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

3666results about How to "Improve rationality" patented technology

Building health monitoring and evaluation method and system based on physical neural network

The invention provides a building health monitoring and evaluation method and system based on a physical neural network, and the method comprises the steps: collecting the monitoring data of vibration, strain, displacement and the like of a building through a sensor network, and carrying out the data preprocessing based on wavelet transformation and a neural network; inputting the processed data into a physical constraint encoder, mapping the processed data to a physical space by adopting a Hamilton quantity encoding method, and constructing constraint conditions in combination with physical model parameters; performing feature matching by using a physical constraint neural network, and extracting key features; adopting a principal component analysis method to decompose early warning indexes, and constructing parameter mapping through a deep neural network; generating a hierarchical decision rule based on a decision tree algorithm; and carrying out constraint check and cost calculation on the candidate schemes, and finishing scheme sorting through an analytic hierarchy process. Physical knowledge is embedded into a deep learning framework, and the accuracy and reliability of monitoring evaluation are improved.
Owner:JIANGSU TESTING CENT FOR QUALITY OF CONSTR ENG

Method for controlling running posture of electric power inspection robot

The invention discloses an electric power inspection robot operation attitude control method, and relates to the technical field of data processing, and the method comprises the following steps: collecting the three-dimensional information of an inspection environment, the obstacle position, the distance, and the illumination and temperature environment parameters based on a multi-type environment data collection device; and the collected environment data is subjected to preprocessing and data fusion. The precision of inspection operation is improved by adjusting the movement track and posture of the robot, the advancing speed and posture of the robot are automatically adjusted by sensing the change of the surrounding environment through the integrated sensor, it is ensured that information of a target area is clearly captured, the inspection path and posture are dynamically adjusted according to collected environment data, and the inspection efficiency is improved. According to the method, the labor intensity of manual inspection is reduced, inspection omission and errors caused by human factors are reduced, the robot can stably operate in a complex environment, potential safety hazards are found and responded in time, and therefore safe and stable operation of an electric power system is guaranteed.
Owner:ZHONGNENG XINGSHENG (XIANGHE) ELECTROMECHANICAL EQUIP CO LTD

Industrial robot cooperative control method, system and device and storage medium

The invention relates to an industrial robot cooperative control method, system and device and a storage medium. The method comprises the following steps: acquiring machine system information, working environment conditions, task demand contents and cooperative mode information of a plurality of industrial robots; performing spatial analysis on the working environment condition to obtain environment structure characteristics; performing task decomposition on the task demand content according to the cooperation mode information to obtain a sub-task list; mapping the machine system information into the environment structure features to obtain a corresponding mapping relationship, and performing association analysis on the mapping relationship to obtain a task allocation scheme; performing individual optimization on the comprehensive control parameters based on a task allocation scheme to obtain robot control parameters; and performing cooperative strategy analysis according to the sub-task list and the robot control parameters to obtain robot cooperative strategies, and performing comprehensive analysis on all the robot cooperative strategies to obtain an overall cooperative control strategy. According to the invention, the whole industrial robot system can be more suitable for complex and changeable actual production scenes.
Owner:SHENZHEN LIHU ELECTRONIC TECH CO LTD

Coastal wetland ecological restoration system and method based on mangrove forest

The invention relates to the technical field of ecological environment restoration, and discloses a coastal wetland ecological restoration system and method based on mangrove forests, and the method comprises the steps: collecting multi-source monitoring data of a coastal wetland, carrying out region division, extracting a key ecological index, and calculating an ecological degradation index; identifying an important ecological region, setting a region importance index, calculating a reachability index, and generating a wetland restoration priority ranking graph; determining an alternative mangrove forest planting area according to the sorting graph, carrying out habitat suitability evaluation, identifying a suitable growth area, and constructing a mangrove forest planting optimization model to obtain an optimal planting density; and formulating a mangrove forest wetland restoration implementation scheme, and refining the protection restoration task, the time progress, the fund budget, the technical route and the management and protection measures of each stage. According to the method, the multi-source monitoring data is combined with the optimization model, so that the scientificity and effectiveness of mangrove forest planting are improved, and the sustainable development of a coastal wetland ecosystem is promoted.
Owner:OCEAN UNIV OF CHINA

Power data management credible planning workflow method based on KCMAP

The invention belongs to the technical field of power data governance, and particularly relates to a KCMAP-based power data governance credible planning workflow method, which comprises the steps of designing a knowledge organization structure for power data governance, constructing a domain knowledge base and performing vectorization storage; designing multi-order knowledge prompt to construct a DR-RAG model, retrieving knowledge fragments from a vector library, and synthesizing a domain process by using LLM; designing a knowledge capability matching agent, matching the domain process knowledge with an available agent based on an agent capability protocol, and correcting the domain process knowledge; designing a task trusted planning agent, decomposing and planning the electric power data management operation based on a domain knowledge process, and generating a task plan; and a two-stage verification mechanism is designed to ensure the reasonability of a task plan and the accuracy of scheduling execution.
Owner:YANTAI HAIYI SOFTWARE

E-commerce intelligent operation monitoring and collaborative decision-making method based on big data analysis

The invention discloses an e-commerce intelligent operation monitoring and collaborative decision-making method based on big data analysis, and the method comprises the following steps: S1, collecting multi-source heterogeneous data, and constructing an original data set; s2, performing data cleaning and characterization processing to generate a feature data set; s3, constructing a knowledge graph and dynamically updating the knowledge graph by using the graph embedding model; s4, generating potential causal paths and weights in combination with the neural relationship reasoning model and the diffusion model, and introducing a microknowledge enhancement layer to generate causal enhancement features; s5, identifying abnormal behaviors in combination with a multi-level anomaly detection mechanism; s6, designing a dynamic game optimization model, determining a collaborative optimal solution under a multi-target conflict through Nash equilibrium, and processing a dominant and subordinate relationship in combination with a Stackelberg game to generate a collaborative optimization strategy; and S7, displaying the monitoring state and the collaborative optimization strategy through a visual interface. According to the invention, big data analysis, a knowledge graph and a dynamic game technology are combined, so that e-commerce intelligent operation monitoring and collaborative decision-making are realized.
Owner:JUNSHI LIXIN TECH GRP CO LTD

First-aid platform work order management method based on digital twinborn and artificial intelligence

The invention provides a first-aid platform work order management method based on digital twinning and artificial intelligence, and belongs to the technical field of information technology application innovation, and the method comprises the steps: collecting historical first-aid data and real-time data of a first-aid scene, and constructing a task scheduling system based on a knowledge graph; decomposing the task into a plurality of sub-tasks according to the work order data, and allocating an optimal first-aid resource combination for the sub-tasks; an optimization strategy is set to carry out collaborative allocation control on each resource, and task allocation is optimized; the optimized task allocation is monitored in real time, and meanwhile, in combination with real-time data flow monitored in real time, it is ensured that the change of the dynamic environment is responded at any time in the task execution process; and re-inputting the optimized task allocation and resource scheduling strategy into the knowledge graph, and carrying out closed-loop optimization. According to the invention, the problems of inaccurate task scheduling, weak real-time response capability, low resource utilization rate and the like in the existing work order management system of the emergency platform are effectively overcome, and the overall efficiency and the automation level of the emergency platform are greatly improved.
Owner:佛山市佛盈盘古信息科技有限公司

Intelligent bridge reinforcement decision generation method, device and equipment based on damage identification

The invention relates to the technical field of data processing, and discloses an intelligent bridge reinforcement decision generation method, device and equipment based on damage identification. The method comprises the following steps: carrying out bridge damage identification and evaluation on a bridge state data set to obtain a bridge damage characteristic spectrum; performing intelligent decision analysis on the bridge damage characteristic spectrum, generating a preliminary reinforcement scheme, and obtaining a candidate reinforcement strategy set; performing parametric modeling and multi-scale simulation on the candidate reinforcement strategy set, and performing coupling calculation evaluation on a reinforcement effect to obtain an optimized reinforcement scheme; virtual construction planning is conducted on the optimized reinforcement scheme, a construction process model is generated through an intelligent scheduling algorithm, and a target construction scheme is obtained; and monitoring and feeding back the target construction scheme in real time, and dynamically optimizing the construction process through an adaptive control algorithm to obtain a target intelligent reinforcement implementation scheme. The intelligent bridge reinforcement decision generation efficiency and accuracy based on damage identification are improved.
Owner:ZHENGZHOU COMM PLANNING SURVEY & DESIGN INST

Intelligent route planning method and system for expressway unmanned aerial vehicle

The invention relates to the technical field of expressway unmanned aerial vehicle route planning, in particular to an intelligent route planning method and system for an expressway unmanned aerial vehicle, and the method specifically comprises the steps: planning unmanned aerial vehicle waypoints on an expressway based on a target three-dimensional model, and obtaining a waypoint set of the expressway; historical route data of the expressway are obtained, a deep learning algorithm is used for analyzing the historical route data, safe flight path features are extracted, a route safety evaluation model is constructed, and the route safety evaluation model is used for evaluating the route safety level of the route of the unmanned aerial vehicle; and determining route planning parameters according to the unmanned aerial vehicle task type, and determining an unmanned aerial vehicle route through the waypoint set, the route safety evaluation model and the waypoint planning parameters based on a multi-objective optimization algorithm. According to the invention, the safety and efficiency of the unmanned aerial vehicle in highway inspection and monitoring tasks are improved, and automatic planning and dynamic adjustment of the route of the unmanned aerial vehicle based on real-time data analysis are realized.
Owner:广东利通科技投资有限公司

Big data intelligent real-time processing and analysis method and system

The invention relates to the field of intelligent traffic management, and discloses a big data intelligent real-time processing analysis method and system, and the method comprises the following steps: obtaining structured, semi-structured and unstructured multi-modal traffic data; preprocessing the data and extracting feature vectors; fusing the feature vectors of different modes through a self-attention mechanism to generate a unified fusion feature; performing time sequence modeling on the fusion features by using a long short-term memory network, and predicting traffic flow; based on a traffic flow prediction result, a deep reinforcement learning algorithm is adopted to dynamically optimize the duration and phase of a traffic signal lamp, and meanwhile, an optimal path is provided for a vehicle in combination with a path recommendation algorithm; and applying the optimized signal control and path recommendation to a real-time traffic management system. According to the invention, intelligent fusion of multi-modal data, accurate traffic flow prediction and intelligent traffic signal control and path recommendation can be realized, and the real-time performance and efficiency of traffic management are improved.
Owner:山东海润数聚科技有限公司

Modular power supply system configuration method and system of micro-module machine room

The invention provides a modular power supply system configuration method and system for a micro-module machine room, and relates to the technical field of electric power, and the method comprises the steps: collecting power utilization state data and load distribution data of functional equipment in the micro-module machine room, building a power supply network topology model, dividing a power supply system into a first-stage load, a second-stage load and a third-stage load, an independent power supply loop and a data acquisition unit are respectively configured in the first-stage load, the second-stage load and the third-stage load; a power supply network topology model is updated according to the power utilization data acquired by the data acquisition unit, a reinforcement learning algorithm is adopted to generate an adaptive power distribution strategy, and a modular energy storage unit is arranged to provide a standby power supply for a primary load and a secondary load; and constructing a machine learning fault prediction model based on the power consumption data, and dynamically adjusting a power supply path and a power distribution scheme of a power supply loop.
Owner:CHANGZHOU RUIWU TECH CO LTD

Long-time-sequence artificial precipitation enhancement operation effect evaluation method

PendingCN118966886AMake up for the shortcomings of strong subjectivityQuantitative evaluation of the effect of rainfall enhancement operations is convenientData processing applicationsScene recognitionVisual comparisonAtmospheric sciences
The invention discloses a long-time-sequence artificial precipitation enhancement operation effect evaluation method. The method comprises the following steps: selecting precipitation enhancement operation in a specific time period of an area to be evaluated, obtaining operation information, calculating to obtain an hour-by-hour operation influence area of each operation, and combining space-time overlapping influence areas to obtain an hour-by-hour influence area product covering all the operations; based on the hourly influence area products, calculating the relative precipitation increasing rate of the selected operation by using a visual comparison method of physical parameter change trend analysis before and after the operation and regional visual comparison analysis, and calculating the relative precipitation increasing rate of the selected operation by using the hourly influence area products and the precipitation increasing rate index library in combination with the hourly precipitation amount. And calculating the rainfall increase amount of all operations in the selected time period based on a rainfall increase rate index method, and completing rainfall increase operation effect evaluation. According to the method, objective, rapid and quantitative evaluation of long-time-sequence artificial precipitation enhancement operation is realized by combining a visual comparison method and a precipitation enhancement rate index method; the method is not only suitable for artificial precipitation enhancement, but also suitable for artificial snow enhancement operation effect evaluation.
Owner:WEATHER MODIFICATION CENTER CHINA METEOROLOGICAL ADMINISTRATION

Solid state disk data reading method and system, storage medium and program product

The invention discloses a solid state disk data reading method and system, a storage medium and a program product, and the method comprises the steps: calculating a temperature change rate and a temperature accumulation effect coefficient of a to-be-read data block according to a current temperature value and a historical temperature record; dividing the physical page address into a plurality of subintervals, and determining a loss level; calculating an initial reading voltage threshold value; compensating the initial reading voltage threshold value to obtain a target reading voltage threshold value; performing parallel reading on the to-be-read data block by adopting the target reading voltage threshold value to obtain original reading data; performing crosstalk correction on the original read data to obtain corrected data; when the reliability verification result of the corrected data of any subinterval is lower than a preset threshold value, error correction processing is carried out; and updating the loss level of the sub-interval according to the verification result of the reliability verification, and re-dividing the sub-interval of the data block to be read. The data reading delay is reduced, and the performance of the solid state disk in a scene of frequently reading small files is improved.
Owner:SHENZHEN WEIKEWEIYE ELECTRONIC TECH CO LTD

Topological optimization-based multi-sealing method and system for high-vacuum die-casting die

The invention provides a multi-sealing method and system for a high-vacuum die-casting die based on topological optimization, and relates to the technical field of die structures.The multi-sealing method comprises the steps that a sealing structure parameterized model is established, geometric parameters and boundary conditions of a cavity wall face are obtained, an initial design domain is constructed, and grid units are divided; carrying out topological optimization calculation based on a multi-objective function considering contact stress distribution, and iteratively optimizing the relative density of grid cells by adopting an SIMP method; and according to the obtained topological configuration of the sealing structure, multiple sealing structure design is carried out, a three-dimensional entity model is constructed, and the sealing performance is verified through finite element analysis.
Owner:NINGBO LONGYUAN PRECISION MACHINERY

Three-dimensional space positioning and path planning method of unmanned aerial vehicle pole tower

The invention relates to the technical field of space positioning and path planning, in particular to a three-dimensional space positioning and path planning method for an unmanned aerial vehicle tower. The method comprises the following steps of performing accurate longitude and latitude height data acquisition based on a laser range finder to generate accurate longitude and latitude height data; obtaining tower equipment parameters; performing inspection point three-dimensional coordinate calculation according to the tower equipment parameters and the tower three-dimensional coordinate system to generate inspection point three-dimensional coordinate data; cruise point comprehensive constraint range data are obtained according to the unmanned aerial vehicle flight association data and the polling area terrain data, and cruise point comprehensive constraint range data are generated; performing cruise node three-dimensional coordinate design on the three-dimensional coordinate data of the inspection point according to the cruise point comprehensive constraint range data to generate cruise point three-dimensional coordinate data; and performing optimized cruise path planning processing according to the cruise point three-dimensional coordinate data to generate optimized cruise path data. According to the invention, more accurate unmanned aerial vehicle tower space positioning and path planning are realized.
Owner:HUNAN ZHONGTUTONG UAV TECH CO LTD

Road line selection optimization method and system based on AI and quantitative parameter constraint

The invention provides a road line selection optimization method, system and device based on AI and quantitative parameter constraint, and a storage medium. The method comprises the following steps: establishing a road line selection initial preset parameter library; a high-precision remote sensing technology, an unmanned aerial vehicle, a GIS database and a traffic monitoring system are utilized to collect quantitative data, and data preprocessing is automatically carried out; a deep learning model is developed and trained, parameter values in historical cases are automatically identified and calculated, the identified and calculated parameters are trained and learned, and a deep learning result is fed back to a quantitative parameter set; a multi-factor target evaluation index system is constructed, and evaluation index values of all candidate schemes are obtained; and providing a decision support tool to help a user to understand the advantages and disadvantages of each scheme and recommend an optimal line scheme meeting all quantitative parameter constraints. According to the invention, the line selection efficiency and accuracy can be improved, the compliance of the line selection scheme in the aspects of technology, safety, environment and the like is ensured, and an efficient, economic and environment-friendly line selection scheme is provided for a road construction project.
Owner:HUNAN PROVINCIAL COMM PLANNING SURVEY & DESIGN INST CO LTD

Distributed energy storage system based on multi-source fusion

The invention discloses a distributed energy storage system based on multi-source fusion, and relates to the technical field of distributed energy storage based on multi-source fusion. The monitoring center is in communication connection with a data acquisition module, a data energy storage module, a power prediction module, an intelligent adjustment module, a multi-source data fusion module, a data monitoring module and an energy distribution control module; electric power data monitoring points are set in each electric power unit through the data acquisition module, so that a power generation power prediction curve and a load demand power prediction curve are constructed, a power supply and discharge power prediction curve is obtained according to the power generation power prediction curve and the load demand power prediction curve, and an energy storage monitoring visual graph is constructed; therefore, the working state of the power storage unit is judged, and the working state of the power storage unit is detected and analyzed, so that the distribution control of various energy sources is realized, and the monitoring efficiency and distribution rationality of the various energy sources are greatly improved.
Owner:WUHAN HUAWORLD POWER TECH

Load balancing optimization method and device, electronic equipment and readable storage medium

The embodiment of the invention provides a load balancing optimization method and device, electronic equipment and a readable storage medium, and the method comprises the steps: obtaining business historical data of a target business under the condition that a business request for the target business is received; taking the service request and the service historical data as input of a target service model, and obtaining a target load state corresponding to a target service output by the target service model; determining a load optimization strategy for the target service based on the target load state and the real-time load data of the cloud server; the load optimization strategy is used for carrying out resource adjustment on cloud resources related to the target service and indicating to allocate the service request to the target cloud server. Therefore, reasonable distribution of the service requests is realized, load balance among the cloud servers is adjusted, load requirements of different service scenes are met, the load balance effect is improved, and meanwhile, the resource utilization rate and the request distribution reasonability are improved.
Owner:GREE ELECTRIC APPLIANCE INC OF ZHUHAI +1

Satellite telemetry data anomaly detection method based on DTW

The invention relates to the technical field of remote sensing satellite data processing, in particular to a DTW-based satellite telemetry data anomaly detection method, which comprises the following steps of: S1, obtaining real-time satellite telemetry data; s2, obtaining preprocessed satellite telemetry data; s3, obtaining time sequence satellite telemetry data; s4, setting a DTW threshold value according to the normal data; s5, performing historical compensation on normal data; s6, performing real-time compensation on normal data according to the anomaly analysis result of the real-time satellite telemetry data; s7, performing sliding detection on the time sequence satellite telemetry data according to the DTW threshold value; step S8, obtaining abnormal satellite telemetry data; step S9, performing post-processing on the abnormal satellite telemetry data; step S10, optimizing the time sequence processing process according to the key time period; and step S11, adjusting the optimization process of the time sequence processing process according to the compensation judgment result. According to the invention, the satellite telemetry data anomaly detection efficiency is improved.
Owner:BEIJING CREATUNION INFORMATION TECH CO LTD

Converter steelmaking endpoint carbon temperature prediction method and device based on adaptive data enhancement

The invention provides a converter steelmaking endpoint carbon temperature prediction method and device based on adaptive data enhancement, and relates to the technical field of converter steelmaking. The method comprises the following steps: preprocessing data in a historical production data set in a converter steelmaking process; the preprocessed data set is processed through an adaptive SMOTE data enhancement technology; building a steelmaking endpoint carbon temperature prediction model based on the random forest; and training a steelmaking end point carbon temperature prediction model according to the processed data set, and obtaining a converter steelmaking end point carbon temperature prediction result according to the trained adaptive data enhanced steelmaking end point carbon temperature prediction model. The invention aims to improve the sample size and diversity of a data set in the converter steelmaking process by using a data preprocessing method and a self-adaptive SMOTE data enhancement algorithm, remove redundant information, reduce the labor cost of manual arrangement and data processing, and introduce a self-adaptive mechanism according to the data distribution density and different working conditions. And the generalization ability and the prediction precision of the model are improved.
Owner:UNIV OF SCI & TECH BEIJING

Battery analysis method

The invention discloses a battery analysis method, and relates to the field of energy storage batteries, and the method comprises the steps: obtaining the data of a battery; key features are extracted from the preprocessed data; according to the key features, constructing combined features; according to the mean value current, the capacity change rate and the temperature change rate, a DBSCAN clustering algorithm is adopted to cluster the working states of the batteries, and a working mode division result of the batteries is obtained; counting transfer frequencies among different working modes according to the working modes obtained by clustering, and calculating a transfer probability matrix; a fault analysis model based on a neural network is constructed, the working mode division result, the key features and the combined features serve as input, the fault state of the battery serves as output, and a supervised learning algorithm is adopted to train the fault analysis model; and inputting to-be-processed battery data into the trained fault analysis model, and predicting the fault probability of the battery. In view of low battery fault analysis accuracy in the prior art, the method improves the accuracy of predicting the fault probability of the battery.
Owner:DONG GUAN QUAN CHUANG DA ENERY CO LTD

Charging pile construction planning method and system based on artificial intelligence

The invention relates to the technical field of artificial intelligence, in particular to a charging pile construction planning method and system based on artificial intelligence. The method comprises the following steps: acquiring existing power infrastructure data and multi-source heterogeneous data, wherein the multi-source heterogeneous data comprises traffic data, geographic data, vehicle data and charging behavior data; performing time sequence feature extraction on the multi-source heterogeneous data, and performing cross-time scale fusion on different data source features by using a preset hierarchical attention network model to obtain factor weight data; and constructing a long-term charging demand prediction model through a sequence-to-sequence model according to the factor weight data and the multi-source heterogeneous data. According to the site selection method based on the risk minimum set coverage problem, initial site selection scheme data is generated by combining multi-objective optimization of the coverage rate, the service radius and the accessibility, and more scientific charging pile layout is achieved.
Owner:北京首兴安成电力工程有限公司

Equipment management method and system for 3D digital factory

The invention relates to the technical field of industrial equipment management, and discloses an equipment management method for a 3D digital factory, and the method comprises the following steps: sensing the operation parameters of a network collection device through the Internet of Things; processing the operation parameters by utilizing a cloud computing or edge computing technology; dynamically generating an equipment health state based on the processed data; the equipment management system of the 3D digital factory comprises an Internet of Things sensing network used for collecting operation parameters of the equipment; the data processing module is used for carrying out cleaning, noise reduction, dynamic modeling and anomaly detection on equipment operation parameters; and the equipment health state generation module is used for generating the health state of the equipment. According to the invention, through the Internet of Things sensing network, dynamic modeling, intelligent scheduling and full-life-cycle management technology, the effects of equipment state real-time monitoring, accurate maintenance, energy efficiency optimization and comprehensive asset management are realized.
Owner:AEROSPACE WANYUAN CLOUD DATA HEBEI CO LTD

Visual network freight platform transportation transaction management system

The invention discloses a visual network freight platform transportation transaction management system. The system comprises an order management module, a vehicle scheduling module, a transportation monitoring module, a transaction settlement module and a visual display module. Each module has innovative functions, such as order intelligent classification, vehicle optimization scheduling algorithm to minimize comprehensive cost, real-time monitoring and accurate settlement. The corresponding management method adopts advanced technologies to ensure efficient operation of each link, including block chain recording, intelligent contract settlement and the like. The whole system realizes efficient management, real-time monitoring and convenient visualization of transportation transaction of a freight platform, and improves the efficiency and quality of logistics transportation; according to the visual network freight platform management system, efficient and accurate order management is realized, vehicle scheduling is optimized, the cost is reduced, comprehensive and real-time transportation monitoring is guaranteed to be safe, safe and accurate transaction settlement is realized, convenient and visual display is convenient to make decisions, and the logistics transportation efficiency, quality and user experience are improved.
Owner:SHANDONG FRONTIER TECH IND DEV CO LTD

Intelligent agent processing method, system, device and equipment and storage medium

The invention provides an agent processing method, system and device, equipment and a storage medium, and relates to the field of data processing, in particular to the technical fields of artificial intelligence, deep learning, large models and the like. The specific implementation scheme is as follows: calling each first agent in N first agents, and performing intelligent testing on the to-be-processed agent to obtain a test result corresponding to each first agent; wherein the N first intelligent agents are used for performing intelligent testing on the to-be-processed intelligent agent from different evaluation dimensions; the test result at least comprises a target question and answer pair of the intelligent dialogue between the first intelligent agent and the to-be-processed intelligent agent; n is a positive integer; calling a second agent, and performing intelligent evaluation on a target question and answer pair contained in the test result corresponding to each first agent to obtain an initial evaluation result corresponding to each test result; and obtaining a target evaluation result for the to-be-processed agent based on the initial evaluation result corresponding to each test result.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

PCB (Printed Circuit Board) defect detection method and device, medium and electronic equipment

The invention relates to a PCB defect detection method and device, a medium and electronic equipment, and belongs to the technical field of PCB detection.A processed training set is independently input into a visual defect recognition model, the prediction precision of each visual defect recognition model is monitored, a plurality of trained visual defect recognition models are obtained, and the defect detection accuracy of the PCB is improved. And finally, acquiring real-time image data of the PCB in the production line, identifying the real-time image data of the PCB in the production line through the visual defect identification model, generating a related anomaly analysis result according to an identification result, and processing the training set through fusion of a particle swarm optimization algorithm and a Pearson's correlation coefficient measurement method to obtain the abnormal data of the PCB in the production line. Interference of multi-scale data on model training can be suppressed, and the precision of the model in defect prediction can be improved. Through fusion of the Markov model, evaluation can be carried out according to actual prediction precision, model training is further optimized, and model training rationality is improved.
Owner:SHENZHEN ZHENHUAXING INTELLIGENT TECH CO LTD

Task execution method based on large language model and related equipment

The invention relates to the technical field of artificial intelligence, and provides a task execution method based on a large language model and related equipment. The method comprises the following steps: decomposing a complex task into a plurality of sub-tasks by utilizing a task decomposition model, and constructing an execution model for each sub-task; planning all the sub-tasks by using the task planning model to obtain an execution logic sequence of all the sub-tasks; calibrating each subtask to obtain a plurality of final subtasks, and then combining all the final subtasks according to an execution sequence to obtain a combined task; and executing the combined task by utilizing all the execution models to obtain a final execution result of the complex task. According to the method, the universality of the task execution method can be improved.
Owner:CENT SOUTH UNIV

Control method and equipment for energy-saving air conditioner

The invention relates to the technical field of air conditioner control, in particular to a control method and device for an energy-saving air conditioner, and the method comprises the steps that a room provided with the energy-saving air conditioner is divided into areas based on the number of air outlets, and the temperature of each area at each moment in each sampling period and the temperature and wind speed of each moment in each outdoor sampling period are collected; obtaining the temperature difference of each region at each moment and the variation of the wind speed state; obtaining a temperature trend difference value, a neighborhood temperature range value and an environment change correlation degree of each region; determining an influence coefficient of each region; and the similarity relation between the temperature of any area and the temperature of other areas at all moments is analyzed, the air conditioner adjusting force of any area in all sampling periods is determined in combination with the influence coefficient, and the energy-saving air conditioner is controlled based on a PID controller. Therefore, the air speed control stability of the energy-saving air conditioner is improved.
Owner:宿州学院

Vehicle track prediction method based on interactive perception and map adaptation

The invention relates to a vehicle track prediction method based on interactive perception and map adaptation, and belongs to the technical field of automatic driving. The method comprises the steps of collecting a historical track and geographical semantic information of a vehicle; the method comprises the following steps of: modeling interaction between dynamic objects by utilizing Transform, and fusing map information when a state sequence is decoded; a hierarchical attention mechanism is adopted, the future state of the vehicle is considered, and the consistency and accuracy of prediction are ensured; in addition, a multi-resolution map coding module is also constructed, the module fully utilizes a Vision Transform module to efficiently capture local and global scene context information, and then map representation is closely associated with a vehicle state to accurately model an interaction process of a vehicle and a scene, so that a more reasonable future trajectory prediction result is generated. The method shows wide application potential, can effectively improve the calculation performance, and is suitable for a more complex traffic environment.
Owner:CHONGQING UNIV OF POSTS & TELECOMM