Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

819results about How to "Avoid idling" patented technology

Logistics management system based on intelligent scheduling

The invention relates to the technical field of logistics transportation scheduling, in particular to a logistics management system based on intelligent scheduling, which comprises a data acquisition module, a demand analysis module, an intelligent scheduling module, a path planning module, a monitoring and feedback module, an optimization module and the like. The data acquisition module is used for collecting information such as goods, vehicles, storage, customer demands and traffic road conditions; the demand analysis module predicts logistics demands by using a time sequence analysis or machine learning algorithm; the intelligent scheduling module adopts a greedy and dynamic programming mixed algorithm to allocate resources; the path planning module calculates an optimal path according to road conditions and starting and ending points; the monitoring and feedback module monitors logistics parameters in real time and feeds back abnormity; and the optimization module optimizes the scheduling scheme according to the fitness function based on the genetic algorithm. According to the invention, data and resources of all links of logistics are effectively integrated, accurate demand prediction, efficient resource configuration, transportation path optimization, real-time monitoring feedback and overall performance improvement of the system are realized, the logistics cost is significantly reduced, and the transportation efficiency and the service quality are improved.
Owner:FUJIAN ORANGE INFORMATION TECHNOLOGY CO LTD

Big data dynamic allocation and optimal scheduling method based on reinforcement learning

The invention discloses a big data dynamic allocation and optimal scheduling method based on reinforcement learning. The method comprises the following steps: S1, constructing a real-time operation data set; s2, preprocessing the real-time operation data set, and constructing a reinforcement learning environment model; s3, initializing a hierarchical reinforcement learning model; s4, generating an optimal data distribution and scheduling strategy based on the hierarchical reinforcement learning model; s5, adjusting data distribution and task scheduling of each computing node in real time to balance the system load and maximize the resource utilization rate; s6, the hierarchical reinforcement learning model continuously monitors the system state and dynamically updates the strategy, and self-adaptive adjustment is carried out on resource allocation and scheduling in time when the system load or environment changes; and S7, through multi-round iterative optimization, gradually converging the hierarchical reinforcement learning model to an optimal strategy. Through application of reinforcement learning, automatic optimization of resource allocation and scheduling strategies is realized, and the resource utilization rate, the scheduling efficiency and the adaptability of the system are remarkably improved.
Owner:BEIJING XINDAYI TECHNOLOGY CO LTD

Nursing decision scheme optimization analysis system based on artificial intelligence

The invention discloses a nursing decision scheme optimization analysis system based on artificial intelligence, and relates to the technical field of data processing. The system comprises a nursing knowledge base module, a data acquisition and preprocessing module, a nursing scheme matching degree analysis module, a nursing demand prediction module, a nursing scheme optimization module and a nursing scheme monitoring feedback module. According to the nursing decision scheme optimization analysis system based on artificial intelligence, the medical history, the diagnosis result, the physiological parameter data and the real-time nursing record multi-source information of the patient are integrated, comprehensive and dynamic evaluation of the health condition of the patient is achieved, deep mining and analysis are conducted on the data, and therefore more accurate nursing decision suggestions are obtained; individual nursing schemes are provided according to individual differences of patients, pertinence and effectiveness of nursing measures are ensured, in addition, execution conditions of the nursing schemes are monitored in real time, deviation is found and corrected in time, and scientificity and accuracy of nursing decision making are further improved.
Owner:JILIN UNIV FIRST HOSPITAL

Data analysis method, system and equipment based on distributed communication and medium

The invention discloses a data analysis method, system and device based on distributed communication and a medium, and relates to the technical field of data processing, and the method comprises the steps: monitoring a node state in real time based on a distributed communication network, obtaining a node resource state data set, building a node performance evaluation model through a machine learning algorithm, and obtaining a node performance evaluation result; computing resources of the data analysis tasks are dynamically allocated to optimize resource allocation, a task allocation strategy is designed according to requirements and node performance of the data analysis tasks, and a distributed data processing framework is established; the method comprises the following steps: performing distributed decomposition and executing a calculation data analysis task, aggregating and collecting distributed calculation results, and dynamically adjusting and optimizing resource task allocation to obtain a final data analysis result, so that a node state can be monitored in real time, and a resource allocation scheme can be intelligently adjusted; according to the advantages of dynamically optimizing task allocation according to the communication condition and the computing power of the node, the problems of insufficient dynamic resource management and poor task scheduling flexibility in the prior art are solved.
Owner:XIDIAN UNIV

MBB multipath local aggregation superposition transmission method and system

The invention provides an MBB multi-channel local aggregation superposition transmission method and an MBB multi-channel local aggregation superposition transmission system. Belongs to the technical field of communication. The method comprises the following steps that: a plurality of physical links are established in a wireless communication system, and the system selects the plurality of optimal physical links for aggregation according to a current network environment, a current equipment state and a current user demand; dividing data to be transmitted into a plurality of data packets, packaging each data packet according to the characteristics of the selected physical link, and transmitting the packaged data packets in parallel through the selected physical link; in the transmission process, the system monitors the transmission state of each link in real time, and dynamically adjusts the transmission rate and power distribution of each link according to the current network load and equipment state. By transmitting a plurality of physical links in parallel, the network bandwidth can be fully utilized, the data transmission rate is improved, and the transmission delay is reduced.
Owner:BEIJING ZHONGYUAN YISHANG TECH CO LTD

Edge cloud computing load balancing method

The invention relates to the technical field of edge cloud computing, discloses an edge cloud computing load balancing method, and aims to solve the load balancing problem caused by wide node distribution, limited resources and dynamic change in an edge computing environment. A traditional load balancing algorithm is based on a static data allocation request, cannot accurately predict future load change, and easily causes node overload or resource idling. According to the method, a neural network algorithm, especially a long-short term memory (LSTM) network model, is adopted to construct and train a load prediction model, and the future load level of the edge computing node is predicted according to the historical use condition of the edge computing node. A monitoring and data acquisition system is deployed, factor data influencing node loads are collected in real time and input into a prediction model, and a resource scheduling strategy is dynamically formulated. According to the method, the dynamic and efficient utilization of the edge computing nodes is realized, the response speed and the operation efficiency of the system are improved, and the user experience is optimized.
Owner:JIANGXI GONGBO NETWORK TECHNOLOGY CO LTD

Self-adaptive computing power scheduling system for large model training

The invention provides a self-adaptive computing power scheduling system for large model training, and relates to the field of electric digital data processing, the self-adaptive computing power scheduling system comprises a computing power management module, a task analysis module, a self-adaptive scheduling module and a data interaction module, the computing power management module is used for managing and monitoring overall computing power resources, and the task analysis module is used for analyzing the overall computing power resources; the task analysis module is used for analyzing requirements and characteristics of training tasks, the self-adaptive scheduling module performs computing power scheduling according to real-time resource conditions and task requirements, and the data interaction module is used for managing data interaction among different computing power nodes; according to the system, the training efficiency can be effectively improved by assigning the training tasks to different nodes and adjusting the allocated resources in the task execution process.
Owner:GLOBALTOUR GROUP LTD

Intelligent task optimization method based on adaptive multi-dimensional dependency graph and dynamic scheduling

The invention relates to task scheduling, in particular to an intelligent task optimization method based on a self-adaptive multi-dimensional dependency graph and dynamic scheduling, which comprises the following steps of: inputting task information and resource information; constructing a self-adaptive multi-dimensional dependency graph according to the task information; in the task execution process, the task state of each task is monitored in real time, and the self-adaptive multi-dimensional dependency graph is dynamically updated; calculating the effective priority of the current task, and updating the effective priority of the current task according to the updated adaptive multi-dimensional dependency graph; dynamically scheduling the current task by adopting a dynamic scheduling algorithm; monitoring a task execution state and a resource use condition of each task in real time; according to the task execution state and the resource use condition, whether dynamic scheduling needs to be adjusted or not is judged until all tasks are executed; according to the technical scheme, the defect that in the prior art, accurate and efficient task optimization scheduling is difficult to carry out under the multi-dimensional dependency relationship between the tasks can be effectively overcome.
Owner:ANHUI GAOSHAN TECH CO LTD

Digital hydraulic pump test bed and digital hydraulic pump control performance verification method

The invention provides a digital hydraulic pump test bed and a digital hydraulic pump control performance verification method. The invention provides a digital hydraulic pump test bed. The digital hydraulic pump test bed comprises a driving module and a loading module, wherein the driving module comprises a tested hydraulic pump, a direct-current adjustable-speed motor, a plurality of couplings and a shock absorber, one ends of the couplings are connected with the tested hydraulic pump, the other ends of the couplings are connected with the direct-current adjustable-speed motor, the shock absorber is connected with the direct-current adjustable-speed motor, and the sensors are installed on the tested hydraulic pump; a plurality of pressure oil ports of the tested hydraulic pump are connected with the loading module, the loading module comprises a bridge loop and a loading loop, the plurality of pressure oil ports are respectively connected with a first series connection point and a second series connection point of the bridge loop, and a parallel connection point of the bridge loop is connected to the loading loop. The digital hydraulic pump test bed and the digital hydraulic pump control performance verification method are used for verifying the key control performance of the digital hydraulic pump and are wide in application range.
Owner:ZHEJIANG UNIV

Computer and cloud computing power optimization method based on multi-task collaboration

The invention relates to the technical field of computing power optimization, and provides a computer and cloud computing power optimization method based on multi-task collaboration. The method comprises the following steps: receiving Q to-be-executed tasks of a local cloud collaborative network; performing priority constraint on the Q to-be-executed tasks according to the multivariate priority evaluation factors, and establishing a task chain; collecting callable computing resource information of a local cloud collaborative network, and establishing a resource space; based on the resource space, performing task chain resource allocation by utilizing a computing resource scheduling optimization algorithm to obtain a scheduling strategy chain; performing cloud computing power balance optimization according to the scheduling strategy chain to obtain an optimized chain; and executing the task chain according to the optimization chain based on the cloud collaborative network. The technical problems of unbalanced scheduling and low resource utilization rate between the cloud and the local computing resources are solved, and the technical effects of improving the cooperative work efficiency and the resource utilization rate of the cloud and the local computing resources through priority constraint and computing resource scheduling optimization are achieved.
Owner:SHENZHEN OUYANG MAILE TECH CO LTD

Method and system for realizing capacity expansion / reduction in artificial intelligence scene

The invention provides a method and a system for realizing capacity expansion / reduction in an artificial intelligence scene. The method comprises the following steps: monitoring system performance and service performance to obtain performance indexes; based on the obtained performance indexes, a real-time updating plan and an off-line elastic plan are made respectively, and the real-time updating plan and the off-line elastic plan both comprise the number of target resources; the offline elastic plan is constructed based on machine learning of historical indexes; and determining a capacity expansion / reduction scheme based on a comparison result of the target resource quantity in the real-time update plan, the target resource quantity in the offline elastic plan and the current resource quantity and in combination with a set strategy.
Owner:SASI DIGITAL TECHNOLOGY (BEIJING) CO LTD

Catalyst scheduling control method applied to weather modification operation of airplane

The invention relates to the field of weather modification, and discloses a catalyst scheduling control method applied to aircraft weather modification, comprising: acquiring target weather modification information, the target weather modification information comprising weather modification demand information and a target modification area; inputting the real-time cloud layer information of each job sub-region into a pre-trained deep learning model to obtain a cloud layer category corresponding to each job sub-region; screening the plurality of operation sub-regions according to the weather operation demand information and the cloud layer category corresponding to each operation sub-region to obtain a catalyst standard putting region group; adjusting the preset reference putting amount corresponding to each catalyst standard putting area to obtain the catalyst putting amount of each catalyst standard putting area; and according to the catalyst diffusion speed, determining a catalyst feeding speed corresponding to the catalyst standard feeding area. Therefore, the accuracy and the high efficiency of artificial influence weather operation are realized.
Owner:山西省人工影响天气中心

Self-adaptive resource scheduling method for improving cluster reconstruction efficiency

The invention discloses a self-adaptive resource scheduling method for improving cluster reconstruction efficiency, and relates to the field of resource scheduling distribution, and the method comprises the steps: monitoring the resource use data of each node in a cluster in real time through a monitoring agent, and obtaining the health state of the node through a heartbeat mechanism; collecting input task requests, predicting the resource demand quantity of each task, and performing preliminary queue processing on the tasks to obtain a task queue group; setting a resource competition constraint according to the task queue group and the resource use data and the health state of each node, obtaining dynamic resource scheduling corresponding to each task by using an optimization algorithm, and allocating the tasks to each node; a resource scheduling dynamic graph is constructed, a visual interface is set, and the resource scheduling dynamic graph is arranged on the visual interface and used for displaying resource scheduling, providing a user-friendly interface and realizing high-efficiency scheduling of adaptive resources in a cluster reconstruction process.
Owner:SHANGHAI KANRONG INFORMATION TECH DEV CO LTD

5G communication data transmission management system

The invention discloses a 5G communication data transmission management system, which relates to the technical field of communication data transmission and comprises a real-time resource monitoring module, an intelligent evaluation module, a feature extraction module, a transmission process division module, a normal transmission management module and an overload transmission regulation and control module, through a deployed network monitoring tool and performance monitoring software, the resource occupation condition in the video monitoring data transmission process is monitored in real time. According to the invention, the system intelligently evaluates the resource occupation condition through real-time monitoring and a machine learning model, and dynamically regulates and controls the resources, reduces the delay, accelerates the analysis speed and guarantees the emergency response in the case of high load by using the queue expansion index, the link fluctuation index and the queue theory model. Through transmission process division, efficient management in a normal stage and dynamic optimization in an overload stage are realized, timely response and resource release are ensured, waste is avoided, and the stability and efficiency of the system under various loads are improved.
Owner:NANJING ZHIGAN SPECTRUM INFORMATION TECH CO LTD

Hospital operation analysis and target management system based on big data

The invention discloses a hospital operation analysis and target management system based on big data, and relates to the technical field of hospital operation management, and the system employs an activity-based cost method ABC, introduces a non-linear sharing function and a multi-dimensional cost sharing model, enables the operation cost to be refined to a specific project of each department, and improves the operation efficiency. Equipment use, medicine consumption and working hours of medical staff are covered, cost allocation and updating are carried out through a dynamic adjustment mechanism and a system according to real-time resource use conditions, hospitals are helped to identify high-cost expenditure points, resource waste is reduced, transparency of operation cost and management efficiency are improved, an automatic feedback mechanism is introduced, and the system is convenient to use. According to the method, the predicted data and the actual data can be compared in real time, the operation abnormity can be identified, the adjustment suggestion is automatically triggered when the abnormity is found, the adjustment suggestion is pushed to the related management personnel for quick response, and compared with a manual examination method, the speed and the accuracy of management response are improved.
Owner:BEIJING KANGLIAN TIMES MEDICAL RESEARCH INSTITUTE CO LTD

Server downtime automatic processing method and device, data processing unit and medium

The invention relates to the technical field of computers, and discloses a server downtime automatic processing method and device, a data processing unit and a medium, the method is executed by the data processing unit installed on a to-be-tested server, and the to-be-tested server has a power supply function in a soft shutdown state. The method comprises the following steps: receiving an indication signal of downtime of a to-be-tested server sent by a cloud server; identifying the current state of the to-be-tested server according to the indication signal; according to the current state of the to-be-tested server, fault log information corresponding to the current state is collected; and transmitting the fault log information to a cloud server. The method does not affect the test progress and efficiency and does not increase the labor cost even under the condition of no attending personnel. The effect of the method is particularly obvious when a plurality of test prototypes of a plurality of projects have problems, and the situation of loss caused by the fact that the problems cannot be solved in time can be avoided as far as possible.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Inference method, inference system, inference device, equipment and storage medium

The invention provides a reasoning method, a reasoning system, a reasoning device, equipment and a storage medium, and relates to the field of data processing, in particular to the technical fields of artificial intelligence, big data, large models and the like. According to the specific implementation scheme, a first task request is received through a first scheduling service in a plurality of scheduling services, and the first task request is a request which is sent by a first reasoning service in a plurality of reasoning services and at least carries a model identifier and current idle reasoning resources of the first reasoning service; determining a target reasoning request matched with the first task request based on a model identifier and idle reasoning resources carried by the first task request; and sending the target reasoning request to a first reasoning service through the first scheduling service.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Winding equipment for wire and cable processing

The utility model provides winding equipment for wire and cable processing, which relates to the technical field of wires and cables and comprises a bottom plate, the upper surface of the bottom plate is fixedly connected with a guide component, and one side of the upper surface of the bottom plate, which is far away from the guide component, is fixedly connected with a rotating component. During use, through cooperative use of the first motor, the threaded rod, the fixed rod, the moving block and the guide ring, when the output end of the first motor drives the threaded rod to rotate and the moving block drives the guide ring to reciprocate, the moving path of a wire and a cable can be guided; according to the winding equipment for the wire and cable processing, the wire and cable are uniformly wound on the winding roller in the winding process, the situation that the wire and cable are easily stacked on one side of a wire spool in the process that the wire and cable are directly wound by the wire spool is avoided, and the winding effect of the winding equipment for the wire and cable processing is improved.
Owner:QINGDAO JINSONG CABLE CO LTD

Electric energy conversion equipment of photovoltaic energy storage micro-grid system

The invention relates to the technical field of electric energy storage, in particular to an electric energy conversion device of a photovoltaic energy storage micro-grid system, which comprises a protection bin, one side of the protection bin is provided with an openable front cover, the middle part of the protection bin is recessed inwards to form a placement cavity, and a plurality of batteries are arranged in the placement cavity. A liquid storage tank is further arranged in the containing cavity, a water pump for sucking cooling liquid is arranged below the liquid storage tank, a heat conduction pipe is arranged at the output end of the water pump, a plurality of cooling devices are arranged outside the batteries, and a moving device for driving the batteries to move is arranged between the batteries and the containing cavity. Through cooperation of structures such as a first cooling plate, a second cooling plate, a first surrounding pipe, a second surrounding pipe and a conveying pipe, cooling liquid is conveyed into the cooling box through the conveying pipe, the cooling liquid is contained and cooled in the cooling box, the cooling liquid is rapidly cooled, the water cooling effect is improved, and the continuous cooling effect on a battery is improved.
Owner:PEKING UNIV ORDOS RES INST OF ENERGY

Computing power directional scheduling method and device of intelligent computing center

The invention relates to the technical field of computing power, and provides a computing power directional scheduling method and device for an intelligent computing center, and the method comprises the steps: S1, determining a to-be-scheduled task; s2, determining a target node in all nodes of the intelligent computing center according to a preset computing power resource scheduling algorithm; and S3, scheduling the to-be-scheduled tasks on the one or more nodes to a target node, and releasing computing power resources occupied by the to-be-scheduled tasks on the original node. Therefore, it can be ensured that the to-be-scheduled task can be allocated to the most appropriate target node, and meanwhile, the originally occupied computing power resources are released in time, so that space is provided for other tasks, efficient and balanced computing power resource management can be kept, excessive concentration or idleness of the computing power resources is avoided, fragmentation of the computing power resources is effectively reduced, and the computing power management efficiency is improved. And the computing power resource utilization rate of the intelligent computing center is remarkably improved, so that the operation efficiency and the response speed of the whole intelligent computing center are improved.
Owner:DATACANVAS LTD

Pathological hybrid expert model-based expert behavior analysis method and system

The invention provides an expert behavior analysis method and system based on a pathological hybrid expert model, and the method comprises the steps: calculating the sum of each row of distribution weights of a basic pathological hybrid expert model, carrying out the statistics of the distribution shape of the contribution to a slot in an input token, and carrying out the evaluation of the contribution of Tokens to the slot; calculating a relative weight average value of each expert in the MoE expert layer for different output tokens, counting the importance degree of different experts in the MoE expert layer for output, and performing expert output contribution evaluation of the MoE expert layer; counting the number of the tokens reaching a set cumulative weight, measuring the distribution difference of the token weights of different slot positions, and evaluating the number of the tokens of each slot position; carrying out inverse proportion shadow processing on the input patch by calculating linear combination weights of different slot positions, and carrying out expert attention visualization evaluation; and optimizing expert configuration in the model.
Owner:BEIJING THOROUGH FUTURE INC

Edge computing resource allocation method and system based on multi-objective optimization

The invention provides an edge computing resource allocation method and system based on multi-objective optimization, and relates to the field of data processing, and the method comprises the steps: determining the resource demand feature of each unmanned retail store and the resource demand association feature between any two unmanned retail stores according to the historical computing resource demand information of a plurality of unmanned retail stores, determining an edge calculation layout scheme, and setting a plurality of edge calculation devices; predicting future computing resource demands of the plurality of unmanned retail stores according to the resource demand feature of each unmanned retail store, the resource demand association feature between any two unmanned retail stores and the demand prediction auxiliary information; acquiring resource allocation auxiliary information; according to the method, the edge computing resource allocation scheme is determined according to the future computing resource demands and the resource allocation auxiliary information of the unmanned retail stores, the edge computing resources are allocated to the unmanned retail stores, and the method has the advantage of improving the flexibility of edge computing resource allocation in an unmanned retail scene.
Owner:SICHUAN HANTANG CLOUD DISTRIBUTED STORAGE TECH CO LTD

Intelligent robot labor dispatch management method and system

ActiveCN119067416AOptimal selection strategyavoid rigidityData processing applicationsMachine learningRobot handWorking environment
The invention belongs to the field of intelligent manufacturing, and provides an intelligent robot labor dispatch management method and system, and the method comprises the steps: obtaining the feature information of a client workpiece, and the feature information of the workpiece comprises a workpiece material, a workpiece shape, a workpiece size and a workpiece surface treatment requirement; processing requirements of workpieces of clients are obtained, wherein the processing requirements of the workpieces comprise processing task types, precision requirements, processing speeds, working environments and processing quantities; on the basis of the feature information of the workpiece and the machining requirement, a first model is used for selecting a required manipulator and peripheral equipment type; and determining the number of robots needing to be dispatched by using a second model according to the machining requirements of the workpieces and the types of the manipulators and the peripheral equipment. According to the scheme, intelligent robot labor dispatching can be efficiently carried out.
Owner:DONGGUAN XINBAIREN ROBOT TECH CO LTD

Method and system for realizing intelligent number asking based on large model

The invention relates to the technical field of natural language processing, in particular to a method and system for achieving intelligent number asking based on a large model, and the method comprises the following steps: integrating data from various data sources including a database, a data warehouse, WEB service and Excel files; the data is cleaned, converted, standardized and normalized through the data management center, so that the data quality is ensured, and basic data support is provided for subsequent intelligent question analysis; the beneficial effects are that the method for realizing intelligent number asking based on the large model provided by the invention responds to complex and changeable data requirements in real time, helps an enterprise to quickly make a data-based decision, and reduces the time cost of waiting for the assistance of an IT department or a data analysis team; through effective integration and intelligent search of mass data resources, various data in an enterprise can be fully mined and utilized, and idleness and waste of the data resources are avoided.
Owner:SHANDONG LANGCHAO YUNTOU INFORMATION TECH CO LTD

Self-service rental vehicle intelligent scheduling and dynamic battery distribution method, system and device and storage medium

The invention discloses a self-service rental vehicle intelligent scheduling and dynamic battery distribution method, system and device and a storage medium. The self-service rental vehicle intelligent scheduling and dynamic battery distribution method comprises the following steps: S1, predicting a battery demand of a rental network in a future set time period through a linear regression model, and feeding back a prediction result to a cloud scheduling platform; s2, a leasing user requests to lease at a leasing network through a user side application program; s3, the cloud scheduling platform extracts the inventory number information of the lease network in the S2; s4, the cloud scheduling platform continues to extract the historical lease information of the lease user in the S2; s5, the cloud scheduling platform performs judgment through a linear regression model in combination with the detailed information of the batteries and the vehicles in the renting network in the S3 and the historical renting information of the renting users in the S4; and S6, the cloud scheduling platform notifies the battery replacement cabinet system to open a corresponding battery compartment door. The method has the advantages of intelligent scheduling and distribution, improved distribution efficiency, prolonged battery life and the like.
Owner:SHENZHEN WANWEI IOT TECH CO LTD

Multi-key index fusion service resource scheduling method based on AI large model driving

The invention discloses a multi-key index fusion service resource scheduling method based on AI large model driving, and relates to the technical field of intelligent resource scheduling, when new service resources are generated, a scheduling process is automatically triggered, and service task information of the service resources is identified and collected; and collecting latest engineer related data, and integrating engineer data and task information to obtain a multi-dimensional task data set. According to the multi-key index fusion service resource scheduling method based on AI large model driving, through comprehensive consideration of factors such as working saturation and distance, overfatigue of engineers and unnecessary path time waste are avoided, resources can be quickly responded, and the average duration of resource processing is reduced, so that the overall service efficiency is improved, and the service quality is improved. And the resources are allocated according to the skills and historical good reputation rates of the engineers, so that the resources are ensured to be processed by the engineers with corresponding capabilities and high service quality, and the success rate of resource processing and the customer satisfaction are improved.
Owner:ZHEJIANG HUIYI NETWORK TECH CO LTD

Intelligent recommendation method and system based on shared robot

The invention belongs to the field of intelligent manufacturing, and provides an intelligent recommendation method and system based on a shared robot, and the method comprises the steps: receiving a picture and a processing demand provided by a user; determining the processing attribute of the target workpiece according to the picture; determining a processing sub-task according to the processing attribute; determining an optimal shared robot combination according to the processing subtasks and the processing requirements; and displaying the optimal shared robot combination to the user.
Owner:DONGGUAN XINBAIREN ROBOT TECH CO LTD

Organization design optimization method for improving work efficiency of earth-rock engineering machinery

The invention relates to the field of earth-rock engineering, and discloses an organization design optimization method for improving the work efficiency of earth-rock engineering machinery, and the method comprises the following steps: S1, carrying out the modeling of each process in the earth-rock engineering through a directed acyclic graph; s2, calculating the earliest starting time and the latest starting time of each process by using a critical path method based on the process relation model, identifying a critical path of the project, and determining a critical process which affects the project construction period; s3, on the basis of the identified key process, performing process scheduling optimization by using mixed integer linear programming to ensure that the project period is minimized under resource limitation, and generating an optimized process scheduling scheme; and S4, based on the optimized process scheduling scheme, establishing a multi-stage queuing theory model, and optimizing the scheduling of the mechanical equipment. By optimizing procedure scheduling and mechanical equipment scheduling, the construction efficiency of earth-rock engineering is remarkably improved, the construction period and resource waste are reduced, and it is ensured that a project is efficiently completed on schedule.
Owner:中核(内蒙古)矿业投资有限公司 +1

Federal learning algorithm based on adaptive aggregation and dynamic training

The invention discloses a federal learning algorithm based on adaptive aggregation and dynamic training, and belongs to the field of deep learning, and the learning algorithm specifically comprises the following steps: S1, each client receives an initial global model parameter, and carries out model training by using local data; s2, locally updating the weight of the model by adopting stochastic gradient descent; s3, after local training is completed, the client side calculates a model loss value of the current round, and the loss is reserved to serve as a reference for subsequent adaptive aggregation; s4, on the client side, each client predicts the time demand of the next round of training by adopting a dynamic training strategy according to the historical training time of the client; according to the method, the accuracy and generalization ability of the model are improved, resource idling is avoided, it is ensured that computing resources of all clients are fully utilized, the convergence speed of the global model is increased, the computing overhead is reduced, resource utilization is optimized, and the cost is reduced.
Owner:SHANGHAI UNIV OF ENG SCI

Heterogeneous GPU resource scheduling method and system based on combination of meta learning and reinforcement learning

The invention relates to a heterogeneous GPU (Graphics Processing Unit) resource scheduling method and system based on the combination of meta learning and reinforcement learning, and aims to improve the utilization efficiency of computing resources in large model training and reasoning and improve the adaptive capacity of tasks and the response speed of the system. According to the method, efficient scheduling of GPU resources is achieved through the five steps of task feature extraction, meta-learning strategy initialization, reinforcement learning scheduling optimization, task scheduling execution and dynamic strategy adjustment. Wherein the meta-learning module generates an initial scheduling strategy by utilizing knowledge accumulated by historical tasks, so that the exploration time is shortened; and the reinforcement learning module continuously optimizes a scheduling strategy through environment feedback to realize efficient distribution of tasks. The system can adaptively adjust strategies according to different task requirements and dynamic changes of GPU hardware resources, and therefore higher resource utilization rate and overall performance optimization are achieved.
Owner:CHENGDU UNIV OF INFORMATION TECH