178 results about "Congestion prediction" patented technology

Provided are a method and an apparatus for constructing a road congestion prediction model, a device, a medium, and a product. A road traffic network is defined as a directed weighted graph. Historical dynamic traffic features of each road segment in the road traffic network are obtained as sample data, including recent dynamic traffic features and periodic dynamic traffic features. The sample data is input into a mixture of adaptive graph learners (MAGL) model for learning, and a probability prediction vector is output. The sample data is input into a trend expert model, and a trend distribution vector of a predicted probability of future traffic conditions is output. The periodic dynamic traffic features are fused to determine a periodicity prediction vector. An aggregated logit vector is obtained. An objective function is determined based on the aggregated logit vector. Congestion prediction training is performed to obtain a road congestion prediction model.

The invention discloses a multi-AGV cooperative path planning and scheduling method for chip intelligent storage, and belongs to the field of high-precision electronic component intelligent storage. The method comprises the following steps: running according to a highway guide strategy, and pre-allocating tasks of each robot by using an MTSP problem according to different task types before path planning; an improved A * algorithm is provided, a global thermodynamic diagram congestion prediction and turning waiting heuristic method is introduced to establish a space-time joint search model, and a transportation path is optimized by greatly reducing the number of nodes needing to be searched and the turning and waiting times of the AGV, so that the efficiency is improved; in addition, a series of priority rules are also provided, and appearing conflicts are eliminated. Experiments verify the effectiveness of the method, high-reliability and low-vibration dust-free workshop AGV collaborative scheduling can be realized, and an efficient and safe warehousing automation solution is provided for semiconductor manufacturing.

The invention provides an expressway variable speed limit control method, system and device and a medium, and belongs to the technical field of intelligent traffic management. The method comprises the following steps: collecting traffic flow data, road condition data and weather data in real time; preprocessing the collected data, and predicting a traffic jam trend and a safety risk index through a machine learning algorithm; determining weight factors of traffic flow, safety risk and congestion prediction through an analytic hierarchy process; dividing a road section speed range by using a clustering algorithm, and calculating a road section unit speed; constructing a target function which aims at maximizing the unit speed of the road section and minimizing the safety risk and the congestion time; and based on the target function, solving an optimal speed limit value by adopting a particle swarm optimization algorithm, and dynamically issuing speed limit information in different lanes. The highway traffic big data is analyzed in real time, the speed limiting strategy is intelligently formulated, the speed limiting strategy is published to the driver in real time through multiple channels, and the passing efficiency and safety of the highway are effectively improved.

The invention discloses a road congestion prediction system and method based on spatial-temporal feature extraction, and belongs to the field of intelligent traffic. The system adopts a layered distributed architecture, and comprises a multi-source data acquisition module, a data preprocessing unit, a double-flow spatio-temporal feature extraction network, a two-stage spatio-temporal attention mechanism module, a congestion prediction model and a result feedback interface. Multi-modal data such as a vehicle-mounted GPS track, checkpoint flow, video monitoring and meteorological data are integrated, a double-flow feature extraction network is constructed by adopting a graph convolutional network and a bidirectional gating circulation unit, and a key space-time region is dynamically focused in combination with a multi-head self-attention and time weighted dot product attention mechanism; and finally, optimizing the generalization ability of the model through a composite loss function. According to the method, a dynamic adaptive learning framework and multi-source data combined modeling mode is adopted for urban road traffic flow characteristics, the space-time precision and the real-time response capability of road network congestion prediction are remarkably improved, and reliable decision support is provided for intelligent traffic control.

The invention discloses an intelligent scheduling method and system for port trailers, and the method comprises the steps: obtaining the state information of a trailer and the information of a target operation region when the trailer arrives at a port fork, and generating a plurality of feasible paths based on the position of the fork and the target region, and obtaining the real-time state of each path trailer, substituting the real-time state into the congestion index prediction model to calculate a congestion index value, screening out an actual path set overlapped with the feasible path, excluding paths with high-priority trailers and congestion indexes exceeding a threshold value according to a trailer operation priority rule, and selecting the path with the minimum congestion index value from the residual paths as a scheduling path. According to the invention, accurate congestion prediction is realized through multi-dimensional data and the model, emergency operation traffic is guaranteed in combination with a priority rule, the path is dynamically optimized, the waiting time is reduced, the road load is balanced, the port trailer scheduling efficiency and safety are improved, and the method adapts to fine management requirements of intelligent ports.

The invention discloses an L-shaped conveyor belt path dynamic planning and congestion prediction system, which relates to the technical field of automatic control, and constructs a conveying path node diagram by collecting material weight, speed and spacing information of each node on a conveying path, and calculates a congestion index of each path section; the method comprises the following steps: combining a light-mass material jumping sensitivity model, identifying a high-risk node and marking the high-risk node as a congestion prediction area, constructing a dynamic optimization model based on path risk distribution and a material flow direction, generating and evaluating a plurality of path adjustment strategies, executing an optimal strategy according to priority, and realizing path speed adjustment, standby path switching and feeding rhythm control; through a feedback mechanism, a strategy effect is evaluated in real time, a path state is updated, operation data is synchronized to a historical database, a learnable conveying operation file is formed, the stability and the intelligent response capability of a conveying system can be effectively improved, and the method is suitable for high-speed sorting and automatic packaging scenes.

The invention provides a traffic control protection method, device and equipment based on congestion prediction, and aims to accurately identify a congestion rule and predict a propagation path by constructing a feature vector set based on historical data and a congestion propagation path prediction mechanism so as to realize timely release of congestion early warning information. Risk assessment grading protection and optimal intervention opportunity dynamic optimization are adopted, the protection opportunity is accurately mastered, and corresponding protection intensity is matched; a regional risk redistribution strategy and a protection effect gradient analysis technology are introduced, risk transfer control among multiple regions is coordinated, and disordered diffusion of congestion risks is avoided; in combination with cross-space-time effect tracing analysis and a strategy conflict detection mechanism, the actual contribution degree of each protection element is evaluated, and a weight adaptive strategy set and a protection capability matrix are constructed; finally, multiple links such as prediction, evaluation and coordination are fused to form a self-adaptive comprehensive protection system, and active prevention and intelligent management and control of urban traffic congestion are realized.

The invention relates to the technical field of artificial intelligence, and discloses an internet television regulation and control method and device, a storage medium and electronic device.The method comprises the steps that network topology data, real-time performance parameters, user behavior data and environment data of nodes of an internet television are collected in real time through a space-time hypergraph convolutional network, a dynamic hypergraph model is constructed, and the network topology data of the nodes of the internet television, the real-time performance parameters of the nodes of the internet television and the environment data of the nodes of the internet television are obtained; extracting a spatial feature matrix and a time feature matrix of the nodes of the Internet television; performing feature fusion on the spatial feature matrix and the time feature matrix to generate a congestion probability prediction result of each node of the Internet television; and based on a congestion probability prediction result, combining historical flow data, generating a resource allocation optimal strategy by using multi-target Bayesian optimization, and training and updating a congestion prediction model by using a lightweight federated incremental learning framework. The Internet television regulation and control method provided by the invention is further improved in the aspects of network congestion prediction precision, real-time performance, energy consumption and the like.

The invention relates to the technical field of artificial intelligence, in particular to a multi-objective optimization-based adaptive learning task scheduling system, which comprises the following contents: a dependency identification module, an energy consumption analysis module, a bottleneck modeling module, a delay judgment module and an isolation migration module. According to the method, through dependence identification of a task resource calling sequence, acquisition precision of an implicit relationship between tasks is improved, a resource allocation strategy under energy consumption driving is optimized by utilizing an occupancy rate of a node processor, activity of a graphic calculation unit and power supply consumption change, and an I / O interval gravity center shift trend is combined, so that communication congestion prediction capability is enhanced; the abnormal node recognition accuracy is improved by combining the response duration change trend with the node load state, the temperature deviation continuity and the thermal diffusion fluctuation characteristics are used, the thermal imbalance node is sensed in time, task migration is achieved, the node overload rate is effectively reduced, I / O accumulation is relieved, and the continuity and stability of learning task execution are improved.

The invention relates to a traffic state perception and control method based on laser vision fusion, and relates to the field of intelligent traffic, and the method comprises the steps: obtaining vehicle images and point cloud data through a traffic monitoring system of a highway entrance ramp, carrying out the vehicle static feature recognition and track reconstruction, and carrying out the analysis to obtain multi-dimensional parameters; according to the method, the traffic flow monitoring means such as license plate attribution distribution, vehicle type distribution and running speed mean value are selected, the congestion condition is predicted, the predicted congestion coefficient is output, and finally a traffic control scheme is formulated and executed according to the predicted congestion coefficient, so that the problems of insufficient data accuracy and reliability caused by single traffic flow monitoring means are solved; the method solves the technical problems of low prediction comprehensiveness and low prediction precision caused by traffic congestion prediction, effectively improves the accuracy and reliability of congestion prediction, provides a scientific basis for traffic management, and is helpful for optimizing traffic flow and reducing congestion.

The invention relates to an intelligent port cargo scheduling method based on the Internet of Things, and the method comprises the steps: collecting cargo state information, equipment position coordinates, operation progress data and environment parameters in real time through Internet of Things sensor nodes disposed on a quay crane, a container truck, a storage yard sling and a cargo carrier, and fusing a port GIS map and a berth plan based on the real-time collected data, and establishing a multi-objective optimization model with maximization of the quay crane-container truck-storage yard cooperative efficiency as an objective and minimization of equipment conflict avoidance and path overlap as constraint conditions, and dynamically activating or sleeping storage yard operation partitions and adjusting the number of container truck marshalling according to the obtained storage yard congestion prediction index and the parking space vacancy rate.

The invention belongs to the technical field of electronic government affair big data processing, and discloses an electronic government affair big data processing system and method. The system comprises a traffic data acquisition module, a depth data acquisition module, a data interaction extraction module, a traffic quantitative prediction module, an auxiliary decision generation module, a causal reasoning interpretation module, a vulnerable group inclination module and a data distinguishing processing module, and is used for analyzing feature vectors to obtain a congestion prediction value, analyzing the congestion prediction value, and obtaining a traffic prediction result. The method comprises the following steps: analyzing a congestion prediction value, obtaining an auxiliary decision report according to an analysis result, performing causal inference on the auxiliary decision report, combining an inference result with the auxiliary decision report to obtain a causal inference report, performing calculation based on region type data and complaint evaluation data, and correcting the congestion prediction value according to a calculation result to obtain a prediction correction value. The method has the remarkable advantages of being high in traffic condition prediction accuracy, high in data mining capacity and large in management balance effect.

The invention discloses a data transmission monitoring method and system based on a switch, and the system comprises an index collection and monitoring module, an early warning threshold adjustment module, a congestion degree comprehensive judgment module, a congestion optimization module, and a congestion prediction module, and relates to the technical field of switch data transmission. The method comprises the following steps: continuously monitoring the queue length of each port of a switch, setting a plurality of early warning threshold types, monitoring the data transmission rate of each port in real time, and establishing a historical congestion database according to a historical congestion condition. The multi-index comprehensive monitoring mode can more comprehensively reflect the network state, and compared with a single-index congestion judgment method, the accuracy of judging the network congestion degree is greatly improved.

The invention provides a hybrid vehicle energy management system and method based on a traffic state, a storage medium and a computer program product, and the system comprises the steps: constructing a congestion prediction model based on a deep learning model, the congestion prediction is used for predicting the traffic flow and the driving speed of a future time period according to the historical traffic flow data and the historical driving speed data; calculating a first congestion index according to the predicted traffic flow in the future period; calculating a second congestion index according to the predicted driving vehicle speed sequence of the future time period; performing weighted calculation on the first congestion index and the second congestion index to obtain a comprehensive traffic congestion index in a future time period; traffic jam types are divided according to the interval where the comprehensive traffic jam index is located; and determining an energy management mode and / or a target SOC of the hybrid vehicle based on the traffic jam type. According to the invention, multi-source data are collected and analyzed in real time, congestion is accurately quantified by using a deep learning algorithm, an energy distribution strategy of vehicles is dynamically adjusted, and the energy utilization efficiency is improved.

The invention discloses an expressway congestion prediction method and system based on fusion of a cellular transmission model and a space-time convolutional network. According to the method, an expressway is divided into continuous cellular units, speed and density data of each cellular in multiple periods are collected, and a space-time input sequence is constructed. Local state correlation between cells is extracted through spatial convolution, and then a causal convolution network is used for modeling a time evolution trend of a traffic state, so that joint prediction of speed and density in a plurality of time steps in the future is realized. According to the invention, the spatial discretization idea of the cellular transmission model and the feature extraction capability of the convolutional neural network are combined, so that the provided method not only retains the interpretability of traffic flow physical evolution, but also has the capability of learning a nonlinear complex mode; the method is suitable for application requirements of traffic situation monitoring, intelligent scheduling, congestion management and the like in various expressway operation scenes.

The invention discloses an intelligent electric vehicle queue optimization method based on congestion prediction and DRL. The method comprises the following steps: (1) modeling a queue position optimization problem of an electric vehicle queue into a mathematical model which takes energy balance as a target and is constrained by a traffic environment; and (2) solving the mathematical model in the step (1) by adopting a DRL method based on a TRPO algorithm to obtain an optimal queue adjustment strategy of the electric vehicle queue. In the step (2), congestion state information in an external traffic environment is obtained through an LSTM traffic prediction and FCM method, and the congestion state information, the remaining electric quantity of each vehicle in the motorcade and the accumulated driving distance are jointly used as state input of a TRPO algorithm; according to the TRPO algorithm, a strategy network and a value network are adopted to respectively obtain a strategy for adjusting the queue position, and the return expectation in the current state is evaluated. The TRPO algorithm dynamically adjusts the updating step length of the strategy through the KL divergence updated by the constraint strategy, and guarantees the stability and convergence in the strategy updating process.

The invention specifically relates to a smart parking lot traffic management system based on traffic Internet of Things, and relates to the technical field of smart traffic and Internet of Things. A data processing and fusion module; a congestion prediction module; a prediction optimization module; and an induction information generation and release module. According to the invention, through multi-dimensional data acquisition, fusion and model optimization, accurate pre-judgment and dynamic adaptation of parking lot congestion are realized; the congestion prediction module constructs a multi-dimensional feature system of stagnation degree, unit average delay degree and occupancy degree, covers core inducements of vehicle retention, parking efficiency, resource mismatch and the like, combines historical data optimization factors and k value dynamic adjustment, and enables the prediction model to continuously adapt to changes of parking lot vehicle types, user habits and the like. Passive response of congestion treatment is upgraded to active prevention, invalid wandering of vehicles and lane congestion are reduced, the parking lot passing efficiency and the parking space turnover rate are remarkably improved, and the operation cost is reduced.

The invention is suitable for the technical field of intelligent traffic, and provides a toll station lane management and control method and device, terminal equipment and a storage medium, and the method comprises the steps: firstly obtaining vehicle track data in at least one upstream sensing area corresponding to a downstream toll station; then, based on the vehicle track data in all the upstream sensing areas, the queuing condition of the downstream toll station is predicted, and a real-time congestion prediction result of the downstream toll station is generated; and finally, according to a real-time congestion prediction result, dynamically managing and controlling lanes of a downstream toll station. Therefore, real-time congestion prediction is performed by using the upstream vehicle trajectory data, and traffic flow changes are coped with by dynamically scheduling the lanes of the downstream toll station, so that flexible management and control of the lanes of the toll station are realized, and the overall traffic efficiency is improved.

The invention discloses a traffic jam prediction management method and system based on artificial intelligence, and a medium, and relates to the technical field of intelligent traffic systems, and the method comprises the steps: collecting multi-source traffic data to construct a space-time traffic data set, carrying out the traffic state classification based on the space-time traffic data set, and generating a multistage jam probability distribution diagram; performing congestion prediction in combination with the multi-stage congestion probability distribution diagram and the real-time traffic event data, and determining a congestion evolution path; and carrying out traffic management according to the congestion evolution path, generating a dynamic dispersion instruction set, and sending the dynamic dispersion instruction set to traffic control equipment of the target road section to carry out traffic congestion management. The technical problems that a traditional traffic management means cannot adapt to complex and changeable traffic conditions, and accurate congestion prediction and efficient management are difficult to achieve are solved, accurate prediction of traffic congestion is achieved, a dynamic dispersion strategy is efficiently generated and executed according to the real-time traffic conditions, and the traffic congestion prediction efficiency is improved. Therefore, the traffic management efficiency and the road traffic capacity are improved.

The invention relates to the technical field of port logistics intelligent analysis, in particular to an inter-port congestion propagation inference method based on Granger causal relationship and reserve pool calculation, which comprises the following steps: constructing a multi-directed container ship transportation network according to AIS ship trajectory data based on an L-space modeling method; quantizing the congestion degree of the port by using the average waiting time of the port as a core index; calculating network features of the container ship transportation network; constructing an initial candidate port set; a machine learning prediction model based on the congestion propagation relation between the ports and reservoir calculation is constructed, and the congestion degree of each port in the next time step is predicted; designing a greedy iterative algorithm based on a Granger causality idea, and optimizing a congestion propagation relation inference result of each port based on a congestion prediction error; and constructing a congestion degree prediction model, and taking the congestion propagation relationship as input to realize prediction of the port congestion degree. According to the invention, congestion propagation between ports can be accurately deduced.

The invention discloses an urban traffic big data congestion prediction method based on deep learning, and the method comprises the following steps: collecting multi-source traffic data in an urban traffic operation process, and constructing a standardized space-time traffic data set; respectively inputting the prediction results into an improved Autoformer model and an improved GKAN model, and respectively generating a first prediction result and a second prediction result; calculating a numerical difference between the first prediction result and the second prediction result, and generating an inconsistency score; executing weighted fusion operation to generate a fusion prediction result; calculating an error value between the fusion prediction result and the observation data, and generating candidate prediction results according to the error value and a preset error threshold value; and comparing the disturbance score with a preset disturbance threshold value to generate a final prediction result. The method realizes joint modeling of model prediction consistency and traffic disturbance state, and has the technical advantages of high prediction precision, strong adaptability and excellent error control capability.

The invention discloses a storage robot cluster management system and method, and belongs to the technical field of robot scheduling. The system comprises a central management server and an autonomous mobile robot cluster. The central management server comprises a congestion prediction and global path planning module; the congestion prediction and global path planning module comprises a congestion prediction sub-module and an A * path planning sub-module with space-time cost; the autonomous mobile robot is internally provided with a multi-sensor sensing and communication module and a local decision module, and the off-line centralized training platform is used for optimizing the local decision module in each autonomous mobile robot through a centralized evaluation network with global information in a simulation environment. The invention provides a hybrid control architecture integrating global path planning, dynamic task allocation and local real-time decision based on multi-agent reinforcement learning, and efficient and smooth cluster collaborative operation can be realized.

The invention discloses a circulation processing method and system based on digital process congestion degree analysis, and relates to the technical field of digital process management. The method comprises the following steps: constructing a network model containing nodes and an association relationship, and representing a task flow path and a weight; real-time data such as to-be-processed task queues, equipment states and environment parameters are collected in a multi-source mode and subjected to cleaning standardization processing; based on static load, dynamic change, equipment reliability and environmental interference characteristics, predicting a future congestion index through an LSTM sequential network; setting a dynamic threshold by combining node importance and a real-time state, and matching a strategy mapping table to generate adjustment strategies such as task shunting and resource redistribution; feedback is monitored after execution, and model parameters are optimized. The system comprises a process modeling module, a data acquisition module, a congestion prediction module, a strategy generation module and an execution feedback module. Through full-process intelligent management, the congestion risk is avoided, and the improvement efficiency and the resource utilization rate are improved.

The invention relates to the technical field of computer network communication and intelligent control, and discloses a switch configuration method and system based on AI adaptive congestion control, and the method comprises the steps: collecting the multi-dimensional feature data of a network in real time through a data plane programmable pipeline of a switch, and transmitting the multi-dimensional feature data to an AI intelligent decision engine through an encryption channel; based on the multi-dimensional feature data, executing congestion prediction, strategy generation and interpretability analysis through an AI intelligent decision engine to obtain a congestion control regulation and control strategy; converting the congestion control regulation and control strategy into an executable switch configuration command, and issuing the executable switch configuration command to switch hardware to dynamically adjust congestion control parameters of the switch; and acquiring the network performance index after configuration execution, calculating the profit value of the congestion control strategy, and updating the model weight of the AI intelligent decision engine based on the profit value. According to the invention, the adaptability of the network to dynamic loads and complex scenes is effectively improved, delay and packet loss are reduced, and the operation and maintenance complexity is reduced.

The invention discloses a multi-level linkage ramp control method and related equipment based on multi-source data fusion, and the method comprises the steps: carrying out the clustering analysis of target multi-source traffic trajectory data, and obtaining travel trajectory feature data; on the basis of the travel track feature data, performing weight calibration on the on-bridge ramp of the expressway to obtain on-bridge ramp control priority data; performing short-time prediction on the current traffic flow data to obtain a short-time flow prediction result; performing congestion prediction according to the short-time flow prediction result and the dynamic bearing capacity of the expressway to obtain a congestion section prediction result; and according to the short-time flow prediction result, the congestion section prediction result and the on-bridge ramp management and control priority data, carrying out ramp control on the predicted on-bridge ramps of the expressway congestion section by adopting a layered management and control strategy. The method can achieve the precise dynamic sorting of the turn-off priorities of the ramps, balances the load of the road network, avoids the secondary congestion, improves the overall traffic efficiency of the road network, and can be widely applied to the technical field of traffic control.

The invention discloses an expressway congestion prediction method, device and equipment, which are used for more accurately predicting the congestion of an expressway. The method comprises the following steps: acquiring historical data of highway detection points, including license plate data and travel data of vehicles; determining the travel speed of each vehicle under the spatial granularity according to the historical data of the highway detection points; the space granularity is the distance between two adjacent detection points; according to the travel speed of each vehicle under the spatial granularity, determining a vehicle average speed change diagram under each spatial granularity in each adjacent equal-length time interval; in the vehicle average speed change diagram, based on a congestion speed threshold value, extracting a speed change characteristic segment before congestion; acquiring the real-time vehicle average speed of the target location of the expressway; generating a real-time vehicle average speed change diagram corresponding to adjacent equal-length time intervals; and matching the real-time vehicle average speed change graph with the speed change characteristic segment before congestion, and determining a congestion risk coefficient of the target location.

The invention discloses a hydraulic engineering management and control system and method based on digital twinning, and relates to the technical field of digital twinning, and the method comprises the steps: firstly collecting and preprocessing channel condition data in real time, then comprehensively processing the data to obtain a sediment deposition factor and a congestion prediction factor, and analyzing whether sediment deposition exists according to the sediment deposition factor and the congestion prediction factor; if yes, whether the channel is congested or not is predicted according to the latter, if congestion is predicted, a congestion early warning is given out, and if no deposition exists or congestion does not exist, the process is ended correspondingly or prediction continues. The method combines flow velocity and flow direction abnormal parameters to form sediment deposition factors, bypasses underwater direct detection bottlenecks by means of digital twin modeling and simulation algorithms, improves sediment deposition judgment accuracy through multi-dimensional analysis, constructs congestion prediction factors based on a standard and actual water flow difference value and the flow direction abnormal parameters, and performs threshold exceeding early warning. The blocking risk is recognized in advance, and time is won for hydraulic engineering maintenance regulation and control.

The invention provides a highway operation and service intelligent system, which comprises a road section platform, an area platform and a road network platform, and is characterized in that the road section platform is used for collecting and summarizing various sensing data of a corresponding highway section based on an ETC system to obtain system business data; road network situation historical statistics, road network situation real-time monitoring and road network situation future prediction are carried out according to the ETC data of the corresponding expressway section and the adjacent expressway road network; and long and short time traffic flow prediction, congestion prediction, holiday and festival traffic flow prediction and traffic flow prediction in a severe weather scene aiming at the corresponding expressway section are realized from multiple angles. According to the invention, the emergency disposal response speed and the intelligent degree of expressway operation and service can be improved, the timeliness rate, the accuracy rate and the correct rate of detection of various traffic and meteorological events can be improved, and the requirements of cooperative monitoring and linkage emergency disposal of low-time-delay traffic safety events are met.

The invention discloses a UWB-based market shopping guide system and method, and relates to the field of intelligent shopping guide, and the system comprises a positioning module, an acquisition fusion module, a model construction module, a shopping guide path generation module, an interference compensation construction module and a credibility evaluation module. According to the method, the problem of insufficient precision of WiFi and Bluetooth methods is effectively solved by combining a time difference arrival and arrival angle combined positioning mode of UWB. A five-level space mapping index is established, direct correspondence between a customer target and an actual position is achieved, and the commodity retrieval and navigation accuracy of the shopping guide system is improved. The machine learning model is used for modeling the residence time, the access frequency and the promotion interaction behaviors of the customers, and the preference distribution of the customers is dynamically calculated, so that personalized recommendation and interest area navigation are provided in the shopping guide process. A congestion prediction model and a customer behavior prediction mechanism are introduced in a path planning process, a high-flow area is dynamically avoided, an optimal shopping path is generated, and shopping guide efficiency and comfort are improved.

The invention aims to provide a heterogeneous EDA data-based multi-task learning QoR prediction method and device, and the method comprises the steps: carrying out the data preprocessing, and obtaining the feature data of non-IID data in different design stages in an EDA process; constructing a multi-task learning model, training the multi-task learning model to optimize loss functions of congestion prediction and DRC violation prediction tasks, and adjusting model parameters to obtain a trained multi-task learning model; generating a prediction result by using the trained multi-task learning model, and optimizing layout and wiring design in an EDA process; according to the method, information sharing among different tasks is integrated through a multi-task learning framework, the relevance among the tasks is fully utilized, the negative migration phenomenon caused by the non-independent identical distribution (Non-IID) characteristic of data is effectively relieved, and therefore the generalization ability and robustness of the model are improved.