85 results about "Time horizon" patented technology

A deep learning system for time series prediction comprising a preprocessor that receives time series input sequences, truncates them by removing terminal values, and appends padding values to maintain the original sequence length. An encoder compresses these padded sequences into latent space representations, while a decoder reconstructs predicted sequences matching the original length, specifically trained to reconstruct values matching the removed terminal values in positions corresponding to the padding values. A training system optimizes the encoder and decoder by minimizing differences between original sequences and predicted sequences. The system can process multiple time horizons simultaneously while maintaining statistical properties and providing uncertainty quantification through confidence intervals. This approach enables accurate short-term forecasting while preserving both temporal patterns and statistical relationships in the predicted sequences.

An AI-driven financial planning system for real-time market adjustment, consisting of: a neural inference coprocessor configured to execute deep financial forecasting models, including recurrent neural networks and attention-based encoders, on the device, and wherein the processor dynamically updates portfolio parameters in response to market signals exhibiting volatility differences above a statistical threshold calculated using an exponentially weighted moving standard deviation; a financial data acquisition module configured to continuously receive and analyze heterogeneous data streams, including market indices, interest rates, stock and bond price fluctuations, economic indicators, regulatory updates, and financial news sentiment feeds; a behavioral analytics engine configured to create a dynamically evolving user-specific financial behavior profile based on real-time analysis of transaction history, income-expenditure cycles, psychometric test results, and temporal lifestyle patterns using supervised and unsupervised machine learning algorithms; A goal optimization module configured to transform high-level, user-defined financial goals into quantitatively tracked multi-level goals. It uses a reinforcement learning framework that predicts optimal asset allocations across multiple time horizons. a real-time strategy simulation engine configured to perform Monte Carlo simulations and deep Q-learning-based assessments to simulate the resilience of proposed financial strategies under different macroeconomic regimes and trigger redistribution events based on predefined confidence thresholds; a compliance-aware execution interface configured to interact with financial institutions through encrypted API channels, ensuring policy enforcement using a smart contract validator and a hardware-enabled secure transaction signing unit; and a recommendation display unit configured to render dynamic dashboards for visualizing investments, reallocation warnings, confidence intervals, and sensitivity sliders, and where user interaction with the unit flows back into the behavioral model for real-time learning.

The invention discloses a method for preventing main steam pressure fluctuation on the basis of controlling the coal combustion amount. The method comprises the following steps: acquiring running state data of the coal-fired boiler in real time; based on the operation state data and a preset boiler dynamic prediction model, predicting a steam pressure sequence of the boiler in a future preset time range, and judging whether to trigger a control action or not in combination with an event triggering strategy obtained by learning of a reinforcement learning agent; if it is judged that the control action is triggered, the reinforcement learning agent outputs an adjustment instruction of the total coal feeding amount according to the current operation state data; and controlling the total coal feeding amount of the boiler according to the adjusting instruction. According to the method, the timing and the force of control intervention can be intelligently determined according to the real-time state and future trend prediction of the boiler, and the accuracy and the foresight of main steam pressure control are improved.

The invention discloses an orbit-driven atmospheric density estimation method. The method comprises the following steps: acquiring historical orbit element data and screening satellite numbers in a required time range; based on the obtained historical orbit element data and the screened satellite number, calculating a propagation orbit of the satellite in a future time period through an orbit propagation model; defining historical orbit element data as a real orbit, and calculating a propagation error at the same time point according to the real orbit and the propagation orbit; dividing the propagation errors into a regular class and an irregular class, and selecting satellite orbit parameters of the regular class; constructing an atmospheric density prediction model, and inputting the selected rule-class satellite orbit parameters into the atmospheric density prediction model for training and evaluation to obtain an optimized atmospheric density prediction model; and inputting the orbit parameter, the state vector, the space environment index and the error of the front and back orbit propagation in the previous time period into the optimized atmospheric density prediction model to obtain the atmospheric density at the future moment.

A method performed by a network node for an adaptive prediction of a time horizon for at least one key performance indicator, KPI, in a wireless network is provided. The method includes transmitting towards a user equipment, UE, a machine learning, ML, model to predict the at least one KPI; and receiving from the UE a first message including the predicted at least one KPI and a predicted time horizon for the predicted at least one KPI. A method performed by a UE is also provided.

A multi-tiered optimization and machine learning framework is provided in which operational decisions as far as driver capacity allocation are taken at three different levels or stages, namely, long-term, short-term, and real-time. While decisions at each stage have individual importance for the operations at different time horizons, this framework utilizes decisions upstream to inform better results downstream. This synergy helps improve allocations when compared to solutions that assign driver capacity for each stage individually.

The invention discloses a renewable energy source-oriented power system planning method. The method comprises the following steps of S1, collecting load data of a power system; s2, according to the historical renewable resource power generation power, the historical meteorological data and the predicted meteorological data, predicting renewable resource power generation power within a preset time range; s3, predicting a power load demand in a preset future time range by adopting LSTM according to the collected load data and historical load data; s4, according to the predicted power generation power, the predicted power load demand, a preset constraint condition and a preset optimization target, a power system planning model is constructed, and the optimization target comprises the minimum power generation cost and the maximum renewable energy utilization rate; and S5, solving the power system planning model by adopting a genetic algorithm to obtain an optimal power system planning scheme. Through the optimal power system planning scheme, the power generation cost is reduced, and the utilization rate of renewable energy sources is improved.

The invention discloses a dynamic environment and multi-event collaborative awareness method based on a multi-modal neural network. According to the method, multi-modal data is obtained through a multi-source sensing device, and a multi-modal data sequence under a unified reference coordinate is formed through time synchronization and space registration. And inputting the data sequence into a multi-modal deep neural network, and adaptively correcting each modal feature weight according to a confidence coefficient change rate between time slices to obtain corrected feature information. And performing external target identification and internal event identification on the feature information to generate a candidate event set, establishing an event priority relationship, and outputting a collaborative event result including an event tag, a spatial position and a time range. And finally, the risk level is determined according to a collaborative event result, and a corresponding early warning or control instruction is generated, so that intelligent identification and collaborative decision-making of multiple events in a complex dynamic environment are realized, and the real-time performance and accuracy of the system in multi-source data fusion and safety monitoring are improved.

The invention discloses an intranet penetration traceability method for multi-scale heterogeneous log behavior analysis, and relates to the technical field of network security, and the method comprises the steps: carrying out the standardization processing of an original log stream of a heterogeneous log source, and generating a unified semantic event stream; performing multi-scale time window division on the unified semantic event stream, calculating an event density characteristic index of each window, and identifying a short-time dense subsequence based on the event density characteristic indexes; clustering analysis is carried out on the identified short-time dense subsequences based on semantic weighted entropy, and aggressive dense segments and normal high-load segments are distinguished; based on the semantic relevance of the event, extracting long-time sparse clues from the unified semantic event stream; a long-time sparse clue is used as a time anchor point, an aggressive dense section adjacent to the time anchor point is positioned in an extended time range of the long-time sparse clue, and an intermediate interpolation event sequence is generated through a conditional time sequence model to reconstruct a complete attack chain.

The invention relates to the technical field of simulation modeling, in particular to a BIM-based building embedded pipeline simulation system, which comprises a pipeline path optimization module, a space conflict detection module, a construction sequence planning module, a dynamic adjustment generation module and a resource utilization rate evaluation module. According to the method, by automatically extracting the spatial distribution information of the pipelines and analyzing the geometrical characteristics and the connection relation of the pipelines, accurate marking of potential conflict positions can be achieved, the comprehensiveness and the accuracy of spatial conflict recognition are effectively improved, and further based on extraction of the construction sequence relation and logic dependency analysis, the construction efficiency is improved. The method can achieve the intelligent judgment of the construction conflict state, achieves the dynamic adjustment of a layout path and a time range, assists in forming a targeted wiring strategy in a conflict region, optimizes the resource space matching degree, automatically recognizes a low-efficiency time period, carries out the real-time identification, improves the response capability of a construction process to the resource utilization efficiency, and improves the construction efficiency. And the precision of path adjustment and the coordination of construction organizations are improved.

The invention belongs to the technical field of water supply network leakage monitoring, and particularly relates to a water supply network leakage node and time window combined positioning method based on a hybrid neural network, which realizes spatial positioning of a water supply network leakage node and time positioning of a leakage time window. Comprising the following steps of 1, collecting node pressure and flow time sequence data of the water supply network in different scenes, and recording leakage nodes and leakage starting and ending time labels; 2, carrying out normalization preprocessing on the data, and constructing a standardized time sequence data set containing a multi-leakage scene mark; step 3, a dual-branch hybrid neural network model TCN-Transform-KAN is built, and a dual-branch hybrid neural network model TCN-Transform-KAN is built; 4, constructing a joint loss function of node classification loss and time regression loss; and step 5, training through a joint loss function constraint model, and outputting a leakage node and a center position and a continuous width of a leakage time window. According to the method, joint precise identification of the leakage nodes and the time range is realized, and technical support of time-space two-dimensional information is provided for intelligent operation and maintenance of a water supply pipe network.

An electric power system (10) is supplied at least in part by renewable energy sources (12). A method for managing storage of energy in such a system includes obtaining a stochastic model (16) that models probabilistic variability (22) in weather (20) across a sequence of time periods (P-1 . . . P-N) within a time horizon (18), each time period (P-n) being at least one day in duration. The method further includes determining, using the stochastic model (16), one or more values (24V) for one or more design or operational parameters (24) of the electric power system (10) that optimize a level of energy (L-1 . . . . L-N) stored by the electric power system (10) at each time period (P-1 . . . P-N) by minimizing an expected impact of renewable energy production variation occurring over the time horizon (18) due to the modeled probabilistic variability (22) in weather (20).

A method may include receiving historical data indicating a demand for a product during a plurality of weeks within a previous year; determining optimal fitting gamma distribution per week based on the historical data; performing a first simulation of the gamma distribution over a short-term time range to generate a first estimated demand for the product over the short-term time range; performing a second simulation of the gamma distribution over a long period of time to generate a second estimated demand for the product over the long period of time; determining a first inventory amount of the product required to meet the first estimated demand at a first confidence level; determining a second inventory amount of the product required to meet the second estimated demand at a second confidence level; and ordering a third stock amount, wherein the third stock amount comprises a minimum value of the first stock amount and the second stock amount.

A method performed by a network node for an adaptive prediction of a time horizon for at least one key performance indicator, KPI, in a wireless network is provided. The method includes transmitting towards a user equipment, UE, a machine learning, ML, model to predict the at least one KPI; and receiving from the UE a first message including the predicted at least one KPI and a predicted time horizon for the predicted at least one KPI. A method performed by a UE is also provided.

The predictive controller determines, using the deep generative decoder model, a conditional probabilistic distribution of the latent representations of the disturbance conditioned on the partial observations of the disturbance, and samples the conditional probabilistic distribution of the latent representations to produce a latent sample of the time-series values of the disturbance affecting the mechanical system over the time horizon. The predictive controller decodes the latent sample with the deep generative decoder model to produce predicted values of the disturbance acting on the system within the time horizon with a probability of the latent sample on the conditional probabilistic distribution of the latent representations and controls the mechanical system using a predictive controller that determines control commands changing a state of the operation of the mechanical system using the probability of at least some of the predicted values of the disturbance.

A computer-implemented method, computer program product, and computer system for automated model predictive control. The computer system trains multiple step look-ahead regression models, using historical states and historical actions for a to-be-optimized system, for each timestep of a past time horizon. Regression models may be either linear or nonlinear in order to capture process dynamics and nonlinearity. The computer system generates optimization constraints for each timestep of a future time horizon. The computer system generates optimization variables, based on the multiple step look-ahead regression models, for each timestep of the future time horizon. The computer system constructs a mixed integer linear programming based optimization model that includes an objective function, the optimization constraints, and the optimization variables. Nonlinear regression models are converted into piecewise linear approximation functions. The computer system solves the optimization model to produce actions for the to-be-optimized system, over the future time horizon, and recommend commitment-look-ahead actions.

The invention discloses an individual care product process optimization method and system based on user behavior data, and relates to the field of intelligent data processing, and the method comprises the steps: collecting a historical user behavior data set in a historical time range after a target product is put into the market through multiple channels, and carrying out the data preprocessing and product improvement correlation feature extraction, obtaining a historical product improvement associated feature set; determining an optimal process adjustment time period by combining a predicted product demand growth rate and a predicted product demand fluctuation coefficient within a preset time range; according to the user behavior data set in the optimal process adjustment time period, determining a product improvement index according to the product quality associated feature set; and obtaining an optimal process adjustment scheme by taking approximation to a product improvement index as an optimization target, and carrying out production process iterative optimization within a preset time range. According to the method and the device, the problems of poor user experience, low optimization strategy scene adaptability and inaccurate process optimization direction in the prior art are solved.

The invention belongs to the technical field of computers, and discloses a query method for a closely associated transaction account group, which comprises the following steps of: 1, extracting all connected k-trus communities in a global time interval of an account transaction network, and calculating a real time interval; step 2, carrying out forward evolution refinement; step 3, carrying out backward evolution refinement; step 4, constructing a DAG index structure of the time evolution community; step 5, querying the maximum connected k-trus community of the given account in a specified time interval by using the index; and step 6, returning a query result. According to the method, by constructing the account community structure diagram evolved in the time interval, the repeatedly stored community information is effectively compressed, and the expression ability and query efficiency of account community evolution in a cross-time range are improved. Through recursive stripping and sharing of edge sets among communities, minimum redundant community representation across multiple time windows is realized, and the storage overhead is remarkably reduced while the historical integrity of the communities is ensured.

A system and a method for stabilizing hydrogen flow to a downstream process in a facility determining a hydrogen density and pressure profiles in the hydrogen storage unit for different target net hydrogen flows at different time intervals of a time horizon of a renewable power availability profile, determining an operating target net hydrogen flow of a hydrogen feed to the downstream process, determining a target direct hydrogen flow of a hydrogen feed and a target stored hydrogen flow of a hydrogen feed to the downstream process, and controlling the operation of the downstream process based on the operating target hydrogen flows.

The invention discloses a hotel reservation management method and device, computer equipment and a storage medium, and relates to the technical field of hotel reservation, and the method comprises the steps: generating and publishing a hotel future option product based on the inventory prediction data of a hotel supplier and a preset price strategy; in response to a purchase request, sent by a user terminal, for future option products of the hotel, receiving earnest money paid by the user, creating an option holding record uniquely associated with the user, and generating an encrypted digital option certificate at the same time; before the option expires or when an agreed performance triggering condition is met, a hotel inventory management interface is automatically called, available hotel room resource information conforming to the check-in time range, the applicable geographic area and the room type level is acquired, and the room type level of the hotel is determined based on a preset multi-factor weighted matching algorithm. And determining a target hotel for the user from the available hotel room source information to complete performance. According to the method, the contradiction between hotel income uncertainty and user travel variability is solved.

The invention discloses a detection method and device for a customer service system in the financial field and electronic equipment. Relates to the financial science and technology field or other fields, and comprises the following steps: obtaining business information of a customer service system in the financial field in a target time range of a target date, and obtaining target business information; according to the date type of the target date, determining N reference dates of which the date type is the same as that of the target date from the plurality of historical dates; based on the service information in a reference time range of the N reference dates, reference information is determined, the reference time range and a target time range are the same time range under different dates, and the reference information comprises at least one of a first reference threshold value of the number of incoming lines of a user and a second reference threshold value of the online rate of a plurality of customer service accounts; and determining a detection result based on the reference information and the target service information. Through the method and the device, the problem that the detection accuracy is low when whether the customer service system in the financial field is abnormal or not is detected in related technologies is solved.

The present invention discloses a method, apparatus, electronic device and storage medium for generating a ship trajectory heat map. The method includes: obtaining AIS data of a target ship and converting the AIS data into a plurality of AIS point data; projecting the AIS point data within a preset unit time onto a preset two-dimensional pixel plane for color radiation to generate an initial heat map corresponding to each segment of the preset unit time; performing a progressive pixel weighted average method operation on the initial heat maps of each segment of the preset unit time to obtain a multi-level heat map for each time interval; obtaining a time range to be searched, and performing a pixel weighted average method operation on the target-level heat map corresponding to the time interval corresponding to the time span of the time range to obtain a target heat map corresponding to the time range. The present invention can efficiently and accurately generate a ship trajectory heat map and can be widely applied to the field of data processing technology.

One or more systems, devices, computer program products and / or computer-implemented methods of use provided herein relate to automated control for a physical system with generic forecasting models. The computer-implemented system can comprise a memory that can store computer executable components. The computer-implemented system can further comprise a processor that can execute the computer executable components stored in the memory, wherein the computer executable components can comprise a training component that trains one or more multivariate time series forecasting models, and a prediction component that forecasts long-horizon action trajectories for a set of state variables over a defined range of time. Furthermore, an analysis component can linearize the state-based action response model, wherein the linearized the state-based action response model can be formulated into an MILP optimization problem and solved to obtain a multi-step set-point recommendation.

Navigation method, wherein a navigation device calculates a navigation route (20) from a starting location to a destination, wherein - a computing unit obtains information about at least one temporally and spatially variable event (1); - the computing unit estimates a temporal-spatial course of the event (1) for a future time horizon and stores it as a dynamic area of ​​interest (2); - the navigation device receives the dynamic area of ​​interest (2), determines a starting location and a starting time and calculates the navigation route (20) from the starting location to the destination, wherein the destination lies within the dynamic area of ​​interest (2) or an observation point (3) is set as the destination from which the event (1) is observable; - the computing unit divides a digital road map (6) into a plurality of polygons (7), wherein map information is assigned to each polygon (7), so that the polygons (7) represent the digital road map (6) in the form of a dynamic graph (8) and the computing unit maps the dynamic area of ​​interest (2) onto the dynamic graph (8), wherein the dynamic graph (8) comprises a plurality of nodes (9), wherein each polygon (7) is assigned a node (9), characterized in that - height information (10) is assigned to the nodes (9) of the graph (8) as map information, wherein the height information (10) describes the topographical height of the terrain and / or the geodetic height of an object located in the respective polygon (7), and the computing unit calculates a height difference to the respective neighboring nodes (11) for each node (9) of the graph (8), wherein a clear view to a neighboring node (11) exists if the height to the neighboring node (11) remains the same or decreases; and wherein - the computing unit determines a node chain (12) emanating from the dynamic area of ​​interest (2) with a clear view of the dynamic area of ​​interest (2) and defines a node (9) of the node chain (12) as an observation point (3).

The invention provides a profit and loss deviation early warning method, device and equipment, a medium and a program product, relates to the field of artificial intelligence, and can be used in the field of financial science and technology or other fields. The method comprises the following steps: obtaining profit and loss actual data and profit and loss prediction data in the same time range, wherein each of the profit and loss actual data and the profit and loss prediction data comprises a department profit and loss index, a project profit and loss index and a project profit and loss composition index; calculating the deviation degree of the first department based on the predicted value and the actual value of the department profit and loss index of the first department; when the deviation degree of the first department is greater than a weak deviation degree threshold but less than or equal to a strong deviation degree threshold, outputting a first early warning message based on the deviation degrees of all items in the first department; and when the deviation degree of the first department is greater than the strong deviation degree threshold, outputting a second early warning message based on the deviation degree of the project profit and loss composition indexes of all projects in the first department.

Power consumption forecasting plays a key role in the efficient operation of a building energy management system to assess energy demands of building, and at the same time, help electrical utilities in planning their supply operations. However, no state-of-the-arts are available for forecasting medium-term or long-term power consumption of the buildings. This disclosure relates to a method and system for forecasting a power consumption of buildings for a scalable forecast horizon. The system is configured to pre-process to deal with outliers / missing values, followed by synchronization of smart meter data with other sensory data. An energy-temperature correlation is calculated to estimate an energy drift using historical power consumptions. Further, in feature derivation stage, additional features necessary for the forecast are derived. The system is to be employed for modeling the building load consumption that depends on the time horizon of forecasting and the granularity of the data.

The invention relates to a method for regulating the operation of an electric furnace (10) during a melting process of molten material, comprising the following method steps:-performing a model predictive calculation (S1) of a target curve of at least one operating characteristic (Op) up to a time range (N) on the basis of the results of the melting process to be achieved; and-setting (S2) the at least one operating characteristic (Op) by means of the electrode positioning means (30) and / or the power supply means (50) in such a way that the at least one operating characteristic (Op) lies on the target curve of the at least one operating characteristic (Op) at a predetermined future point in time. The invention also relates to an electric furnace (10) configured to perform a method for adjusting the operation of the electric furnace (10) during a melting process of a molten material.

The invention provides a method for adjusting a timeout time range of a root complex, a network chip and electronic equipment. The method comprises the steps that a substrate management controller system acquires a working load parameter of a data processing unit in real time; the baseboard management controller system obtains the current load level of the data processing unit according to the working load parameters of the data processing unit; the baseboard management controller system dynamically determines the timeout time range of the root complex according to the current load level of the data processing unit; and the baseboard management controller system configures the completion timeout time of the corresponding root port on the host side according to the determined timeout time range of the root complex. According to the technical scheme, the response capability and the processing efficiency of the system can be improved.

To predict the future evolution of the health state of equipment and / or processing units of a chemical production plant such as a steam cracker, a computer-implemented method is provided that builds a data-driven model of future key performance indicators based on current key performance indicators, current process conditions, and process conditions within a prediction time horizon.