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

251results about How to "Increase resources" patented technology

Distributed computing resource smart evolution method and system based on digital twinning

The invention provides a distributed computing resource smart evolution method and system based on digital twinning, and relates to the technical field of resource evolution.The distributed computing resource smart evolution method comprises the steps that a smart sensing probe is deployed at a computing node to collect operation data, a double-layer attention mechanism is used for extracting features, and a digital twinning model is constructed based on a graph neural network; a resource allocation strategy and a scheduling decision are optimized in combination with a hierarchical reinforcement learning framework, a prediction sequence is generated through an attention-enhanced sequence prediction network, and finally an optimal configuration scheme is solved by adopting a particle swarm algorithm. According to the method, the utilization rate of distributed computing resources can be improved, the energy consumption of the system is reduced, and intelligent scheduling and optimal configuration of the computing resources are realized.
Owner:北京科杰科技有限公司

Parameter optimization method and device of coupling type transformer

The invention relates to the field of transformer parameter regulation and control, in particular to a parameter optimization method and device for a coupling type transformer. The method comprises the following steps: acquiring multi-dimensional real-time working monitoring parameters and real-time working environment state parameters of the coupling type transformer; performing nonlinear dynamic analysis and global state sensing modeling on the multi-dimensional real-time working monitoring parameters so as to construct a transformer global state sensing model; performing multi-parameter combination definition on the multi-dimensional real-time working monitoring parameters, performing dynamic operation simulation based on a transformer global state sensing model, and collecting operation simulation response data of a plurality of schemes; performing multi-target dynamic balance analysis on the operation simulation response data of the plurality of schemes to obtain an optimal transformer working parameter combination; and carrying out environment dynamic parameter change analysis on the real-time working environment state parameters, and constructing a real-time environment condition distribution field. According to the invention, efficient and self-adaptive adjustment transformer parameter optimization is realized.
Owner:SHENZHEN RUIQIZHENG TECH CO LTD

WEB browsing real-time rendering method and system based on distributed rendering

The invention provides a WEB browsing real-time rendering method and system based on distributed rendering, and relates to the technical field of distributed rendering, and the method comprises the following steps: receiving a rendering request from a user terminal browser, obtaining page data of a target webpage according to the rendering request, preprocessing the page data, analyzing the preprocessed page data, and displaying the analyzed page data. Obtaining a DOM tree structure and a CSSOM tree structure of the page, and constructing a rendering tree adaptive to the user terminal according to the DOM tree structure, the CSSOM tree structure and the equipment parameters; dividing the rendering tree into a plurality of sub-rendering trees, transmitting sub-rendering results generated by the plurality of distributed rendering nodes to a synthesis service node, performing image compression, transmitting the compressed rendering result data to a user terminal browser, receiving and decompressing the rendering result data in the user terminal browser to obtain a rendering result bitmap, and displaying the rendering result bitmap in the synthesis service node. And displaying the information to the user for real-time interactive browsing of the user.
Owner:HANGZHOU ELECTRIC EQUIP MFG

Cascade-based multi-platform data synchronization method and system

The invention belongs to the field of video monitoring systems, and particularly relates to a cascade-based multi-platform data synchronization method and system, and the method comprises the steps: designing an interface security mechanism of cross-platform data exchange; constructing a data synchronization service architecture, namely deploying corresponding data synchronization services at different levels of platforms to realize resource data synchronization, and supporting data synchronization of multi-level cascade or platform interconnection; performing data initialization synchronization; real-time synchronization of data change is realized; establishing a service heartbeat keep-alive mechanism; service multi-instance deployment is carried out, and efficient data processing and flexible load balancing are achieved. According to the invention, many defects of a data synchronization mechanism of an existing video monitoring system are effectively solved, and the stability, expansibility and data processing efficiency of the system are improved.
Owner:HANGZHOU ARTECH

Satellite internet task planning method based on intention understanding and large model

The invention relates to a satellite internet task planning method based on intention understanding and a large model, which belongs to the field of task planning and comprises the following steps: constructing a satellite internet intention library and a satellite internet knowledge tensor library based on RAG enhanced retrieval; receiving a communication intention demand report, and performing intention acceptance according to a user communication intention; performing RAG enhanced retrieval through the accepted communication intention and the knowledge tensor database to obtain a tensor retrieval result, and performing reasoning to obtain an intention analysis result; communication intention verification is carried out according to the intention analysis result and a satellite internet intention library, if legality is met, execution is continued, and otherwise, the process is ended and abnormal warning is carried out; task planning and scheduling are carried out through a satellite internet intention library and an equipment and resource library, and a network planning parameter result is obtained; and then network parameter configuration is carried out on the application layer to realize satellite planning, station planning and terminal planning. According to the method, the total resource occupancy rate and the service capacity can be effectively improved, and meanwhile load balancing is achieved.
Owner:THE 54TH RESEARCH INSTITUTE OF CHINA ELECTRONICS TECHNOLOGY GROUP CORPORATION

Mobile communication network load prediction and scheduling method and system based on deep learning

The invention relates to the technical field of network load prediction and scheduling methods, in particular to a mobile communication network load prediction and scheduling method and system based on deep learning, and the method comprises the steps: obtaining data from a plurality of edge computing nodes, including base station data, user behavior data and environment parameter data; constructing a multi-layer model for load prediction and resource scheduling based on cooperative work of the central system and the edge system; carrying out feature extraction by utilizing a dynamic feature embedding transformation module in the edge computing node; recursive spatial-temporal feature processing is carried out based on the optimized features; generating a network load prediction result through the prediction model; and resource scheduling optimization is performed through a reinforcement learning model based on a prediction result, and multi-dimensional features are nested and mapped to a high-dimensional feature space through dynamic feature embedding of original data. And the nested features are further optimized through a time-varying collaborative tensor optimization algorithm, so that the spatial relevance between different base stations can be enhanced while complex nonlinear features are captured.
Owner:SOUTHWEST FORESTRY UNIVERSITY

Lightweight wisdom classroom learning behavior detection method and system

The invention belongs to the technical field of computer vision and artificial intelligence, and discloses a lightweight wisdom classroom learning behavior detection method and system, and the method comprises the steps: extracting student behavior features in a classroom image, and obtaining preliminary multi-scale features; designing a deep convolutional neural network to perform deep spatial-temporal feature representation on the extracted features, and introducing a focusing modulation module to enhance the features; designing a dynamic detection head to fuse and process features of different scales; and calculating the difference between a prediction result and a real label by using the optimized classification loss function and bounding box loss function, optimizing model parameters, and outputting a final student behavior detection result through the model. And finally, the system performs detailed analysis on the detected student behaviors and generates a visual classroom behavior report. According to the method, more accurate student behavior detection in a classroom scene is realized, a complex classroom environment and diversified student behavior modes can be effectively processed, and the method has relatively high practicability.
Owner:HUAZHONG NORMAL UNIV

Modularized intelligent identification and configuration system for portable Internet of Things electric energy metering box

The invention discloses a modularized intelligent identification and configuration system for a portable Internet of Things electric energy metering box, and relates to the technical field of Internet of Things. Electric energy data are collected in real time through an integrated sensor network, and are cleaned, compressed and preliminarily filtered by a data processing module; a deep learning algorithm is adopted to perform feature extraction and abnormal power consumption behavior detection on the data, and rapid response is ensured; a graphical operation interface is provided through the user interface module, and a user is allowed to update configuration immediately according to requirements; the link state is monitored through the LACP, the optimal link is automatically selected, and stable data transmission is ensured; temporarily storing data through a local cache and backup module when the network fluctuates, and automatically synchronizing the data to the cloud after the network is recovered; the system load is monitored through the self-adaptive optimization module, resource allocation is dynamically adjusted, and efficient and stable operation of the system is guaranteed; the data processing speed of the metering box equipment of the electric power internet of things is greatly improved, and the flexibility and the stability are enhanced.
Owner:HENAN ZHENGYU ELECTRIC CO LTD

Method for recycling waste polyester through acid-base concerted catalysis and methanol hydrolysis

The invention discloses an acid-base synergistic catalysis waste polyester methanolysis recovery method, which comprises the following steps: adding polyester waste plastics, an acidic auxiliary agent and a basic catalyst into methanol, and carrying out a depolymerization reaction to obtain dicarboxylic acid ester, the basic catalyst is strong alkali, acetate, phosphate, carbonate, pypocholoride, meta-aluminate, alkoxide or phenate. According to the method for directionally converting the waste polyester under the synergistic catalysis of the acid and the alkali, the rapid and mild degradation of the polyester waste plastic is successfully realized. The method not only improves the degradation efficiency, but also can obtain chemicals with high added value, and has the advantages of small pollution, strong controllability, green and cheap catalyst, low cost input and the like. In addition, a reaction system of the method is close to neutral, corrosion to equipment is low, safety and environmental protection are achieved, energy consumption is low, a brand new thought is provided for efficient waste polyester methanolysis recovery, and the method has extremely high industrial application value.
Owner:ZHEJIANG UNIV

Bifidobacterium longum subsp. Longum IMAU12449 and application thereof

The invention discloses bifidobacterium longum subsp. Longum IMAU12449 and application thereof, belongs to the technical field of microorganisms, and provides the bifidobacterium longum subsp. Longum IMAU12449, the bifidobacterium longum subsp. Longum IMAU12449 is preserved in the China General Microbiological Culture Collection Center on July 8, 2024, the preservation address is No. 3, No.1 yard, Beichen West Road, Chaoyang District, Beijing, and the preservation number is CGMCC NO. The preservation number is CGMCC (China General Microbiological Culture Collection Center) The invention provides application of the bifidobacterium longum subsp. Longum IMAU12449 in preparation of fermented cow milk and / or soybean milk. The bifidobacterium longum subsp. Longum IMAU12449 is used as a potential probiotic to prepare cow milk and soybean milk, and the prepared fermented milk is stable in viable count, moderate in acidity and free of whey precipitation.
Owner:INNER MONGOLIA AGRICULTURAL UNIVERSITY

Method and system for evaluating health state of offshore operation equipment

The invention relates to the technical field of equipment state evaluation, in particular to an evaluation method and system for the health state of offshore operation equipment. The method comprises the following steps: acquiring component data of offshore operation equipment; performing initial life marking on the data of the offshore operation equipment component to generate initial life marking data of the offshore operation equipment component; performing real-time operation data acquisition on the data of the offshore operation equipment component to generate real-time operation data of the offshore operation equipment component; performing component division on the real-time operation data of the components of the offshore operation equipment based on the components of the initial life mark data to generate novel component operation data and old component operation data; performing environment change influence analysis on the operation data of the novel part to generate an external change influence factor of the novel part. According to the invention, through multi-dimensional data acquisition, environment and electrical influence analysis, fatigue damage assessment and intelligent prediction, the accuracy of health state assessment of the offshore operation equipment is improved.
Owner:YANTAI UNIV +1

PCDN equipment detection method and device, computer equipment and storage medium

The invention relates to a PCDN equipment detection method and device, computer equipment and a storage medium. The method comprises the following steps: acquiring terminal information data; according to a preset analysis threshold value, the historical query data and the terminal information data, carrying out equipment confirmation on the to-be-identified equipment to obtain an equipment confirmation result; when the device confirmation result is that the to-be-identified device is confirmed to belong to the PCDN device, updating a feature library of the management platform based on the terminal information data to obtain an updated feature library, and generating an isolation blocking instruction; and transmitting the isolation blocking instruction and the updated feature library to the gateway terminal. By adopting the method, the security and management capability of the home network can be effectively improved, the PCDN equipment is accurately detected by collecting and analyzing the equipment flow information through the local plug-in and combining the characteristics and the cloud secondary identification, the false alarm and the missing alarm are reduced, the damage of malicious equipment to the home network is prevented, suspicious equipment is isolated or blocked in real time, and the safety of the home network is improved. And timely updating of the feature library is ensured.
Owner:E-SURFING DIGITAL LIFE TECH CO LTD

Office area people flow statistical method using Wi-Fi signal

The invention discloses an office area people flow statistical method using Wi-Fi signals, which belongs to the technical field of intelligent office management, abandons the traditional manual counting, automatic signal receiving and processing and real-time accurate data acquisition in terms of working efficiency, enables managers to concentrate on important work, optimizes space planning and resource allocation, and improves the working efficiency. The system can accurately count people flow density and speed, reasonably adjust facilities and space, enhance safety management, combine with an access control system, give an alarm prompt in case of difference, discover abnormity, provide multiple measures for data secrecy, protect privacy and sensitive information, have obvious cost advantages, do not need a large number of additional devices, reduce purchase and maintenance costs, and have wide coverage. The method is efficient, accurate, safe and low in cost, intelligent management of the office area is comprehensively improved, a good environment is created, and enterprise competitiveness and operation efficiency are improved.
Owner:FUJIAN WURONG SYSTEM INTEGRATION CO LTD

Tumor standardized whole-course management system based on digitization

The invention discloses a tumor standardized whole-course management system based on digitization, and relates to the technical field of medical information. Comprising a personnel management module, a system management module, a diagnosis and treatment specification module, a tumor specification diagnosis and treatment training and examination module, a TNM staging module, an anti-tumor drug prescription right oriented application module, an anti-tumor drug data real-time monitoring module, a tumor treatment medical record supervision module and a tumor medical conjoined module. According to the method, the working efficiency of a team is improved by managing the individual information and role authority of medical personnel, the treatment scheme is optimized by analyzing the TNM stage data, the information transparency is improved by submitting the prescription right application, and the anti-tumor drug use data of the tumor patient is monitored in real time, so that the anti-tumor effect of the patient is improved. The medical staff can know the use condition of the medicine, the medical records of the tumor patients are randomly selected for spot check, the medical record recording and processing quality is continuously improved, a medical conjoined platform interface is constructed, and the operation efficiency of the whole medical conjoined is improved.
Owner:RUIJIN HOSPITAL AFFILIATED TO SHANGHAI JIAO TONG UNIV SCHOOL OF MEDICINE

USB interface management and control method and device for information security protection

The invention relates to the technical field of data transmission, and discloses a USB interface management and control method and device for information security protection, and the method comprises the steps: recognizing a USB connection state, collecting the information of a to-be-connected device, and carrying out the identity verification; collecting a historical transmission task of the to-be-connected equipment, extracting a historical task index, and determining the available capacity of a transmission channel; a real-time transmission task is collected to determine real-time structure information and real-time content information, a transmission risk value is determined, and whether the available capacity of a transmission channel is adjusted or not is judged; when the adjustment is judged to be carried out, collecting a characteristic index, comparing the characteristic index with a historical adjustment scheme, and determining an adjustment coefficient according to a comparison result to adjust the available capacity of the transmission channel; and communicating the to-be-connected equipment with the workstation by using the adjusted available capacity of the transmission channel. According to the method, the information security protection capability is enhanced, and potential safety hazards and fault risks are reduced through resource scheduling and risk management.
Owner:北京网藤科技有限公司

Model training method and device, electronic equipment and storage medium

The invention provides a model training method and device, electronic equipment and a storage medium, and relates to the technical field of distributed computing. The method comprises the steps of dividing a context into context tasks based on structural analysis of a to-be-trained model; performing dependency relationship analysis on the context task to determine a task dependency graph; configuring priorities for the context tasks according to the task dependency graph, distributing the context tasks with the configured priorities to corresponding computing nodes, training according to an execution sequence, and obtaining load information and task execution information of the computing nodes; and according to the load information and the task execution information of the computing nodes, scheduling context tasks among the computing nodes, adjusting the execution sequence of the context tasks in the computing nodes, and outputting a training result. According to the real-time load condition of each node, task allocation is adjusted, load balancing of the computational nodes is realized, the utilization efficiency of computational resources is improved, a context task scheduling strategy is optimized, the utilization rate of the computational resources is improved, and the training time is shortened.
Owner:CHINA TELECOM CORP LTD TECHNOLOGY INNOVATION CENTER +1

Processing method of enzymolysis corn protein powder with high protein content

The invention discloses a high-protein-content enzymolysis corn protein powder processing method which comprises the following steps: S1, pretreatment: pretreating corn protein powder to obtain low-starch-content wet corn protein powder; s2, enzymolysis: starch in the corn protein powder is removed, the enzymolysis comprises I-segment enzymolysis and II-segment enzymolysis, one compound protease is firstly used for I-segment enzymolysis, and then the other compound protease is used for II-segment enzymolysis; and S3, spray drying: finally, spray drying is performed to generate the sectional type enzymolysis processing corn protein powder of the product, on one hand, the starch content in the corn protein powder is reduced, and the dosage limitation of the corn protein powder in aquatic feed is relieved; on the other hand, the corn protein powder is modified and added, most of prolamin and glutelin in the raw materials are changed into water-soluble protein and small peptide, and the animal utilization rate is greatly increased; in addition, the product can partially replace fish meal, so that feed resources are expanded, dependence on the fish meal is reduced, and the cost of an aquatic feed formula is also reduced.
Owner:QINGDAO YUANTONG SHENGLONG IND CO LTD +1

Synergistic flotation enrichment method for metal lithium gallium and kaolinite in coal gangue

The invention discloses a collaborative flotation enrichment method for metal lithium gallium and kaolinite in coal gangue, belongs to the technical field of coal series metal enrichment and extraction, and aims to solve the problems of difficulty in physical separation and enrichment and low separation efficiency of coal series metal lithium gallium in the prior art. The method comprises the following steps: roughing coal gangue in advance, and removing part of carbon-containing minerals to obtain a roughed material; ore grinding is conducted on tailings obtained after roughing, and materials obtained after ore grinding are obtained; decarburization flotation is conducted on the ground materials, and decarburization flotation materials are obtained; carrying out pyrite removal flotation on the decarburized and floated material to obtain a pyrite-removed and floated material; and performing quartz removal flotation on the material subjected to pyrite removal flotation. The method can be used for collaborative flotation enrichment of lithium gallium and kaolinite in coal gangue.
Owner:CHINA UNIV OF MINING & TECH

Membrane-free electrochemical calcium and magnesium selective removal and recovery system and method

The invention belongs to the technical field of electrochemistry, and relates to a membrane-free electrochemical calcium-magnesium selective removal and recovery system and method. The membrane-free electrochemical calcium-magnesium selective removal and recovery system comprises a water inlet tank, a direct-current power supply, an electrolytic bath, a water pump and a crystallization granulation column; the anode cylinder is internally provided with a porous cathode filter element, the anode of the direct-current power supply is electrically connected with the anode, and the cathode of the direct-current power supply is electrically connected with the porous cathode filter element; a water outlet of the water inlet tank is connected with the electrolytic bath, the top in the porous cathode filter element cylinder is communicated to the bottom of the crystallization granulation column, and a water outlet is formed in the upper part of the crystallization granulation column; a membrane-free electrochemical method is adopted, OH <-> is generated by pumping the porous cathode, and the problem of membrane pollution is completely avoided; by regulating and controlling electrochemical parameters and cathode configuration, the purpose of graded calcium and magnesium removal can be achieved, and meanwhile efficient recovery of calcium and magnesium ions can be achieved by combining with a crystallization and granulation system; the membrane-free design reduces the operation and maintenance cost of the system, and calcium and magnesium ions are efficiently removed and recycled in a graded manner, so that the economical efficiency of the process is improved.
Owner:XI AN JIAOTONG UNIV +1

Green edge computing task unloading and resource optimization method

The invention discloses a green edge computing task unloading and resource optimization method, which comprises the following steps of: acquiring task types of an intelligent port in processing, and classifying the task types by considering a time delay demand and an energy demand; establishing a network optimization resource model, processing the classified task types, and taking the minimum energy consumption and time delay satisfaction degree as a task unloading target; performing global optimization on a task unloading target based on a grey wolf algorithm to obtain an optimal network resource allocation solution; the method can dynamically adjust task allocation, reduce system energy consumption, optimize response speed of delay sensitive tasks, improve resource utilization efficiency of the system, reduce network load and improve task processing stability, is especially suitable for scenes with high energy efficiency requirements such as smart ports, and has high practicability.
Owner:JIANGSU MARITIME INST

Intelligent transportation device for logistics storage

The invention relates to the field of logistics transportation, in particular to an intelligent transportation device for logistics storage, comprising a roller conveyor body which is a telescopic roller conveyor; the roller conveyor body is provided with an electric conveying roller, a connecting rod and a connecting shaft; the device further comprises a connecting block, a two-way telescopic rod, a connecting piece, a sliding block, a connecting belt and a rotating rod. The end parts of the electric conveying rollers are rotationally connected with connecting blocks; a two-way telescopic rod is fixedly connected between every two adjacent connecting blocks, and the connecting blocks are fixedly connected with the fixing parts of the two-way telescopic rods. Two fixing parts of the bidirectional telescopic rod are fixedly connected with a connecting piece respectively; each of the two connecting pieces is fixedly connected with a sliding block; a connecting belt is connected between the two sliding blocks in a sliding mode. And a plurality of rotating rods are rotationally connected to the connecting belt. The telescopic roller conveyor effectively solves the problem that when an existing telescopic roller conveyor is stretched, the distance between adjacent electric conveying rollers is large, and only large objects can be conveyed.
Owner:ZHONGSHENG GROUP (TIANJIN) SUPPLY CHAIN MANAGEMENT CO LTD

Measurement-based quantum calculation method of physical drive variable component sub-character solver

The invention provides a measurement-based quantum calculation method for a physical driving variable component sub-character solicitation solver, and the method comprises the steps: S1, constructing a variational structure according to a Hamiltonian expression of a to-be-solved quantum multi-body system; s2, converting the variational structure into a graph state and a measurement mode corresponding to a measurement type quantum calculation scheme; s3, initializing an input state; s4, according to the designed measurement sequence, performing a series of single particle measurement on the graph state from the input state to obtain the output state of the variable component sub-line; and S5, continuously iteratively optimizing the variational parameters until the ground state energy of the target Hamiltonian is solved. According to the method, a variational structure is constructed from Hamiltonian of a problem to be solved, the advantages of single-particle measurement operation in measurement type quantum calculation are utilized, implementation of a multi-quantum-bit revolving door is simplified by introducing a small number of auxiliary quantum bits, and therefore quantum resource overhead of a quantum circuit is greatly reduced.
Owner:BEIHANG UNIV

Product production and processing intelligent scheduling method and system based on M0M system

The invention discloses a product production and processing intelligent scheduling method and system based on an M0M system, and relates to the technical field of product production and processing scheduling. Merchant live broadcast sales information of brand clothing in an e-commerce live broadcast platform is collected based on the M0M system, order information data is obtained, and production and processing conditions of manufacturers on clothing of different sizes are combined to obtain a product production and processing intelligent scheduling result. The method comprises the following steps: acquiring order information data, acquiring production information data, analyzing the order information data and the production information data to obtain an order production scheduling index Zjj of each merchant, determining and marking a merchant order needing priority production scheduling according to the size of the order production scheduling index Zjj, merging a plurality of marked orders into a priority production set order, and sending a resource analysis instruction. Through analyzing the size and quantity information and the cloth demand information data and combining with the residual cloth information data, the required original cloth purchase amount Ncg is obtained through fitting, and then a corresponding original cloth purchase plan is formulated.
Owner:SHENZHEN BANGQI MINE ELECTROMECHANICAL CO LTD

Unmanned aerial vehicle cluster collaborative search method based on adaptive division

The invention discloses an unmanned aerial vehicle cluster collaborative search method based on adaptive division, and the method comprises the following steps: 1, evaluating the performance of an unmanned aerial vehicle: evaluating the comprehensive performance of the unmanned aerial vehicle according to the index of the unmanned aerial vehicle, and obtaining a comprehensive performance index; step 2, task area distribution: distributing unmanned aerial vehicle task areas according to the comprehensive performance indexes; step 3, initial region division: a Voronoi graph algorithm is adopted to divide a task region; and 4, a dynamic adjustment mechanism: monitoring the state of the unmanned aerial vehicle in real time and re-dividing a task area by using a dynamic adaptive division mechanism. According to the method, the limitation of a traditional region division method in a dynamic complex environment is solved, the self-adaptive division and real-time adjustment of the search region are realized, the search efficiency is improved, the resource configuration is optimized, and the comprehensive completion of tasks is ensured.
Owner:杭州智元研究院有限公司

Face recognition method and access control equipment

The invention relates to the technical field of access control equipment. The invention provides a face recognition method and access control equipment, the face recognition method is applied to the access control equipment, and the access control equipment calls a second camera to collect a second original image when recognizing that the advancing speed of a to-be-recognized object is greater than a preset speed threshold value or the ambient brightness is smaller than a preset brightness threshold value; obtaining a face matching result of a first original image collected by the first camera and a second original image collected by the second camera by using a pre-trained twin network; and when the face recognition result is that the to-be-recognized object is matched with the face library and the face matching result is that the first original image is matched with the second original image, sending a control instruction to perform unlocking operation. According to the invention, the fast movement of the to-be-recognized object and the face recognition precision in the dark environment are improved.
Owner:SHENZHEN AOYAN TECH DEV CO LTD

Mobile robot performance system popularity racking method based on improved TabNet algorithm

The invention discloses a mobile robot performance system popularity racking method based on an improved TabNet algorithm. Comprising the following steps: collecting historical order data; the historical order data is preprocessed; a TabNet algorithm is improved, and a popularity model based on the improved TabNet algorithm is constructed; training a popularity model based on an improved TabNet algorithm by using the preprocessed data set, calculating a popularity score of each SKU, and performing real-time data updating and dynamic recalculation of the popularity score; and according to the SKU popularity score obtained through calculation, goods are put on different goods shelf areas. The invention provides a novel mobile robot performance system popularity shelving method based on an improved TabNet algorithm, so that high-popularity SKUs can be effectively identified and shelved in a concentrated manner through dynamic feature selection and a popularity scoring mechanism, thereby improving the order line hit rate of an RMFS system and optimizing the sorting efficiency.
Owner:NANJING UNIV OF POSTS & TELECOMM

Intelligent agent selection method, task processing method, device, equipment, medium and product

The invention relates to an agent selection method and device, a task processing method and device, equipment, a medium and a product. The method comprises the steps of obtaining a target task and preference information for the target task; decomposing the target task to obtain sub-tasks of the target task; obtaining capability labels of the candidate intelligent agents; the capability label comprises quantized values of a plurality of capability dimensions; according to a weight vector in the preference information, carrying out weighted calculation on the quantized numerical value of each capability dimension of the candidate intelligent agent to obtain a comprehensive score of the candidate intelligent agent; and based on the comprehensive score, selecting a target agent for executing the subtask from the candidate agents. By adopting the method, the resource utilization efficiency can be improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Intelligent monitoring and decision-making system and method for soil pollution remediation process

The invention relates to an intelligent monitoring and decision-making system for a soil pollution remediation process, and the system comprises a data collection layer which is used for collecting and uploading the data of a pollution remediation site; the data processing layer is used for receiving, cleaning, storing and managing data of a pollution remediation site; the analysis and decision-making layer is used for carrying out intelligent analysis such as pollution diffusion prediction, equipment state monitoring and restoration progress optimization on the data; and the user interface layer is used for remote monitoring, dynamic operation and information feedback of pollution remediation data and equipment states. According to the system, through cooperative work of the data acquisition layer, the data processing layer, the analysis and decision-making layer and the user interface layer, intelligent management and scientific decision-making of the soil pollution remediation process are achieved. The system collects on-site key data in real time through the Internet of Things, provides real-time monitoring, automatic control and decision support for pollution remediation projects by combining big data analysis and machine learning technologies, and ensures that the remediation process is efficient, low-carbon and safe.
Owner:CCCC TIANJIN ECO ENVIRONMENTAL PROTECTION DESIGN & RES INST CO LTD +2

Power grid equipment operation monitoring auxiliary system based on artificial intelligence

The invention relates to the technical field of power grid monitoring, and discloses a power grid equipment operation monitoring auxiliary system based on artificial intelligence, and the system comprises an equipment collection module which obtains all equipment data in a power grid monitoring area to generate equipment sets of different levels; the equipment data processing module determines a connection relation between the equipment sets, sets monitoring indexes and determines monitoring time of the equipment monitoring indexes; the monitoring module performs step-by-step monitoring according to the hierarchical sorting of the equipment set and formulates a monitoring strategy; and the early warning module carries out early warning reporting on the abnormal equipment. According to the invention, through comprehensive collection and classification of equipment data, all-directional and emphasized monitoring is realized, ordered monitoring is carried out according to levels, a result is output, through a preset threshold value and an anomaly detection algorithm, abnormal equipment is early warned and reported, distribution of monitoring resources is optimized, the occurrence probability of power failure accidents is reduced, and the power failure rate is improved. The monitoring capability, the early warning capability and the resource optimization capability of the system are improved, and the safety and the reliability of the overall operation of the power grid are enhanced.
Owner:STATE GRID ANHUI ELECTRIC POWER CO LTD +1

Power system unit commitment optimization scheduling method, device, equipment and medium

The invention belongs to the field of electric power system dispatching operation and control, and discloses an electric power system unit combination optimization dispatching method, device and equipment and a medium. The method comprises the following steps: acquiring a unit set G in a power system and characteristic parameters of each unit g in the unit set G; based on the characteristic parameters of each unit g, solving a pre-established power system unit combination model considering the multi-working-condition wide-power adjustment characteristics of the coal power unit, and obtaining a power system unit combination optimization scheduling result; and outputting the unit commitment optimization scheduling result of the power system. According to the invention, the supporting capability of the unit combination result on the multi-dimensional adjustment of the power system is enhanced; the method adapts to development and application of a novel power system.
Owner:CHINA ELECTRIC POWER RESEARCH INSTITUTE CO LTD +2