and the calculated amount of data processing is reduced. Meanwhile, on the basis of the historical data of an SCADA (Supervisory Control And Data Acquisition) system, the early warning model of each equipment component of a wind turbine generator is established, and a nonlinear state estimation technology is adopted to obtain the real-time prediction value of each piece of equipment and each component. On the basis, an adaptive threshold value is designed, and the false alarm of the system due to interference including environment temperature, wind speed change and the like can be avoided. By use of the method, an abnormal state is identified before faults happen so as to be convenient in adopting a corresponding measure in time, so that preventive repair is carried out, and the method has an important practical application value.

The invention relates to a computerized system for predicting completions to input text which is typed by a user to a text-oriented active application within a client computer, which comprises: (a) an off-line server that gathers texts from textual repositories, analyzes and processes the same to produce entries for an off-line database, said off-line server updates periodically a real time database of a real time server; (b) a real-time prediction server for receiving from an agent at said client computer serial requests for predictions, extracting in response to each of said requests one or more text predictions from tables within said real time database, and for conveying said one or more text predictions to said agent, wherein each of said text predictions comprises one or more words; (c) said real time database which comprises one or more tables containing word combination entries of various sizes, wherein each of said entries is associated with a weight which is used to estimate the probability for this combination to complete the typed text as included in the respective request for prediction; and (d) said agent which extracts in real time each present user typing to said text-oriented application, produces requests for prediction for new typing, sends the same to said prediction server, receives in response said one or more text predictions, and presents to said user said one or more text predictions for selection.

The invention discloses a traffic flow prediction method of a divergence convolution recurrent neural network based on a space-time diagram. The traffic flow prediction method is characterized in thata directed weighted graph of a road network is constructed based on spatial features of a traffic network, then a traffic flow prediction model of a graphic divergence convolution recurrent neural network is constructed by taking the directed weighted graph as a basic unit of prediction, deep learning is carried out by means of time-space characteristics of the traffic network, time-space prediction is carried out on the traffic flow of the traffic road network, a final traffic flow prediction model is constructed, and real-time prediction of the traffic flow is realized. The traffic flow prediction method has the advantages of precise prediction and high fitting degree.

A wind generating set fault prediction method based on D-S evidence fusion is disclosed. In the method, for two kinds of signals, two support vector machines after parameter optimization are constructed, the two support vector machines are taken as two evidences, and after D-S fusion, a final prediction fault type is given. The method has advantages that (1) in a traditional vibration method, only a vibration signal is analyzed, and a neural network, a decision tree and other machine learning algorithm models are constructed according to a vibration energy characteristic vector; but the vibration signal is only observed so that some fault states can be misclassified, for instance, a bearing damage and rotor eccentricity can cause a vibration signal abnormity, and at this time, a current signal can be used to distinguish two kinds of fault states; and (2) a prediction model established in the method can be stored, historical data does not need to be repeatedly extracted and trained, and under a real-time prediction environment of a wind field, a prediction result can be quickly provided.

The invention discloses a rear-end collision real-time prediction method aimed at a frequently jammed section of an expressway. Firstly, a traffic flow detector used for collecting real-time traffic flow data of all sections of the expressway is installed on the expressway (generally the upstream section of a bottleneck area). When a rear-end collision occurs, vehicle following running tracks are analyzed, a rear-end collision risk real-time prediction logistic model of the frequently jammed section of the expressway is built, and model parameters are calibrated according to traffic flow data by five minutes before the collision occurs. The method overcomes the defect that effective real-time prediction of the rear-end collision of frequently jammed section of the expressway cannot be conducted in the past, rear-end collision risks can be estimated in real time according to the traffic data collected by the traffic flow detector on the expressway, and moreover, dynamic traffic control is utilized to control and prevent the rear-end collision. The method has important time application value and wide application prospects in China.

The invention provides a method for predicting the internal temperature of a battery in real time, and relates to the real-time prediction methods for the battery. The problem that the actual internal working temperature of the battery can not be embodied by battery surface temperature monitoring is solved. According to the method, the battery is divided into an inner core and an outer shell, temperature prediction models are established respectively, the specific heat capacity of the internal material and the surface material of the battery, the thermal-resistance parameter of the inner core-outer shell of the battery, the thermal-resistance parameter of the outer shell-the outside of the battery, the open-circuit voltage curve of the battery, the curve of the open-circuit voltage variation with temperature and the like are acquired by an experiment method. A Kalman filtering method is used for tracking and correcting the internal temperature of the battery in real time, real-time battery surface and environment temperatures are input into the predication models, and the internal temperature of the battery is predicted in real time. The method is suitable for predicting the internal temperature of the battery in an electrical automobile and an energy storage system.

The invention relates to a method for predicting the space-time traveling track of a blacklisted vehicle. The method comprises the prediction of the traveling route of the blacklisted vehicle and the prediction of the traveling time of the blacklisted vehicle on the predicted traveling route. The prediction of the traveling route is achieved with a traveling route predicting method based on historical route similarity. The prediction of the traveling time of the blacklisted vehicle on the predicted traveling route is achieved with a traveling time predicting method based on road traffic condition evaluation. The method for predicting the space-time traveling track of the blacklisted vehicle is high in efficiency. According to the method for predicting the space-time traveling track of a blacklisted vehicle, the traveling route of the blacklisted vehicle can be predicted in real time after the blacklisted vehicle appears, the next position where the blacklisted vehicle might appear and the time when the blacklisted vehicle appears at the position can be determined, video surveillance and control can be conducted on the corresponding position in advance according to the predicted traveling route and the predicted traveling time of the blacklisted vehicle, and decision aids are provided for the arrest of the blacklisted vehicle.

An approach is provided for automatically predicting an event occurrence based on a question from an end user presented using a near-real-time natural language processing (NLP) analysis to generate, score and rank a plurality of event occurrences based on a plurality of question context parameters extracted from the question, one or more user profile parameters for the end user, and the one or more historical questions, answers, and events having a specified spatial and/or temporal proximity to the question which are identified by an information handling system. In the approach, performed by an information handling system, a top ranked event occurrence from the ranked plurality of event occurrences is selected for inclusion in a notification message that is communicated or broadcast to the end user, as well as other users engaged with the information handling system and/or first responders in the affected area.

The invention discloses a micro-grid robustness multi-target operation optimization method containing renewable energy resources. The method comprises the steps of: collecting micro-grid operation information, generating an uncertainty implementation scene in micro-grid operation, constructing a robustness multi-target model according to micro-grid attributes, inputting the robustness multi-target model and the uncertainty implementation scene into a two-stage solving strategy, carrying out iterative solving respectively on an internal layer maximum optimization problem under the uncertainty scene and an external layer minimum optimization problem under an operation scheme until an ending condition is met and circulation is stopped, forming an optimal operation scheme set, and selecting an optimal operation strategy according to real-time prediction data. The optimal robustness non-domination leading edge of economy and environment can be obtained under a worst uncertainty condition. Compared with an existing operation optimization method, the operation optimization method provided by the invention realizes interference inhibition of uncertainty in the micro-grid operation under a multi-target framework.

The invention discloses a multi-AUV self-adaptive target searching and obstacle avoidance method oriented to an unknown environment, and the method is suitable for multi-AUV target searching under anunknown complex underwater environment. The method is mainly divided into three modes including a target mode, a non-target mode, and an obstacle avoidance mode. In the target mode, the self-adaptivesearching is achieved through dynamic real-time prediction according to the target information for sensing the outside; in the non-target mode, full-area coverage searching and collaborative planningtasks are achieved through a sub-area strategy; and in the obstacle avoidance mode, the barrier threat is avoided in real time based on the improved dynamic window method. According to different underwater environment information, a multi-AUV target searching task is executed through alternate mode switching among the three modes, and the uncertain information under the unknown water can be dealtwith, the credible interval of the target state information is guaranteed, and environment adaptability and searching efficiency are achieved.

The invention discloses a real-time prediction method of mine gas concentration in short and medium terms based on radial basis function neural network integration. The method comprises the following steps of: taking mine gas concentration data as a chaotic time series to construct a plurality of prediction sub-models of radial basis function (RBF) neural networks, and taking a weighted mean of synchronous prediction results of all prediction sub-models as an integrated prediction value to realize prediction model initializtion of RBF neural network integration; then realizing prediction of the gas concentration in the range of from a short term to a medium term through setting an integrated capacity parameter (the integrated capacity parameter is also equal to an RBF network prediction step-length); and obtaining a new prediction sub-model by utilizing an incremental training mode aiming at the characteristics that gas concentration information is continuously collected, and realizing updating of the RBF neural network integration according to a first in first out queue sequence so as to improve real-time prediction precision of the gas concentration, therefore, a proper compromise can be obtained between prediction range and prediction precision requirements, and the technical requirement on a mine gas information management system is satisfied.

The invention provides a fan control method and a fan control device of a server and the server, wherein the server comprises a plurality of feature components and a plurality of fans. The method comprises the following steps: measuring temperature information and power consumption information of the plurality of feature components of the server; obtaining a current work mode of the server according to the temperature information and the power consumption information of the plurality of feature components; obtaining temperature of a plurality of key positions in the server according to the current work mode of the server and the preset temperature prediction model; respectively controlling the plurality of fans according to the temperature of the plurality of key positions. By adopting the method disclosed by the embodiment of the invention, real-time prediction of the temperature of the plurality of key positions is achieved in a numerical simulation manner under the premise of not increasing a physical sensor to the server; the plurality of fans are respectively controlled according to the real-time prediction temperature; the reliability of real-time measurement of temperature of the server is improved; the potential safety hazard in the server is reduced; meanwhile, the fans of the server are accurately controlled, and the waste of power consumption of the fans is avoided.