1165 results about "Time segment" patented technology

Systems and methods are described for detecting anomalies within time series data using one or more online machine learning models. In one example, time series data may be obtained that spans a moving time period of a set length, to be used as training data. A machine learning model may be trained using the training data to identify anomalies in the time series data by upon detecting an estimation of an anomalous value in the time series data, pausing input of additional values of the training data into the machine learning model, and resuming input of the additional values of the training data into the machine learning model based on detecting at least one non-anomalous value. The trained machine learning model may then be used to detect a first anomaly in additional time series data by comparing the at least one additional value to the trained machine learning model.

It aims to appropriately manage the bias of the signal processing amount. 【Solution means】 The abnormality management device 1 uses, as teacher data, normal data indicating the number of normal packets distributed to each device for each time zone, and learns, by maximum likelihood estimation, the parameters of a probability model that outputs the posterior probability that the number of packets distributed to each device for each time zone is normal. A learning unit 11, the posterior probability for each device for each time zone estimated by the learned probability model, the probability distribution of the normal data for each device estimated based on the normal data, and the prior probability of being normal. A derivation unit 12 that derives the probability distribution of abnormal data indicating the number of abnormal packets distributed to each device in the time zone, and the probability distribution of the normal data and the probability distribution of the abnormal data for each device for each time zone are equal. And a setting unit 13 that sets, as a threshold value for abnormality determination of the number of packets distributed to each device, the number of packets corresponding to the value of the probability distribution that becomes the value.

Method comprising: receiving, for each of plural times, a respective first indication indicating that a first base station adopted a respective beam setting at the respective time; storing, in a database, for each of the plural times, the respective beam setting adopted, according to the respective first indication, by the first base station at the respective time along with the respective time; monitoring whether a request for the beam setting adopted by the first base station in a time period is received; retrieving, from the database, the one or more beam settings adopted, according to the database, by the first base station in the time period if the request is received; reporting the retrieved one or more beam settings adopted, according to the database, by the first base station in the time period in a response to the request.

To provide a power amount adjustment system capable of reducing power consumption according to requests to reduce the power consumption due to tight power supply and demand.SOLUTION: In a power amount adjustment system 100, when a server 4 acquires tight power supply and demand information requiring a reduction in power consumption in a specific time period, the server is configured to change and adjust a start time of defrosting operation when the specific time period overlaps with a time period during which pulldown is scheduled to be performed.SELECTED DRAWING: Figure 1

The invention discloses a power consumption distribution method and device, a storage medium and a program product, and relates to the technical field of servers, and the method comprises the steps: dividing a plurality of time slots, and in each time slot interval, according to the predicted load demand of each node and the task priority weight of a task executed by each node in the corresponding time slot, determining the task priority of each node; according to the method, the dynamic priority of each node is determined, and then the power consumption of each node is allocated based on the dynamic priority and the resource budget of each node in each time slot interval, so that the method can flexibly adapt to different load requirements and execution of tasks with different priorities in different time periods, and the tasks with high priorities can guarantee more resources; according to the method, resource waste is avoided, reliable decision support is provided for power consumption management of the server, system stability and task execution efficiency are effectively balanced, and double breakthrough of the data center in the aspects of energy conservation and performance optimization is promoted.

The invention relates to the technical field of subway information broadcast control, and discloses a subway information broadcast control method based on time period scheduling. The method comprises the steps of collecting multi-source monitoring data of a subway operation environment in real time, wherein the multi-source monitoring data comprises passenger flow data, train arrival data and emergency event report data; dividing the current operation cycle into a plurality of continuous time slices based on a preset time period division rule, and generating a corresponding time period identification code for each time slice; matching a target broadcast control template from a broadcast control strategy library according to the time period identification code, and performing parameter dynamic filling on the target broadcast control template in combination with the multi-source monitoring data; and performing logic verification on the target broadcast control template after parameter filling, triggering a broadcast control decision reconstruction process when verification is abnormal, and generating an executable broadcast control instruction set when verification is normal. According to the method, operation requirements of different time periods are dynamically adapted, so that the accuracy and timeliness of subway information broadcast control are improved, and the passenger travel experience and the operation efficiency are optimized.

The invention discloses an airport flight quantity and throughput prediction method and system, and relates to the technical field of intelligent airport management. The method comprises the following steps: firstly, determining a future target time period to be predicted, and obtaining related multi-source data according to the future target time period; preprocessing the data and extracting time sequence and non-time sequence features; processing time sequence features by using the trained long-short-term memory neural network model, processing non-time sequence features by using the extreme gradient boosting tree model, and respectively obtaining prediction results; and integrating the outputs of the two types of models through a weighted fusion strategy to obtain an accurate prediction value of the flight sortie and the single-machine passenger capacity, and further calculating to obtain a passenger throughput prediction result. According to the method and the system provided by the invention, through the architecture of multi-source data fusion and hybrid intelligent model cooperation, the prediction precision and reliability are effectively improved, and scientific decision support is provided for airport operation management.

Provided in the embodiments of the present disclosure are a resource scheduling method and apparatus. The resource scheduling method comprises: determining historical operating log data and historical resource usage data of a data processing node set which are generated within a preset historical time period; on the basis of the historical operating log data, and by means of using a log prediction model, predicting predicted operating log data of the data processing node set that is generated within a preset future time period; on the basis of the predicted operating log data, and by means of using a resource prediction model, predicting predicted resource usage data of the data processing node set that is required within the preset future time period; on the basis of the historical resource usage data, determining target resource usage data of the data processing node set within the preset future time period; and on the basis of the predicted resource usage data and the target resource usage data, performing resource scheduling on the data processing node set. The resource scheduling method is more reasonable and more intelligent, and does not require human participation, thus resulting in more stable application systems.

The invention discloses a real data generation method and system, a storage medium and a program product, and the method comprises the steps: carrying out the trend analysis of target data, and obtaining a trend coefficient of the change trend of the target data; constructing a global trend function according to the trend coefficient; obtaining a primary period value and a secondary period value of the target data; constructing a period superposition function according to the primary period value and the secondary period value; performing function synthesis on the global trend function and the periodic superposition function to obtain a time sequence characteristic function; acting the time sequence characteristic function on each time sampling point of the target time period to obtain a reference data sequence; performing random disturbance processing on the reference data sequence according to preset fluctuation parameters to obtain a target data sequence containing random fluctuation characteristics; and adjusting the target data sequence according to a preset data constraint condition, and generating real data meeting the data constraint condition. According to the method and the device, the accuracy of reflecting the time sequence evolution rule by real data is improved, and the capability of discovering defects in time sequence related function tests is further improved.

The present application relates to the technical field of communications, and discloses a path planning method and apparatus, a device, a system, and a storage medium. The method comprises: acquiring traffic prediction information respectively corresponding to at least one time period; and on the basis of the traffic prediction information respectively corresponding to the at least one time period and at least one selectable path respectively corresponding to each service, determining a target forwarding path of each service meeting path planning objectives. The path planning objectives comprise: the service traffic borne by any link in a hierarchical network in any time period is less than or equal to the bandwidth capacity upper limit of any link, load balancing is realized between multiple links connected to a same network node in the hierarchical network, and the transmission quality of the target forwarding path of any service meets a quality requirement of any service. Path planning of a global service is realized, network link congestion can be reduced, and better effects that load balancing between all network links is realized and a service forwarding path meets a service quality requirement are achieved.

The embodiment of the invention provides a fault positioning method and device, a storage medium and a program product, relates to the technical field of communication, and can realize quick fault positioning and improve the fault positioning efficiency. The method comprises the steps that alarm information sent by first equipment is received, the first equipment comprises a plurality of ports, a first flow rate time sequence and a second flow rate time sequence of the flow rate of each port in a first time period are determined, and the first flow rate time sequence and the second flow rate time sequence are sent to the first equipment; and finally, based on the first flow rate time sequence and the second flow rate time sequence of each port in the plurality of ports, determining a port in a fault state in the first equipment. Wherein the first flow rate time sequence is used for representing the change condition of the actual flow rate of the port in the first time period, and the second flow rate time sequence is used for representing the change condition of the predicted flow rate of the port in the first time period.

The invention discloses a power transmission line icing galloping prediction method and system based on an improved time sequence large model, equipment and a storage medium, and relates to the technical field of power system safety monitoring, and the method comprises the steps: obtaining line parameters, and meteorological data and power transmission line icing galloping data in an abnormal accumulation time period; constructing a data feature project by using the line parameters, the meteorological data in the abnormal accumulation time period and the icing galloping data of the power transmission line; performing data synthesis on the meteorological data and the icing galloping data of the power transmission line in the abnormal accumulation time period through time alignment to obtain a comprehensive time sequence; and taking the comprehensive time sequence as input, and obtaining the icing galloping probability and the galloping amplitude of the power transmission line based on the output of the improved time sequence large model. According to the invention, the icing galloping risk early warning of the power transmission line can be rapidly and accurately output, and reliable guarantee is provided for safe operation of a power grid.

The invention relates to the technical field of elevator energy consumption analysis, and discloses an elevator energy consumption analysis method and system.The elevator energy consumption analysis method comprises the steps that elevator operation data are obtained, anchor point events are detected based on the elevator operation data, time alignment processing is conducted on the elevator operation data, and a synchronous data sequence with a unified time axis is generated; based on the synchronous data sequence, elevator running states are recognized, regeneration running stages are marked, and time segments corresponding to the elevator running states are output; carrying out integral calculation on the active power of the line in a time segment, realizing bottom consumption stripping in combination with a standby power reference, and outputting segment energy consumption through positive and negative power decomposition; and in the regeneration operation stage, feedback energy and braking energy are calculated according to the elevator operation data, feedback efficiency is calculated, and an energy consumption analysis result is output. According to the method, a reliable basis is provided for energy efficiency evaluation, abnormal early warning and operation optimization of the elevator system.

The invention discloses a network equipment fault analysis method and device based on multi-dimensional characteristics, and relates to the technical field of network equipment fault analysis, and the method comprises the steps: obtaining the time sequence characteristic data of each network equipment in an Internet of Things cluster during the operation of a current time period, and forming a multi-dimensional network fault identification data set according to the time window dimension, the network equipment dimension and the feature dimension, carrying out encoding processing on the network fault identification data set by adopting a pre-trained encoder to obtain an encoding vector, inputting the encoding vector into a pre-constructed fault prediction decoder, and carrying out fault prediction on the network fault identification data set according to the pre-constructed fault prediction decoder. And outputting the fault probability of each network device in the preset time period. The network equipment fault diagnosis method and device solve the technical problems that when network equipment fault diagnosis is carried out in the related technology, due to the fact that network faults have space-time variability and diversity, single-dimension analysis cannot accurately capture the full view of the faults, and fault diagnosis is delayed and misdiagnosed.

The embodiment of the invention provides a resource scheduling method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining task meta-information and task constraint information of each task in a task set, and determining to-be-executed tasks in each time period based on the task meta-information and the task constraint information, determining the total resource consumption amount of each time period based on the resource consumption amount of the to-be-executed tasks, determining a target time period in which the total resource consumption amount is greater than the set total available resource amount from each time period, and obtaining adjustable tasks from the to-be-executed tasks in the target time period, and determining the scheduling priority of each adjustable task based on the resource consumption of the adjustable tasks, the downstream task quantity and the task running duration, determining the adjustable task with the lowest scheduling priority as a target task, and adjusting the predicted starting time of the target task according to a preset adjustment strategy.

The invention provides an elastic thread pool management method and device based on load prediction and electronic equipment, and the method comprises the steps: obtaining a task submitted by a client, and routing the task to a corresponding queue according to the task feature of the task; wherein the I / O type task is routed to an asynchronous queue, and the CPU calculation type task is routed to a thread pool queue; monitoring and collecting thread index data of the thread pool queue in real time, and obtaining thread index data of a first preset time period based on a preset sliding window; inputting the thread index data of the first preset time period into a prediction model to obtain a predicted load value of a second preset time period; wherein the prediction model is a Holt-Winters model, and the prediction model is a Holt-Winters model; and performing thread adjustment based on the predicted load value and a preset load threshold value. The problems existing in an existing thread pool management scheme are solved.

Certain aspects of the present disclosure provide flow estimation techniques for dynamic scenes. A method generally includes obtaining a first time series sequence of sample sets of a scene (including a first and a second set of samples) over a first period of time associated with a reference time; processing, with a spatial-temporal attention module, the first time series sequence, to generate a modified first time series sequence of sample sets of the scene comprising the first set and not the second set of samples; processing, with a first neural ordinary differential equation (ODE) and a first ODE solver, the modified first time series sequence to predict a second time series sequence of sample sets; and generating a first output indicating a predicted flow of the scene from the reference time to a first selected time based on the modified first time series sequence and the second time series sequence.

The embodiment of the invention relates to the technical field of communication, provides a communication method and device, and is used for solving the problems that the speed dimension perception resolution is low and a target with relatively low speed is difficult to perceive when communication and perception signals are multiplexed. In the method, a first network device sends first indication information to a terminal device, the first indication information indicates information of a first time segment, a second time segment and a third time segment, and the first time segment and the second time segment are time segments occupying a first time period. The third time segment comprises at least a part of time segments in each second time segment in the plurality of first time periods; and the first network equipment sends second indication information to the terminal equipment, wherein the second indication information indicates that the first signal occupies the first time segment or the second time segment. Thus, more resources can be scheduled at the same time at one time, the target with the high speed can be sensed for the sensing signal, and the sensing capacity is improved.

This application relates to the field of communication technologies, and discloses a communication method, apparatus, and system. The method includes: A terminal determines predicted values of first-type measurement quantities of a plurality of cells at at least one time point in a first time period, where the plurality of cells include a serving cell and a candidate cell; and if the predicted values of the first-type measurement quantities of the plurality of cells at the at least one time point satisfy a reporting condition, sends measurement report information to a network device.

The embodiment of the invention provides a pilot signal transmission method, device and system, which are used for reducing the correlation of pilot signals in the same time period. The method can be applied to a first terminal device, and comprises: generating pilot signals respectively corresponding to at least two time units, the pilot signals respectively corresponding to the at least two time units being different; and respectively sending corresponding pilot signals to the network device on the at least two time units.

The invention provides a user task processing method and device, equipment and a medium. In one method, user input represented in a natural language from a user is received, the user input indicating a task to be performed. A task type of the task is determined based on the user input. And in response to determining that the task type indicates that the execution result of the task cannot be obtained within the predetermined time period, creating a subsequent task of the task so as to provide the execution result of the task by utilizing a machine learning model when the trigger condition of the task is met. By utilizing the exemplary implementation mode of the invention, the user task which cannot obtain the execution result of the task within the preset time period can be processed in a more flexible and effective mode.

The invention provides a measurement and control task scheduling method based on an equipment idle time period. The measurement and control task scheduling method comprises the following steps: S1, acquiring a task demand, a resource scheduling scheme and forecast data; s2, extracting demand information of each task demand, screening according to the demand information to obtain consistent forecast data, and generating an equipment selectable task segmental arc matrix; s3, extracting an idle time period of each antenna device to construct a task scheduling plan matrix; s4, according to the idle time period of each antenna device and the demand information of each task demand, re-planning selectable task arc segments in the device selectable task arc segment matrix and recording the re-planned selectable task arc segments into a task scheduling plan matrix; and S5, controlling each antenna device to execute a measurement and control task and / or a data transmission task on each satellite, and analyzing to obtain a measurement and control task satisfaction degree and a data transmission task satisfaction degree. The method has the beneficial effects that the idle time period of the antenna equipment can be effectively utilized for task replanning, and the equipment utilization rate and the task completion rate are improved.

The invention belongs to the technical field of behavior prediction, and particularly relates to a ship anomaly detection method and device based on TCN trajectory prediction. The method comprises the following steps: S1, acquiring AIS data given by a ship automatic identification system in a set time period before the current moment; s2, predicting the position of the ship at the next moment based on a pre-trained time convolutional network; s3, determining an error between the actual position and the predicted position of the ship at the next moment; s4, when the error exceeds a threshold value, determining that the position is an abnormal point; s5, continuously appearing abnormal points serve as abnormal track segments, the time length of the abnormal track segments serves as a weight calculation factor, and the abnormal scores of the abnormal track segments are calculated; and S6, determining the abnormal level of the abnormal track segment according to the abnormal score and the plurality of abnormal degree intervals. According to the invention, the detection precision of ship abnormal behaviors is improved.

The invention relates to the technical field of data analysis, in particular to an ultra-low temperature refrigerator based on operation data analysis, which comprises the steps of forming a fluctuation event sequence under multiple time periods by regarding a time period corresponding to temperature fluctuation as a fluctuation event; dividing the fluctuation event sequence into event types corresponding to fluctuation events according to values in an operation period, and calculating a fluctuation duration proportion under each time segment; defining temperature state transition of a plurality of fluctuation events under each fluctuation duration proportion, combining the fluctuation events according to a plurality of time periods, and solving a fluctuation event combination probability; performing correlation analysis on the fluctuation events by taking the event attributes and the temperature characteristics of the fluctuation events as input to obtain related factors of the combined fluctuation events; carrying out multi-objective solution according to related factors of the fluctuation event, solving an optimal control parameter combination, and taking the optimal control parameter combination as an output control strategy; the control efficiency of the refrigerator and the accuracy of temperature regulation and control are achieved.

The invention relates to the technical field of computer processing, in particular to a Kafka cluster configuration parameter adjusting method and device, equipment and a medium, and is used for relieving problems caused by a fixed change means of code modification. The method comprises the following steps: according to related historical data of a Kafka cluster, predicting a first predicted load index in a future time period through a first time sequence model, and predicting a second predicted load index in the future time period through a second time sequence model; weighting the first predicted load indicator; weighting the second predicted load index; determining a predicted load index according to the weighted first predicted load index and the weighted second predicted load index; determining a plurality of first candidate adjustment actions according to the predicted load index; selecting a first candidate adjustment action from the plurality of first candidate adjustment actions as a first adjustment action; and adjusting a partition allocation index and a copy allocation index of the Kafka cluster configuration parameters by using the first adjustment action.

The invention provides an NTN feeder line link time delay parameter determination method and device, a base station and a storage medium, and the method comprises the steps: solving satellite-ground distances corresponding to a plurality of sample moments of a detection time period according to ephemeris information and epoch time corresponding to the detection time period by the base station; according to the method, the fitting coefficient of the distance time function corresponding to the detection time period is determined by performing curve fitting on the satellite-ground distance, and the public time delay parameter is determined according to the fitting coefficient, so that the accuracy and the efficiency of determining the public time delay parameter are improved; therefore, the user terminal can accurately estimate the public time delay of the feeder line link according to the public time delay parameter and perform corresponding timing compensation, signal synchronization is ensured, and the technical problem that the base station cannot accurately determine the public time delay parameter in the prior art is solved. In addition, the variation trend of the satellite-to-ground distance in a long time period can be determined according to the calculation of fewer sample points, and the accuracy of time delay evaluation is ensured with lower operation overhead.

The invention relates to the technical field of data processing, in particular to an artificial intelligence-based information recommendation method and system, and the method comprises the steps: obtaining the push information of a user in a preset historical time period, and obtaining the information cocoon house depth of the user according to the push information of the user; according to the reading duration of the user for each piece of push information, obtaining the satisfaction degree of the user for the push information; combining the information cocoon house depth and the satisfaction degree to obtain an information recommendation degree; obtaining a difference between two adjacent reading durations of the user for the push information of the same attribute, and obtaining an information acceptance degree of the user for the push information of each attribute; according to the information recommendation degree and the information acceptance degree, information recommendation is performed on the user, more comprehensive data information can be recommended to the user, pushing limitation is eliminated, pushing diversity of the data information is realized, and the user can effectively contact new interests or potential demands.

The invention discloses an energy consumption prediction and optimization system and method based on artificial intelligence, and relates to the technical field of energy consumption prediction and optimization, and the method comprises the following steps: calculating the energy consumption intensity indexes of all devices in different time periods, and forming a time segment set of historical energy consumption abnormity of the devices; generating a candidate scheduling strategy, for any strategy, obtaining an equipment calling sequence and energy consumption switching time between equipment, and when the scheduling time of the equipment falls into a historical energy consumption abnormal paragraph set, calculating the actual operation energy consumption of the equipment in an abnormal time period; traversing the equipment calling time in the strategy to calculate the actual total energy consumption and the number of times exceeding the predicted energy consumption, calculating the energy efficiency matching value of each candidate strategy, and generating a strategy recommendation sequence; and selecting the strategy with the highest energy efficiency matching value from the strategy recommendation sequence as a preferred execution scheme, collecting real-time energy consumption data after execution, calculating an energy consumption deviation rate, comparing the energy consumption deviation rate with a threshold value, and judging the effectiveness of the strategy, so that energy consumption prediction and optimization are realized.

The invention provides a communication method and a communication device, which are applied to a service scene with low-delay and high-reliability requirements, and particularly applied to a URLLC (Uniform Resource Logical Link Control) scene. The method comprises: sending first indication information, the first indication information being used for indicating at least one sub-band full duplex SBFD time period, the time period comprising at least two types of SBFD time units, each type of SBFD time unit comprising an uplink sub-band and a downlink sub-band, the sub-band configurations of different types of SBFD time units being different; and independently configuring a control resource set CORESET resource for each type of SBFD time unit in the at least two types of SBFD time units. The scheme of the invention can support the demand of transmitting downlink control information at any time in a service scene, thereby reducing the time delay and improving the communication performance.

The invention provides an elevator maintenance period prediction method based on endogenous and exogenous variable multi-granularity embedding. The elevator maintenance period prediction method comprises the steps that collected elevator operation parameters are divided into endogenous variables and exogenous variables; dividing the endogenous variable into a plurality of non-overlapping time slices, and mapping the time slices into patch-level tokens for processing; and the exogenous variables are mapped to the low-dimensional feature space to form respective series-level tokens. According to the method, a learnable global token is introduced to represent the macroscopic state of the whole endogenous variable, and information fusion among different granularities is promoted; according to the method, the strong capacity of a Transform architecture is utilized, complex association between endogenous and exogenous variables is captured through a cross attention mechanism, and the association is further strengthened through interaction between global and local tokens, so that the model can more accurately understand the influence of internal and external factors on the elevator maintenance period. Through the method, prediction precision and robustness are improved, and higher accuracy and reliability are shown in elevator maintenance period prediction.