64 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.

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 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 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.

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.

The invention provides a wind power resource analysis and evaluation method and system for a new energy base, and belongs to the technical field of safety evaluation, and the method specifically comprises the steps: determining the change data of wind directions in different target time ranges according to the analysis results of wind power monitoring data in different target time ranges, and obtaining the change data of the wind directions in the different target time ranges; a wind direction variation time range within a target time range is determined on the basis of a wind direction variation interval, and configuration data of an available power generation period within an aggregation time interval within the wind direction variation time range is determined. And combining with the time interval data between the different aggregation time intervals and the distribution data of the time periods in the preset wind speed interval in the different aggregation time intervals, the evaluation and analysis method of the wind power resources of the new energy base in the wind direction change time range is determined, and the reliability degree of evaluation, analysis and processing of the wind power resources is improved.

Methods and systems are presented for providing a framework that enables a computer system to analyze and compare changes to different account characteristics of different accounts that occurred over a time period. A code is generated for an account to represent changes to different account characteristics of the account within the time period. Changes to different account characteristics may be highlighted in the code using different colors or patterns. By analyzing the code, overlapping changes from different account characteristics that occurred within the same time frame may be detected. The different change patterns associated with the user account may then be used to assess a risk for the user account and / or a transaction involving the user account.

A computer-implemented method selects publicly traded assets suitable for trading consideration. A computer accesses market databases, selects assets, and defines an analysis configuration with parameters and timeframes common across assets. For each parameter-timeframe series, the computer forms a normalizing indicator from at least two smoothed sequences and builds multiple deviation bands using specified band families and settings. Within a time window, boundary-crossing events of the indicator are detected for each band. For every asset, the computer records counts of boundary crossings in a result matrix, computes an integral score, optionally with weights, and forms an ordered set of result matrices obtained under alternative configurations. An asset-level output includes a per-matrix score and a set-wise score, such as a sum of per-matrix scores. Assets may be sorted or grouped by these values, and results may be visualized as comparison charts.

The present application relates to the technical field of power grid operation and maintenance, and particularly relates to a multi-target optimization power load interval prediction method and system. A number of high-frequency burst feature data intervals are determined by extracting and clustering burst event features according to power grid operation monitoring records of a target power grid in a historical time range; a power load prediction model is obtained based on the number of high-frequency burst feature data intervals; real-time burst feature data of a current power grid burst event is compared with the number of high-frequency burst feature data intervals respectively to obtain a plurality of burst scenario similarities; a model calling strategy is configured according to the plurality of burst scenario similarities, and the power load prediction model is called to predict power load in a preset time zone; an interval fitting strategy is configured according to the plurality of burst scenario similarities, and J initial load prediction intervals are fitted to output a power load prediction interval of the target power grid in the preset time zone. The present application realizes accurate prediction of a power load prediction interval.

The invention relates to the technical field of intelligent traffic scheduling and emergency management, and discloses a multi-rescue center dynamic vehicle path planning method based on double-layer adaptive large neighborhood search. And dividing the global time range into a plurality of continuous time periods, when each time period is finished, freezing the executed path section and the completed task in the previous time period as boundary conditions, and inheriting the real-time position, the residual workload capacity and the unserved accident point set of each rescue vehicle. Through cooperation of a periodic rolling optimization mathematical framework, prediction-driven global reallocation and double-layer ALNS search, a high-quality feasible solution can be continuously output within given time, and time window default is remarkably reduced, commuting distance and total cost are reduced, cross-site resources are more balanced, and online solution is more stable.

This invention discloses a velocity field correction method, apparatus, device, and medium, comprising: determining the initial velocity field of the area to be drilled based on target data of the area; when a new first completed well appears in the area, performing time-depth conversion on the initial velocity field to obtain an initial structural map; correcting the initial structural map based on key point data of the first completed well to obtain a corrected target structural map; determining the velocity correction amount corresponding to each stratum based on the differences between the target structural map and the initial structural map, and the time horizon of each stratum in the target structural map or the initial structural map; and correcting the initial velocity field based on the velocity correction amount corresponding to each stratum to obtain the corrected target velocity field. This invention eliminates well-seismic errors, improves the accuracy of time-depth conversion, and thus obtains high-precision depth-domain seismic data.

Systems and methods for predicting demand in real estate sales receive project-specific input data such as launch pricing, unit mix, project configuration, location factors, and / or market dynamics; identify comparable real estate projects within a defined geographic range based on similarity of project size, configuration, and / or launch conditions; apply an Initial Timeframe Model to forecast the number of units likely to sell within a first timeframe after launch, using a comparative analysis of the identified comparable projects and the project-specific input data; generate a project-specific demand curve for a subsequent timeframe using a demand curve model in which the model establishes a relationship between unit pricing and demand; dynamically refining the demand curve by incorporating real-time market data and / or housing market trends to align predictions with current economic conditions; and provide a graphical representation of the demand curve to guide optimal pricing and sales strategies for sustained revenue generation.

A system for processing and integrating contextual information across multiple time scales simultaneously analyzes immediate and historical data. The system comprises three main components working together to maintain temporal coherence. A temporal processing engine processes input data at different time scales using multiple processors, each dedicated to a specific time horizon. A context integration engine extracts and organizes contextual features from the input data, generating representations for different types of context while maintaining state information across these context types. A fusion engine combines the outputs from the temporal processors and integrates them with the context representations to generate coherent, unified outputs. The three engines operate cooperatively to ensure temporal consistency while processing context across multiple time scales. This architecture enables robust handling of complex temporal and contextual relationships, supporting applications in fields such as customer service, healthcare monitoring, and interactive systems where maintaining coherence across time scales is crucial.

This invention relates to the field of coating production line control technology, and particularly to a time-series linkage control method and system for a coating production line. The method includes the following steps: calculating the congestion level of each workstation; identifying the workstation with the highest congestion level as the bottleneck workstation; calculating the upstream supply segment disturbance index of the bottleneck workstation; obtaining a target time horizon based on the upstream supply segment disturbance index and a preset time horizon; obtaining a buffer target value based on the target time horizon and the real-time processing rate of the bottleneck workstation, wherein the buffer target value is positively correlated with the target time horizon; and updating the buffer capacity in the DBR scheduling algorithm using the buffer target value to control the material input at the beginning of the production line, effectively improving the efficiency of the time-series linkage control of the coating production line.

A system for time-controlled optimization and real-time control of dynamic systems under constraints, based on the time to loss of control, consisting of: a data acquisition module configured to receive real-time data from one or more technical sources representing the state of a monitored dynamic system; a preprocessing module connected to the data acquisition module and configured to process and filter the received real-time data to generate a structured representation of the current system state; a state prediction module connected to the preprocessing module and configured to receive the preprocessed data and, based on the structured representation of the current system state, calculate predicted future states of the monitored dynamic system over a defined time horizon;a Time to Loss of Control (TLC) module connected to the state prediction module and configured to compare predicted future states with predefined thresholds representing acceptable operating limits, determine a Time to Loss of Control (TLC) that represents an estimated time at which the monitored dynamic system is expected to reach an unstable or undesired state, and continuously updates the TLC as new real-time data becomes available;a constraint modeling module configured to identify operational constraints related to the monitored dynamic system, wherein the operational constraints include resource constraints, safety thresholds, and operating rules, and wherein the constraint modeling module is further configured to transform the operational constraints into a structured representation that defines a feasible set of permissible actions;An optimization module connected to the constraint modeling module, comprising a quantum processing unit configured to perform constrained optimization using energy minimization-based computational techniques to determine executable control actions within the remaining time until loss of control, wherein the optimization module is configured to determine one or more executable control actions that improve system stability based on the current system state, predicted future states, determined TLC, and structured representation of the operational constraints, wherein the one or more executable control actions are determined based on the remaining time until loss of control (TLC) such that only actions possible within this time window are considered;A control signal generation module connected to the optimization module is configured to convert the results of the optimization module into executable output signals, which are executed by a control execution module connected to the monitored dynamic system. After the signal is executed, control actions are automatically performed on the monitored dynamic system within the remaining time until loss of control.